Merge pull request #20394 from open-webui/dev

0.7

.github/workflows/deploy-to-hf-spaces.yml

@@ -57,7 +57,8 @@ jobs:
           git lfs install
           git lfs track "*.ttf"
           git lfs track "*.jpg"
-          rm demo.gif
+          rm demo.png
+          rm banner.png
           git add .
           git commit -m "GitHub deploy: ${{ github.sha }}"
           git push --force https://open-webui:${HF_TOKEN}@huggingface.co/spaces/open-webui/open-webui main

.github/workflows/docker-build.yaml

@@ -141,6 +141,9 @@ jobs:
           platform=${{ matrix.platform }}
           echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
       - name: Checkout repository
         uses: actions/checkout@v5
 
@@ -243,6 +246,9 @@ jobs:
           platform=${{ matrix.platform }}
           echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
       - name: Checkout repository
         uses: actions/checkout@v5
 

.prettierignore

@@ -3,8 +3,6 @@ pnpm-lock.yaml
 package-lock.json
 yarn.lock
 
-kubernetes/
-
 # Copy of .gitignore
 .DS_Store
 node_modules

CHANGELOG.md

@@ -5,6 +5,438 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.7.0] - 2026-01-09
+
+### Added
+
+- 🤖 **Native Function Calling with Built-in Tools.** Users can now ask models to perform multi-step tasks that combine web research, knowledge base queries, note-taking, and image generation in a single conversation—for example, "research the latest on X, save key findings to a note, and generate an infographic." Requires models with native function calling support and function calling mode set to "Native" in Chat Controls. [#19397](https://github.com/open-webui/open-webui/issues/19397), [Commit](https://github.com/open-webui/open-webui/commit/5c1d52231a3997a17381c48639bd7e339262cf7c)
+- 🧠 Users can now ask the model to find relevant context from their notes, past chats, and channel messages—for example, "what did I discuss about project X last week?" or "find the conversation where I brainstormed ideas for Y." [Commit](https://github.com/open-webui/open-webui/commit/646835d76744ad9b2e67ede0407a61d62e969aab)
+- 📚 Users can now ask the model to search their knowledge bases and retrieve documents without manually attaching files—for example, "find the section about authentication in our API docs" or "what do our internal guidelines say about X?" [Commit](https://github.com/open-webui/open-webui/commit/c8622adcb01f3091b17ca50f8c8e2f20c7b9cd2a)
+- 💭 Users with models that support interleaved thinking now get more refined results from multi-step workflows, as the model can analyze each tool's output before deciding what to do next.
+- 🔍 When models invoke web search, search results appear as clickable citations in real-time for full source verification. [Commit](https://github.com/open-webui/open-webui/commit/2789f6a24d8405c30cd48ae460071f6a4f2c35f9)
+- 🎚️ Users can selectively disable specific built-in tools (timestamps, memory, chat history, notes, web search, knowledge bases) per model via the model editor's capabilities settings. [Commit](https://github.com/open-webui/open-webui/commit/60e916d6c0c5f7db9e6d670e12be2d1d4abc2dd6)
+- 👁️ Pending tool calls are now displayed during response generation, so users know which tools are being invoked. [Commit](https://github.com/open-webui/open-webui/commit/1d08376860e775049abd1dd5f568ac0c6466c944)
+- 📁 Administrators can now limit the number of files that can be uploaded to folders using the "FOLDER_MAX_FILE_COUNT" setting, preventing resource exhaustion from bulk uploads. [#19810](https://github.com/open-webui/open-webui/issues/19810), [Commit](https://github.com/open-webui/open-webui/commit/a1036e544d573e3d35e05c1c2472ba762c32431b), [Commit](https://github.com/open-webui/open-webui/commit/d3ee3fd23e762c9d83fe1da5636d03259e186e57)
+- ⚡ Users experience transformative speed improvements across the entire application through completely reengineered database connection handling, delivering noticeably faster page loads, butter-smooth interactions, and rock-solid stability during intensive operations like user management and bulk data processing. [Commit](https://github.com/open-webui/open-webui/commit/2041ab483e21b3a757baa25c47dc2fa29018674f), [Commit](https://github.com/open-webui/open-webui/commit/145c7516f227ce56fd52373cee86217fadf16181), [Commit](https://github.com/open-webui/open-webui/commit/475dd91ed798f2efcdf27799d5c5cae3f0e6e847), [Commit](https://github.com/open-webui/open-webui/commit/5d1459df166cce8445eb1556cc26abbd65a3f9f4), [Commit](https://github.com/open-webui/open-webui/commit/2453b75ff0fb2dc75b929d96f417d84e332922d9), [Commit](https://github.com/open-webui/open-webui/commit/5649a668fad15393a52c27a2f188841af8b66989)
+- 🚀 Users experience significantly faster initial page load times through dynamic loading of document processing libraries, reducing the initial bundle size. [#20200](https://github.com/open-webui/open-webui/pull/20200), [#20202](https://github.com/open-webui/open-webui/pull/20202), [#20203](https://github.com/open-webui/open-webui/pull/20203), [#20204](https://github.com/open-webui/open-webui/pull/20204)
+- 💨 Administrators experience dramatically faster user list loading through optimized database queries that eliminate N+1 query patterns, reducing query count from 1+N to just 2 total queries regardless of user count. [#20427](https://github.com/open-webui/open-webui/pull/20427)
+- 📋 Notes now load faster through optimized database queries that batch user lookups instead of fetching each note's author individually. [Commit](https://github.com/open-webui/open-webui/commit/084f0ef6a5491e186bf6b71c6386973ba18ef2fa)
+- 💬 Channel messages, pinned messages, and thread replies now load faster through batched user lookups instead of individual queries per message. [#20458](https://github.com/open-webui/open-webui/pull/20458), [#20459](https://github.com/open-webui/open-webui/pull/20459), [#20460](https://github.com/open-webui/open-webui/pull/20460)
+- 🔗 Users can now click citation content links to jump directly to the relevant portion of source documents with automatic text highlighting, making it easier to verify AI responses against their original sources. [#20116](https://github.com/open-webui/open-webui/pull/20116), [Commit](https://github.com/open-webui/open-webui/commit/40c45ffe1f9b45538d32c8ecba8cac62c6eca503)
+- 📌 Users can now pin or hide models directly from the Workspace Models page and Admin Settings Models page, making it easier to manage which models appear in the sidebar without switching to the chat interface. [#20176](https://github.com/open-webui/open-webui/pull/20176)
+- 🔎 Administrators can now quickly find settings using the new search bar in the Admin Settings sidebar, which supports fuzzy filtering by category names and related keywords like "whisper" for Audio or "rag" for Documents. [#20434](https://github.com/open-webui/open-webui/pull/20434)
+- 🎛️ Users can now view read-only models in the workspace models list, with clear "Read Only" badges indicating when editing is restricted. [#20243](https://github.com/open-webui/open-webui/issues/20243), [#20369](https://github.com/open-webui/open-webui/pull/20369)
+- 📝 Users can now view read-only prompts in the workspace prompts list, with clear "Read Only" badges indicating when editing is restricted. [#20368](https://github.com/open-webui/open-webui/pull/20368)
+- 🔧 Users can now view read-only tools in the workspace tools list, with clear "Read Only" badges indicating when editing is restricted. [#20243](https://github.com/open-webui/open-webui/issues/20243), [#20370](https://github.com/open-webui/open-webui/pull/20370)
+- 📂 Searching for files is now significantly faster, especially for users with large file collections. [Commit](https://github.com/open-webui/open-webui/commit/a9a979fb3db1743553ca0705f571c0b9c252841f)
+- 🏆 The Evaluations leaderboard now calculates Elo ratings on the backend instead of in the browser, improving performance and enabling topic-based model ranking through semantic search. [#15392](https://github.com/open-webui/open-webui/pull/15392), [#20476](https://github.com/open-webui/open-webui/issues/20476), [Commit](https://github.com/open-webui/open-webui/commit/10838b3654bf6fdef02d57311f7f1c01df4cd033)
+- 📊 The Evaluations leaderboard now includes a per-model activity chart displaying daily wins and losses as a diverging bar chart, with 30-day, 1-year, and all-time views using weekly aggregation for longer timeframes.
+- 🎞️ Users can now upload animated GIF and WebP formats as model profile images, with animation preserved by skipping resize processing for these file types. [Commit](https://github.com/open-webui/open-webui/commit/00af37bb4ed1ea0957c7c84a6a8def3a7998b8ca)
+- 📸 Users uploading profile images for users, models, and arena models now benefit from WebP compression at 80% quality instead of JPEG, resulting in significantly smaller file sizes and faster uploads while maintaining visual quality. [Commit](https://github.com/open-webui/open-webui/commit/b1d30673b69571e081abb881d34944cf33cdc67e)
+- ⭐ Action Function developers can now update message favorite status using the new "chat:message:favorite" event, enabling the development of pin/unpin message actions without race conditions from frontend auto-save. [#20375](https://github.com/open-webui/open-webui/pull/20375)
+- 🌐 Users with OpenAI-compatible models that have web search capabilities now see URL citations displayed as sources in the interface. [#20172](https://github.com/open-webui/open-webui/pull/20172), [Commit](https://github.com/open-webui/open-webui/commit/fe84afd09a2bc8a89311f30186ec2608a4edda3a)
+- 📰 Users can now dismiss the "What's New" changelog modal permanently using the X button, matching the behavior of the "Okay, Let's Go!" button. [#20258](https://github.com/open-webui/open-webui/pull/20258)
+- 📧 Administrators can now configure the admin contact email displayed in the Account Pending overlay directly from the Admin Panel instead of only through environment variables. [#12500](https://github.com/open-webui/open-webui/issues/12500), [#20260](https://github.com/open-webui/open-webui/pull/20260)
+- 📄 Administrators can now enable markdown header text splitting as a preprocessing step that works with either character or token splitting, through the new "ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER" setting. [Commit](https://github.com/open-webui/open-webui/commit/d3a682759f375c6cb0bc8c170f62863a070f712e), [Commit](https://github.com/open-webui/open-webui/commit/18a33a079bf07487edffc421a721c86194cc90c9), [Commit](https://github.com/open-webui/open-webui/commit/08bf4670ec862018f9dc57296cb19fd5eab14ef6)
+- 🧩 Administrators can now set a minimum chunk size target using the "CHUNK_MIN_SIZE_TARGET" setting to merge small markdown header chunks with neighbors, which improves retrieval quality by eliminating tiny meaningless fragments, significantly speeds up document processing and embedding, reduces storage costs, and lowers embedding API costs or local compute requirements. [#19595](https://github.com/open-webui/open-webui/issues/19595), [#20314](https://github.com/open-webui/open-webui/pull/20314), [Commit](https://github.com/open-webui/open-webui/commit/c32435958073cf002d87e78544baa88bc4e15d7f)
+- 💨 Administrators can now enable KV prefix caching optimization by setting "RAG_SYSTEM_CONTEXT" to true, which injects RAG context into the system message instead of user messages, enabling models to reuse cached tokens for follow-up questions instead of reprocessing the entire context on each turn, significantly improving response times and reducing costs for cloud-based models. [#20301](https://github.com/open-webui/open-webui/discussions/20301), [#20317](https://github.com/open-webui/open-webui/pull/20317)
+- 🖼️ Administrators and Action developers can now control image generation denoising steps per-request using a steps parameter, allowing Actions and API calls to override the global IMAGE_STEPS configuration for both ComfyUI and Automatic1111 engines. [#20337](https://github.com/open-webui/open-webui/pull/20337)
+- 🗄️ Administrators running multi-pod deployments can now designate a master pod to handle database migrations using the "ENABLE_DB_MIGRATIONS" environment variable. [Commit](https://github.com/open-webui/open-webui/commit/9824f0e33359a917ac07b60bf1f972074d5c8203)
+- 🎙️ Administrators can now configure Whisper's compute type using the "WHISPER_COMPUTE_TYPE" environment variable to fix compatibility issues with CUDA/GPU deployments. [Commit](https://github.com/open-webui/open-webui/commit/26af1f92e21ddfd08348570bf54a6f345ac69648)
+- 🔍 Administrators can now control sigmoid normalization for CrossEncoder reranking models using the "SENTENCE_TRANSFORMERS_CROSS_ENCODER_SIGMOID_ACTIVATION_FUNCTION" environment variable, enabled by default for proper relevance threshold behavior with MS MARCO models. [#20228](https://github.com/open-webui/open-webui/pull/20228)
+- 🔒 Administrators can now disable SSL certificate verification for external tools using the "REQUESTS_VERIFY" environment variable, enabling integration with self-signed certificates for Tika, Ollama embeddings, and external rerankers. [#19968](https://github.com/open-webui/open-webui/issues/19968), [Commit](https://github.com/open-webui/open-webui/commit/dfc5dad63167eabb7fb027e63c324675b23f2e9d)
+- 📈 Administrators can now control audit log output destinations using "ENABLE_AUDIT_STDOUT" and "ENABLE_AUDIT_LOGS_FILE" environment variables, allowing audit logs to be sent to container logs for centralized logging systems. [#20114](https://github.com/open-webui/open-webui/pull/20114), [Commit](https://github.com/open-webui/open-webui/commit/fdae5644e36972384b3e2513e3074f95f9f7381f)
+- 🛡️ Administrators can now restrict non-admin user access to Interface Settings through per-user or per-group permissions. [#20424](https://github.com/open-webui/open-webui/pull/20424)
+- 🧠 Administrators can now globally enable or disable the Memories feature and control access through per-user or per-group permissions, with the Personalization tab automatically hidden when the feature is disabled. [#20462](https://github.com/open-webui/open-webui/pull/20462)
+- 🟢 Administrators can now globally enable or disable user status visibility through the "ENABLE_USER_STATUS" setting in Admin Settings. [#20488](https://github.com/open-webui/open-webui/pull/20488)
+- 🪝 Channel managers can now create webhooks to allow external services to post messages to channels without authentication. [Commit](https://github.com/open-webui/open-webui/commit/cd296fcf0d79cecd1a6a3ee4e492c6b5246ca7ae)
+- 📄 In the model editor users can now disable the "File Context" capability to skip automatic file content extraction and injection, forwarding raw messages with file attachment metadata instead for use with custom tools or future built-in file access tools. [Commit](https://github.com/open-webui/open-webui/commit/daccf0713e3ecd6d24f003a87b5f8b3c61852958), [Docs:Commit](https://github.com/open-webui/docs/commit/18ec6eaefc071a278ec57d4d1b8d66d686af0870)
+- 🔊 In the model editor users can now configure a specific TTS voice for each model, overriding user preferences and global defaults to give different AI personas distinct voices. [#3097](https://github.com/open-webui/open-webui/issues/3097), [Commit](https://github.com/open-webui/open-webui/commit/bb6188abf04302f79d80b0d6cc42c232624b5757)
+- 👥 Administrators now have three granular group sharing permission options instead of a simple on/off toggle, allowing them to choose between "No one", "Members", or "Anyone" for who can share content to each group. [Commit](https://github.com/open-webui/open-webui/commit/ca514cd3eda2524b8da472ef17c0ccb216bac2e8)
+- 📦 Administrators can now export knowledge bases as zip files containing text files for backup and archival purposes. [#20120](https://github.com/open-webui/open-webui/issues/20120), [Commit](https://github.com/open-webui/open-webui/commit/c1147578c073a8c7fa7e7f836149e1cdfec8f18d)
+- 🚀 Administrators can now create an admin account automatically at startup via "WEBUI_ADMIN_EMAIL", "WEBUI_ADMIN_PASSWORD", and "WEBUI_ADMIN_NAME" environment variables, enabling headless and automated deployments without exposing the signup page. [#17654](https://github.com/open-webui/open-webui/issues/17654), [Commit](https://github.com/open-webui/open-webui/commit/1138929f4d083931305f1f925899971b190562ae)
+- 🦆 Administrators can now select a specific search backend for DDGS instead of random selection, with options including Bing, Brave, DuckDuckGo, Google, Wikipedia, Yahoo, and others. [#20330](https://github.com/open-webui/open-webui/issues/20330), [#20366](https://github.com/open-webui/open-webui/pull/20366)
+- 🧭 Administrators can now configure custom Jina Search API endpoints using the "JINA_API_BASE_URL" environment variable, enabling region-specific deployments such as EU data processing. [#19718](https://github.com/open-webui/open-webui/pull/19718), [Commit](https://github.com/open-webui/open-webui/commit/f7f8a263b92289df8d4f8dbc3bae09bd009a5699)
+- 🔥 Administrators can now configure Firecrawl timeout values using the "FIRECRAWL_TIMEOUT" environment variable to control web scraping wait times. [#19973](https://github.com/open-webui/open-webui/pull/19973), [Commit](https://github.com/open-webui/open-webui/commit/89ad1c68d1aadf849960b5e202aa4651096b05f5)
+- 💾 Administrators can now use openGauss as the vector database backend for knowledge base document storage and retrieval. [#20179](https://github.com/open-webui/open-webui/pull/20179)
+- 🔄 Various improvements were implemented across the application to enhance performance, stability, and security.
+- 📊 Users can now sync their anonymous usage statistics to the Open WebUI Community platform to power community leaderboards, drive model evaluations, and contribute to open-source AI research that benefits everyone, all while keeping conversations completely private (only metadata like model names, message counts, and ratings are shared). By sharing your stats, you're helping the community identify which models perform best, contributing to transparent AI benchmarking, and supporting the collective effort to make AI better for all. You can also download your stats as JSON for personal analysis.
+- 🌐 Translations for German, Portuguese (Brazil), Spanish, Simplified Chinese, Traditional Chinese, and Polish were enhanced and expanded.
+
+### Fixed
+
+- 🔊 Text-to-speech now correctly splits on newlines in addition to punctuation, so markdown bullet points and lists are spoken as separate sentences instead of being merged together. [#5924](https://github.com/open-webui/open-webui/issues/5924), [Commit](https://github.com/open-webui/open-webui/commit/869108a3e1ce2b8110084113c1b392072e98fd5f)
+- 🔒 Users are now protected from stored XSS vulnerabilities in iFrame embeds for citations and response messages through configurable same-origin sandbox settings instead of hardcoded values. [#20209](https://github.com/open-webui/open-webui/pull/20209), [#20210](https://github.com/open-webui/open-webui/pull/20210)
+- 🔑 Image Generation, Web Search, and Audio (TTS/STT) API endpoints now enforce permission checks on the backend, closing a security gap where disabled features could previously be accessed via direct API calls. [#20471](https://github.com/open-webui/open-webui/pull/20471)
+- 🛠️ Tools and Tool Servers (MCP and OpenAPI) now enforce access control checks on the backend, ensuring users can only access tools they have permission to use even via direct API calls. [#20443](https://github.com/open-webui/open-webui/issues/20443), [Commit](https://github.com/open-webui/open-webui/commit/9b06fdc8fe1c933071610336be05f11e77e6c8eb)
+- 🔁 System prompts are no longer duplicated when using native function calling, fixing an issue where the prompt would be applied twice during tool-calling workflows. [Commit](https://github.com/open-webui/open-webui/commit/9223efaff0db6e56bfa157ef214d9590005156d2)
+- 🗂️ Knowledge base uploads to folders no longer fail when "FOLDER_MAX_FILE_COUNT" is unset, fixing an issue where the default null value caused all uploads to error. [Commit](https://github.com/open-webui/open-webui/commit/ef9cd0e0ad6e45b8a3efec6f3858b3d69d42f619)
+- 📝 The "Create Note" button in the chat input now correctly hides for users without Notes permissions instead of showing and returning a 401 error when clicked. [#20486](https://github.com/open-webui/open-webui/issues/20486), [Commit](https://github.com/open-webui/open-webui/commit/9e9616b670c1c4389193b18500a7d80d86d7e280)
+- 📊 The Evaluations page no longer crashes when administrators have large amounts of feedback data, as the leaderboard now fetches only the minimal required fields instead of loading entire conversation snapshots. [#20476](https://github.com/open-webui/open-webui/issues/20476), [#20489](https://github.com/open-webui/open-webui/pull/20489), [Commit](https://github.com/open-webui/open-webui/commit/b2a1f71d920e55b143f1c02e61104938d2588762)
+- 💬 Users can now export chats, use the Ask/Explain popup, and view chat lists correctly again after these features were broken by recent refactoring changes that caused 500 and 400 server errors. [#20146](https://github.com/open-webui/open-webui/issues/20146), [#20205](https://github.com/open-webui/open-webui/issues/20205), [#20206](https://github.com/open-webui/open-webui/issues/20206), [#20212](https://github.com/open-webui/open-webui/pull/20212)
+- 💭 Users no longer experience data corruption when switching between chats during background operations like image generation, where messages from one chat would appear in another chat's history. [#20266](https://github.com/open-webui/open-webui/pull/20266)
+- 🛡️ Users no longer encounter critical chat stability errors, including duplicate key errors from circular message dependencies, null message access during chat loading, and errors in the chat overview visualization. [#20268](https://github.com/open-webui/open-webui/pull/20268)
+- 📡 Users with Channels no longer experience infinite recursion and connection pool exhaustion when fetching threaded replies, preventing RecursionError crashes during chat history loading. [#20299](https://github.com/open-webui/open-webui/pull/20299), [Commit](https://github.com/open-webui/open-webui/commit/c144122f608759c2b79472e1f6948a7c1600a3d1)
+- 📎 Users no longer encounter TypeError crashes when viewing messages with file attachments that have undefined URL properties. [#20343](https://github.com/open-webui/open-webui/pull/20343)
+- 🔐 Users with MCP integrations now experience reliable OAuth 2.1 token refresh after access token expiration through proper Protected Resource discovery, preventing integration failures that caused sessions to be deleted. [#19794](https://github.com/open-webui/open-webui/issues/19794), [#20138](https://github.com/open-webui/open-webui/pull/20138), [#20291](https://github.com/open-webui/open-webui/issues/20291), [Commit](https://github.com/open-webui/open-webui/commit/bf2b2962399e341926bdbf9e0a82101f31a90b23), [Commit](https://github.com/open-webui/open-webui/commit/89565c58c6ae6b5b129559ef68b5a0c18c110765)
+- 📚 Users who belong to multiple groups can now see Knowledge Bases shared with those groups, fixing an issue where they would disappear when shared with more than one group. [#20124](https://github.com/open-webui/open-webui/issues/20124), [#20229](https://github.com/open-webui/open-webui/issues/20229), [Commit](https://github.com/open-webui/open-webui/commit/61e25dc2dce9c12dcb5b88a6b814060c4338e67b)
+- 📂 Users now see the correct Knowledge Base name when hovering over # file references in chat input instead of "undefined". [#20329](https://github.com/open-webui/open-webui/issues/20329), [#20333](https://github.com/open-webui/open-webui/pull/20333)
+- 📋 Users now see notes displayed in correct chronological order within their time range groupings, fixing an issue where insertion order was not preserved. [Commit](https://github.com/open-webui/open-webui/commit/3f577c0c3fbfd9f09c02940e4ae474f987149277)
+- 📑 Users collaborating on notes now experience proper content sync when initializing from both HTML and JSON formats, fixing sync failures in collaborative editing sessions. [Commit](https://github.com/open-webui/open-webui/commit/e27fb3e291a735c715a089a80e7a49d2c2209096)
+- 🔎 Users searching notes can now find hyphenated words and variations with spaces, so searching "todo" now finds "to-do" and "to do". [Commit](https://github.com/open-webui/open-webui/commit/a3270648d8b8535443d8ce2ea719f8e678e4e358)
+- 📥 Users no longer experience false duplicate file warnings when reuploading files after initial processing failed, as the file hash is now only stored after successful processing completion. [#19264](https://github.com/open-webui/open-webui/issues/19264), [#20282](https://github.com/open-webui/open-webui/pull/20282), [Commit](https://github.com/open-webui/open-webui/commit/d3ab9f4b96eee7f91c9b1355cee055fdabca9730)
+- 💾 Users experience significantly improved page load performance as model profile images now cache properly in browsers, avoiding unnecessary image refetches. [Commit](https://github.com/open-webui/open-webui/commit/bb821ab654e93908a3b4632c359753eeff053264)
+- 🎨 Users can now successfully edit uploaded images instead of having new images generated, fixing an issue introduced by the file storage refactor where images with type "file" and content_type starting with "image/" weren't being recognized as editable images. [#20237](https://github.com/open-webui/open-webui/issues/20237), [#20169](https://github.com/open-webui/open-webui/pull/20169), [#20239](https://github.com/open-webui/open-webui/pull/20239), [Commit](https://github.com/open-webui/open-webui/commit/1148d1c927d096e14917b6d762789fca3188f281)
+- 🌐 Users writing in Persian and Arabic now see properly displayed right-to-left text in the notes section through automatic text direction detection. [#19743](https://github.com/open-webui/open-webui/issues/19743), [#20102](https://github.com/open-webui/open-webui/pull/20102), [Commit](https://github.com/open-webui/open-webui/commit/b619a157bc54c5bc44d223d2ae3acb9ce4ac6a6c)
+- 🤖 Users can now successfully @ mention models in Channels instead of experiencing silent failures. [Commit](https://github.com/open-webui/open-webui/commit/59957715836acb635f4b1c4ddbfb4ba7b82b3281)
+- 📋 Users on Windows now see correctly preserved line breaks when using the {{CLIPBOARD}} variable through CRLF to LF normalization. [#19370](https://github.com/open-webui/open-webui/issues/19370), [#20283](https://github.com/open-webui/open-webui/pull/20283)
+- 📁 Users now see the Knowledge Selector dropdown correctly displayed above the Create Folder modal instead of being hidden behind it. [#20219](https://github.com/open-webui/open-webui/issues/20219), [#20213](https://github.com/open-webui/open-webui/pull/20213)
+- 🌅 Users now see profile images in non-PNG formats like SVG, JPEG, and GIF displayed correctly instead of appearing broken. [#20171](https://github.com/open-webui/open-webui/pull/20171)
+- 🆕 Non-admin users with disabled temporary chat permissions can now successfully create new chats and use pinned models from the sidebar. [#20336](https://github.com/open-webui/open-webui/issues/20336), [#20367](https://github.com/open-webui/open-webui/pull/20367), [Commit](https://github.com/open-webui/open-webui/commit/e754940c031f9689fb4f6edb3625aa06aeb53377)
+- 🎛️ Users can now successfully use workspace models in chat, fixing "Model not found" errors that occurred when using custom model presets. [#20340](https://github.com/open-webui/open-webui/issues/20340), [#20344](https://github.com/open-webui/open-webui/pull/20344), [Commit](https://github.com/open-webui/open-webui/commit/b55a46ae99c32068ed306a5ecdaafa9f75504cd7), [Commit](https://github.com/open-webui/open-webui/commit/2bb13d5dbc6e233856e8aa26143222ceda8f6c11)
+- 🔁 Users can now regenerate messages without crashes when the parent message is missing or corrupted in the chat history. [#20264](https://github.com/open-webui/open-webui/pull/20264)
+- ✏️ Users no longer experience TipTap rich text editor crashes with "editor view is not available" errors when plugins or async methods try to access the editor after it has been destroyed. [#20266](https://github.com/open-webui/open-webui/pull/20266)
+- 📗 Administrators with bypass access control enabled now correctly have write access to all knowledge bases. [#20371](https://github.com/open-webui/open-webui/pull/20371)
+- 🔍 Administrators using local CrossEncoder reranking models now see proper relevance threshold behavior through MS MARCO model score normalization to the 0-1 range via sigmoid activation. [#19999](https://github.com/open-webui/open-webui/issues/19999), [#20228](https://github.com/open-webui/open-webui/pull/20228)
+- 🎯 Administrators using local SentenceTransformers embedding engine now benefit from proper batch size settings, preventing excessive memory usage from the default batch size of 32. [#20053](https://github.com/open-webui/open-webui/issues/20053), [#20054](https://github.com/open-webui/open-webui/pull/20054), [Commit](https://github.com/open-webui/open-webui/commit/e4a5b06ca68303512678b4d2dc296bc78b9f983f)
+- 🔧 Administrators and users in offline mode or restricted environments like uv, poetry, and NixOS no longer experience crashes when Tools and Functions have frontmatter requirements, as pip installation is now skipped when offline mode is enabled. [#20320](https://github.com/open-webui/open-webui/issues/20320), [#20321](https://github.com/open-webui/open-webui/pull/20321), [Commit](https://github.com/open-webui/open-webui/commit/bd07ef8)
+- 📄 Administrators can now properly configure the MinerU document parsing service as the MinerU Cloud API key field is now available in the Admin Panel Documents settings. [#20319](https://github.com/open-webui/open-webui/issues/20319), [#20328](https://github.com/open-webui/open-webui/pull/20328)
+- ⚠️ Administrators no longer see SyntaxWarnings for invalid escape sequences in password validation regex patterns. [#20298](https://github.com/open-webui/open-webui/pull/20298), [Commit](https://github.com/open-webui/open-webui/commit/e55bf2c2ac391caed871d41f0484820091081908)
+- 🎨 Users with ComfyUI workflows now see only the intended final output images in chat instead of duplicate images from intermediate processing nodes like masks, crops, or segmentation previews. [#20158](https://github.com/open-webui/open-webui/issues/20158), [#20182](https://github.com/open-webui/open-webui/pull/20182)
+- 🖼️ Users with image generation enabled no longer see false vision capability warnings, allowing them to send follow-up messages after generating images and to send images to non-vision models for image editing. [#20129](https://github.com/open-webui/open-webui/issues/20129), [#20256](https://github.com/open-webui/open-webui/pull/20256)
+- 🔌 Administrators no longer experience infinite loading screens when invalid or MCP-style configurations are used with OpenAPI connection types for external tools. [#20207](https://github.com/open-webui/open-webui/issues/20207), [#20257](https://github.com/open-webui/open-webui/pull/20257)
+- 📥 Administrators no longer encounter TypeError crashes during SHA256 verification when uploading GGUF models via URL, fixing 500 Internal Server Error crashes. [#20263](https://github.com/open-webui/open-webui/issues/20263)
+- 🚦 Users with Brave Search now experience automatic retry with a 1-second delay when hitting rate limits, preventing failures when sequential requests exceed the 1 request per second limit, though this only works reliably when web search concurrency is set to a maximum of 1. [#15134](https://github.com/open-webui/open-webui/issues/15134), [#20255](https://github.com/open-webui/open-webui/pull/20255)
+- 🗄️ Administrators with Redis Sentinel deployments no longer experience crashes during websocket disconnections due to improper async-generator handling in the YDocManager. [#20142](https://github.com/open-webui/open-webui/issues/20142), [#20145](https://github.com/open-webui/open-webui/pull/20145)
+- 🔐 Administrators using SCIM group management no longer encounter 500 errors when working with groups that have no members. [#20187](https://github.com/open-webui/open-webui/pull/20187)
+- 🔗 Users now experience more reliable citations from AI models, especially when using smaller or weaker models that may not format citation references perfectly. [Commit](https://github.com/open-webui/open-webui/commit/c0ec04935b4eea3d334bfdec2fc41278f1085a49)
+- 🕸️ Administrators can now successfully save WebSearch settings without encountering validation errors for domain filter lists, YouTube language settings, or timeout values. [#20422](https://github.com/open-webui/open-webui/pull/20422)
+- 📦 Administrators installing with the uv package manager now experience successful installation after deprecated dependencies that were causing conflicts were removed. [#20177](https://github.com/open-webui/open-webui/issues/20177), [#20192](https://github.com/open-webui/open-webui/pull/20192)
+- ⏱️ Administrators using custom "AIOHTTP_CLIENT_TIMEOUT" settings now see the configured timeout correctly applied to embedding generation, OAuth discovery, webhook calls, and tool/function loading instead of falling back to the default 300-second timeout. [Commit](https://github.com/open-webui/open-webui/commit/e67891a374625d9888ec391da561f0b4ed79ed5d)
+
+### Changed
+
+- ⚠️ This release includes a major overhaul of database connection handling in the backend that requires all instances in multi-worker, multi-server, or load-balanced deployments to be updated simultaneously; running mixed versions will cause failures due to incompatible database connection management between old and new instances.
+- 📝 Administrators who previously used the standalone "Markdown (Header)" text splitter must now switch to "character" or "token" mode with the new "ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER" toggle enabled, as document chunking now applies markdown header splitting as a preprocessing step before character or token splitting. [Commit](https://github.com/open-webui/open-webui/commit/d3a682759f375c6cb0bc8c170f62863a070f712e), [Commit](https://github.com/open-webui/open-webui/commit/18a33a079bf07487edffc421a721c86194cc90c9), [Commit](https://github.com/open-webui/open-webui/commit/08bf4670ec862018f9dc57296cb19fd5eab14ef6)
+- 🖼️ Users no longer see the "Generate Image" action button in chat message interfaces; custom function should be used. [Commit](https://github.com/open-webui/open-webui/commit/f0829ba6e6fd200702fb76efc43dd785cf87fec9)
+- 🔗 Administrators will find the Admin Evaluations page at the new URL "/admin/evaluations/feedback" instead of "/admin/evaluations/feedbacks" to use the correct uncountable form of the word. [#20296](https://github.com/open-webui/open-webui/pull/20296)
+- 🔐 Scripts or integrations that directly called Image Generation, Web Search, or Audio APIs while those features were disabled in the Admin UI will now receive 403 Forbidden errors, as backend permission enforcement has been added to match frontend restrictions. [#20471](https://github.com/open-webui/open-webui/pull/20471)
+- 👥 The default group sharing permission changed from "Members" to "Anyone", meaning users can now share content to any group configured with "Anyone" permission regardless of their membership in that group. [Commit](https://github.com/open-webui/open-webui/commit/ca514cd3eda2524b8da472ef17c0ccb216bac2e8)
+
+## [0.6.43] - 2025-12-22
+
+### Fixed
+
+- 🐍 **Python dependency installation issues** were resolved by correcting pip dependency handling, preventing installation failures in certain environments and improving setup reliability. [Commit](https://github.com/open-webui/open-webui/commit/5c5f87a)
+- 🎙️ **Speech-to-Text default content type handling** was fixed and refactored to ensure correct MIME type usage, improving compatibility across STT providers and preventing transcription errors caused by incorrect defaults. [Commit](https://github.com/open-webui/open-webui/commit/4ab917c)
+- 🖼️ **Temporary chat image handling** was fixed and refactored, ensuring images generated or edited in temporary chats are correctly processed, stored, and displayed without inconsistencies or missing references. [Commit](https://github.com/open-webui/open-webui/commit/423983f)
+- 🎨 **Image action button fixed**, restoring the ability to trigger image generation, editing, and related image actions from the chat UI. [Commit](https://github.com/open-webui/open-webui/commit/def8a00)
+
+## [0.6.42] - 2025-12-21
+
+### Added
+
+- 📚 Knowledge base file management was overhauled with server-side pagination loading 30 files at a time instead of loading entire collections at once, dramatically improving performance and responsiveness for large knowledge bases with hundreds or thousands of files, reducing initial load times and memory usage while adding server-side search and filtering, view options for files added by the user versus shared files, customizable sorting by name or date, and file authorship tracking with upload timestamps. [Commit](https://github.com/open-webui/open-webui/commit/94a8439105f30203ea9d729787c9c5978f5c22a2)
+- ✨ Knowledge base file management was enhanced with automatic list refresh after file operations ensuring immediate UI updates, improved permission validation at the model layer, and automatic channel-file association for files uploaded with channel metadata. [Commit](https://github.com/open-webui/open-webui/commit/c15201620d03a9b60b800a34d8dc3426722c5b8b)
+- 🔎 Knowledge command in chat input now uses server-side search for massive performance increases when selecting knowledge bases and files. [Commit](https://github.com/open-webui/open-webui/commit/0addc1ea461d7b4eee8fe0ca2fedd615b3988b0e)
+- 🗂️ Knowledge workspace listing now uses server-side pagination loading 30 collections at a time with new search endpoints supporting query filtering and view options for created versus shared collections. [Commit](https://github.com/open-webui/open-webui/commit/ceae3d48e603f53313d5483abe94099e20e914e8)
+- 📖 Knowledge workspace now displays all collections with read access including shared read-only collections, enabling users to discover and explore knowledge bases they don't own while maintaining proper access controls through visual "Read Only" badges and automatically disabled editing controls for name, description, file uploads, content editing, and deletion operations. [Commit](https://github.com/open-webui/open-webui/commit/693636d971d0e8398fa0c9ec3897686750007af5)
+- 📁 Bulk website and YouTube video attachment now supports adding multiple URLs at once (newline-separated) with automatic YouTube detection and transcript retrieval, processed sequentially to prevent resource strain, and both websites and videos can now be added directly to knowledge bases through the workspace UI. [Commit](https://github.com/open-webui/open-webui/commit/7746e9f4b831f09953ad2b659b96e0fd52911031), [#6202](https://github.com/open-webui/open-webui/issues/6202), [#19587](https://github.com/open-webui/open-webui/pull/19587), [#8231](https://github.com/open-webui/open-webui/pull/8231)
+- 🪟 Sidebar width is now resizable on desktop devices with persistent storage in localStorage, enforcing minimum and maximum width constraints (220px to 480px) while all layout components now reference the dynamic sidebar width via CSS variables for consistent responsive behavior. [Commit](https://github.com/open-webui/open-webui/commit/b364cf43d3e8fd3557f65f17bc285bfaca5ed368)
+- 📝 Notes feature now supports server-side search and filtering with view options for notes created by the user versus notes shared with them, customizable sorting by name or date in both list and grid view modes within a redesigned interface featuring consolidated note management controls in a unified header, group-based permission sharing with read, write, and read-only access control displaying note authorship and sharing status for better collaboration, and paginated infinite scroll for improved performance with large note collections. [Commit](https://github.com/open-webui/open-webui/commit/9b24cddef6c4862bd899eb8d6332cafff54e871d)
+- 👁️ Notes now support read-only access permissions, allowing users to share notes for viewing without granting edit rights, with the editor automatically becoming non-editable and appropriate UI indicators when read-only access is detected. [Commit](https://github.com/open-webui/open-webui/commit/4363df175d50e0f9729381ac2ba9b37a3c3a966d)
+- 📄 Notes can now be created directly from the chat input field, allowing users to save drafted messages or content as notes without navigation or retyping. [Commit](https://github.com/open-webui/open-webui/commit/00c2b6ca405d617e3d7520953a00a36c19c790ec)
+- 🪟 Sidebar folders, channels, and pinned models sections now automatically expand when creating new items or pinning models, providing immediate visual feedback for user actions. [Commit](https://github.com/open-webui/open-webui/commit/f826d3ed75213a0a1b31b50d030bfb1d5e91d199), [#19929](https://github.com/open-webui/open-webui/pull/19929)
+- 📋 Chat file associations are now properly tracked in the database through a new "chat_file" table, enabling accurate file management across chats and ensuring proper cleanup of files when chats are deleted, while improving database consistency in multi-node deployments. [Commit](https://github.com/open-webui/open-webui/commit/f1bf4f20c53e6493f0eb6fa2f12cb84c2d22da52)
+- 🖼️ User-uploaded images are now automatically converted from base64 to actual file storage on the server, eliminating large inline base64 strings from being stored in chat history and reducing message payload sizes while enabling better image management and sharing across multiple chats. [Commit](https://github.com/open-webui/open-webui/commit/f1bf4f20c53e6493f0eb6fa2f12cb84c2d22da52)
+- 📸 Shared chats with generated or edited images now correctly display images when accessed by other users by properly linking generated images to their chat and message through the chat_file table, ensuring images remain accessible in shared chat links. [Commit](https://github.com/open-webui/open-webui/commit/446cc0ac6063402a743e949f50612376ed5a8437), [#19393](https://github.com/open-webui/open-webui/issues/19393)
+- 📊 File viewer modal was significantly enhanced with native-like viewers for Excel/CSV spreadsheets rendering as interactive scrollable tables with multi-sheet navigation support, Markdown documents displaying with full typography including headers, lists, links, and tables, and source code files showing syntax highlighting, all accessible through a tabbed interface defaulting to raw text view. [#20035](https://github.com/open-webui/open-webui/pull/20035), [#2867](https://github.com/open-webui/open-webui/issues/2867)
+- 📏 Chat input now displays an expand button in the top-right corner when messages exceed two lines, providing optional access to a full-screen editor for composing longer messages with enhanced workspace and visibility while temporarily disabling the main input to prevent editing conflicts. [Commit](https://github.com/open-webui/open-webui/commit/205c7111200c22da42e9b5fe1e676aec9cca6daa)
+- 💬 Channel message data lazy loading was implemented, deferring attachment and file metadata retrieval until needed to improve initial message list load performance. [Commit](https://github.com/open-webui/open-webui/commit/54b7ec56d6bcd2d79addc1694b757dab18cf18c5)
+- 🖼️ Channel image upload handling was optimized to process and store compressed images directly as files rather than inline data, improving memory efficiency and message load times. [Commit](https://github.com/open-webui/open-webui/commit/22f1b764a7ea1add0a896906a9ef00b4b6743adc)
+- 🎥 Video file playback support was added to channel messages, enabling inline video viewing with native player controls. [Commit](https://github.com/open-webui/open-webui/commit/7b126b23d50a0bd36a350fe09dc1dbe3df105318)
+- 🔐 LDAP authentication now supports user entries with multiple username attributes, correctly handling cases where the username field contains a list of values. [Commit](https://github.com/open-webui/open-webui/commit/379f888c9dc6dce21c3ef7a1fc455258aff993dc), [#19878](https://github.com/open-webui/open-webui/issues/19878)
+- 👨‍👩‍👧‍👦 The "ENABLE_PUBLIC_ACTIVE_USERS_COUNT" environment variable now allows restricting active user count visibility to administrators, reducing backend load and addressing privacy concerns in large deployments. [#20027](https://github.com/open-webui/open-webui/pull/20027), [#13026](https://github.com/open-webui/open-webui/issues/13026)
+- 🚀 Models page search input performance was optimized with a 300ms debounce to reduce server load and improve responsiveness. [#19832](https://github.com/open-webui/open-webui/pull/19832)
+- 💨 Frontend performance was optimized by preventing unnecessary API calls for API Keys and Channels features when they are disabled in admin settings, reducing backend noise and improving overall system efficiency. [#20043](https://github.com/open-webui/open-webui/pull/20043), [#19967](https://github.com/open-webui/open-webui/issues/19967)
+- 📎 Channel file association tracking was implemented, automatically linking uploaded files to their respective channels with a dedicated association table enabling better organization and future file management features within channels. [Commit](https://github.com/open-webui/open-webui/commit/2bccf8350d0915f69b8020934bb179c52e81b7b5)
+- 👥 User profile previews now display group membership information for easier identification of user roles and permissions. [Commit](https://github.com/open-webui/open-webui/commit/2b1a29d44bde9fbc20ff9f0a5ded1ce8ded9d90d)
+- 🌍 The "SEARXNG_LANGUAGE" environment variable now allows configuring search language for SearXNG queries, replacing the hardcoded "en-US" default with a configurable setting that defaults to "all". [#19909](https://github.com/open-webui/open-webui/pull/19909)
+- ⏳ The "MINERU_API_TIMEOUT" environment variable now allows configuring request timeouts for MinerU document processing operations. [#20016](https://github.com/open-webui/open-webui/pull/20016), [#18495](https://github.com/open-webui/open-webui/issues/18495)
+- 🔧 The "RAG_EXTERNAL_RERANKER_TIMEOUT" environment variable now allows configuring request timeouts for external reranker operations. [#20049](https://github.com/open-webui/open-webui/pull/20049), [#19900](https://github.com/open-webui/open-webui/issues/19900)
+- 🎨 OpenAI GPT-IMAGE 1.5 model support was added for image generation and editing with automatic image size capabilities. [Commit](https://github.com/open-webui/open-webui/commit/4c2e5c93e9287479f56f780708656136849ccaee)
+- 🔑 The "OAUTH_AUDIENCE" environment variable now allows OAuth providers to specify audience parameters for JWT access token generation. [#19768](https://github.com/open-webui/open-webui/pull/19768)
+- ⏰ The "REDIS_SOCKET_CONNECT_TIMEOUT" environment variable now allows configuring socket connection timeouts for Redis and Sentinel connections, addressing potential failover and responsiveness issues in distributed deployments. [#19799](https://github.com/open-webui/open-webui/pull/19799), [Docs:#882](https://github.com/open-webui/docs/pull/882)
+- ⏱️ The "WEB_LOADER_TIMEOUT" environment variable now allows configuring request timeouts for SafeWebBaseLoader operations. [#19804](https://github.com/open-webui/open-webui/pull/19804), [#19734](https://github.com/open-webui/open-webui/issues/19734)
+- 🚀 Models API endpoint performance was optimized through batched model loading, eliminating N+1 queries and significantly reducing response times when filtering models by user permissions. [Commit](https://github.com/open-webui/open-webui/commit/0dd2cfe1f273fbacdbe90300a97c021f2e678656)
+- 🔀 Custom model fallback handling was added, allowing workspace-created custom models to automatically fall back to the default chat model when their configured base model is not found; set "ENABLE_CUSTOM_MODEL_FALLBACK" to true to enable, preventing workflow disruption when base models are removed or renamed, while ensuring other requests remain unaffected. [Commit](https://github.com/open-webui/open-webui/commit/b35aeb8f46e0e278c6f4538382c2b6838e24cc5a), [#19985](https://github.com/open-webui/open-webui/pull/19985)
+- 📡 A new /feedbacks/all/ids API endpoint was added to return only feedback IDs without metadata, significantly improving performance for external integrations working with large feedback collections. [Commit](https://github.com/open-webui/open-webui/commit/53c1ca64b7205d85f6de06bd69e3e265d15546b8)
+- 📈 An experimental chat usage statistics endpoint (GET /api/v1/chats/stats/usage) was added with pagination support (50 chats per page) and comprehensive per-chat analytics including model usage counts, user and assistant message breakdowns, average response times calculated from message timestamps, average content lengths, and last activity timestamps; this endpoint remains experimental and not suitable for production use as it performs intensive calculations by processing entire message histories for each chat without caching. [Commit](https://github.com/open-webui/open-webui/commit/a7993f6f4e4591cd2aaa4718ece9e5623557d019)
+- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌐 Translations for German, Danish, Finnish, Korean, Portuguese (Brazil), Simplified Chinese, Traditional Chinese, Catalan, and Spanish were enhanced and expanded.
+
+### Fixed
+
+- ⚡ External reranker operations were optimized to prevent event loop blocking by offloading synchronous HTTP requests to a thread pool using asyncio.to_thread(), eliminating application freezes during RAG reranking queries. [#20049](https://github.com/open-webui/open-webui/pull/20049), [#19900](https://github.com/open-webui/open-webui/issues/19900)
+- 💭 Text loss in the explanation feature when using the "CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE" environment variable was resolved by correcting newline handling in streaming responses. [#19829](https://github.com/open-webui/open-webui/pull/19829)
+- 📚 Knowledge base batch file addition failures caused by Pydantic validation errors are now prevented by making the meta field optional in file metadata responses, allowing files without metadata to be processed correctly. [#20022](https://github.com/open-webui/open-webui/pull/20022), [#14220](https://github.com/open-webui/open-webui/issues/14220)
+- 🗄️ PostgreSQL null byte insertion failures when attaching web pages or processing embedded content are now prevented by consolidating text sanitization logic across chat messages, web search results, and knowledge base documents, removing null bytes and invalid UTF-8 surrogates before database insertion. [#20072](https://github.com/open-webui/open-webui/pull/20072), [#19867](https://github.com/open-webui/open-webui/issues/19867), [#18201](https://github.com/open-webui/open-webui/issues/18201), [#15616](https://github.com/open-webui/open-webui/issues/15616)
+- 🎫 MCP OAuth 2.1 token exchange failures are now fixed by removing duplicate credential passing that caused "ID1,ID1" concatenation and 401 errors from the token endpoint. [#20076](https://github.com/open-webui/open-webui/pull/20076), [#19823](https://github.com/open-webui/open-webui/issues/19823)
+- 📝 Notes "Improve" action now works correctly after the streaming API change in v0.6.41 by ensuring uploaded files are fully retrieved with complete metadata before processing, restoring note improvement and summarization functionality. [Commit](https://github.com/open-webui/open-webui/commit/a3458f492c53a3b00405f59fbe1ea953fe364f18), [#20078](https://github.com/open-webui/open-webui/discussions/20078)
+- 🔑 MCP OAuth 2.1 tool servers now work correctly in multi-node deployments through lazy-loading of OAuth clients from Redis-synced configuration, eliminating 404 errors when load balancers route requests to nodes that didn't process the original config update. [#20076](https://github.com/open-webui/open-webui/pull/20076), [#19902](https://github.com/open-webui/open-webui/pull/19902), [#19901](https://github.com/open-webui/open-webui/issues/19901)
+- 🧩 Chat loading failures when channels permissions were disabled are now prevented through graceful error handling. [Commit](https://github.com/open-webui/open-webui/commit/5c2df97f04cce5cb7087d288f816f91a739688c1)
+- 🔍 Search bar freezing and crashing issues in Models, Chat, and Archived Chat pages caused by excessively long queries exceeding server URL limits were resolved by truncating queries to 500 characters, and knowledge base layout shifting with long names was fixed by adjusting flex container properties. [#19832](https://github.com/open-webui/open-webui/pull/19832)
+- 🎛️ Rate limiting errors (HTTP 429) with Brave Search free tier when generating multiple queries are now prevented through asyncio.Semaphore-based concurrency control applied globally to all search engines. [#20070](https://github.com/open-webui/open-webui/pull/20070), [#20003](https://github.com/open-webui/open-webui/issues/20003), [#14107](https://github.com/open-webui/open-webui/issues/14107), [#15134](https://github.com/open-webui/open-webui/issues/15134)
+- 💥 UI crashes and white screen errors caused by null chat lists during loading or network failures were prevented by adding null safety checks to chat iteration in folder placeholders and archived chat modals. [#19898](https://github.com/open-webui/open-webui/pull/19898)
+- 🧩 Chat overview tab crashes caused by undefined model references were resolved by adding proper null checks when accessing deleted or ejected models. [#19935](https://github.com/open-webui/open-webui/pull/19935)
+- 🔄 MultiResponseMessages component crashes when navigating chat history after removing or changing selected models are now prevented through proper component re-initialization. [Commit](https://github.com/open-webui/open-webui/commit/870e29e3738da968c396b70532f365a3c2f71995), [#18599](https://github.com/open-webui/open-webui/issues/18599)
+- 🚫 Channel API endpoint access is now correctly blocked when channels are globally disabled, preventing users with channel permissions from accessing channel data via API requests when the feature is turned off in admin settings. [#19957](https://github.com/open-webui/open-webui/pull/19957), [#19914](https://github.com/open-webui/open-webui/issues/19914)
+- 👤 User list popup display in the admin panel was fixed to correctly track user identity when sorting or filtering changes the list order, preventing popups from showing incorrect user information. [Commit](https://github.com/open-webui/open-webui/commit/ae47101dc6aef2c7d8ae0d843985341fff820057), [#20046](https://github.com/open-webui/open-webui/issues/20046)
+- 👥 User selection in the "Edit User Group" modal now preserves pagination position, allowing administrators to select multiple users across pages without resetting to page 1. [#19959](https://github.com/open-webui/open-webui/pull/19959)
+- 📸 Model avatar images now update immediately in the admin models list through proper Cache-Control headers, eliminating the need for manual cache clearing. [#19959](https://github.com/open-webui/open-webui/pull/19959)
+- 🔒 Temporary chat permission enforcement now correctly prevents users from enabling the feature through personal settings when disabled in default or group permissions. [#19785](https://github.com/open-webui/open-webui/issues/19785)
+- 🎨 Image editing with reference images now correctly uses both previously generated images and newly uploaded reference images. [Commit](https://github.com/open-webui/open-webui/commit/bcd50ed8f1b7387fd700538ae0d74fc72f3c53d0)
+- 🧠 Image generation and editing operations are now explicitly injected into system context, improving LLM comprehension even for weaker models so they reliably acknowledge operations instead of incorrectly claiming they cannot generate images. [Commit](https://github.com/open-webui/open-webui/commit/28b2fcab0cd036dbe646a66fe81890f288c77121)
+- 📑 Source citation rendering errors when citation syntax appeared in user messages or contexts without source data were resolved. [Commit](https://github.com/open-webui/open-webui/commit/3c8f1cf8e58d52e86375634b0381374298b1b4f3)
+- 📄 DOCX file parsing now works correctly in temporary chats through client-side text extraction, preventing raw data from being displayed. [Commit](https://github.com/open-webui/open-webui/commit/6993b0b40b10af8cdbe6626702cc94080fff9e22)
+- 🔧 Pipeline settings save failures when valve properties contain null values are now handled correctly. [#19791](https://github.com/open-webui/open-webui/pull/19791)
+- ⚙️ Model usage settings are now correctly preserved when switching between models instead of being unexpectedly cleared or reset. [#19868](https://github.com/open-webui/open-webui/pull/19868), [#19549](https://github.com/open-webui/open-webui/issues/19549)
+- 🛡️ Invalid PASSWORD_VALIDATION_REGEX_PATTERN configurations no longer cause startup warnings, with automatic fallback to the default pattern when regex compilation fails. [#20058](https://github.com/open-webui/open-webui/pull/20058)
+- 🎯 The DefaultFiltersSelector component in model settings now correctly displays when only global toggleable filters are present, enabling per-model default configuration. [#20066](https://github.com/open-webui/open-webui/pull/20066)
+- 🎤 Audio file upload failures caused by MIME type matching issues with spacing variations and codec parameters were resolved by implementing proper MIME type parsing. [#17771](https://github.com/open-webui/open-webui/pull/17771), [#17761](https://github.com/open-webui/open-webui/issues/17761)
+- ⌨️ Regenerate response keyboard shortcut now only activates when chat input is selected, preventing unintended regeneration when modals are open or other UI elements are focused. [#19875](https://github.com/open-webui/open-webui/pull/19875)
+- 📋 Log truncation issues in Docker deployments during application crashes were resolved by disabling Python stdio buffering, ensuring complete diagnostic output is captured. [#19844](https://github.com/open-webui/open-webui/issues/19844)
+- 🔴 Redis cluster compatibility issues with disabled KEYS command were resolved by replacing blocking KEYS operations with production-safe SCAN iterations. [#19871](https://github.com/open-webui/open-webui/pull/19871), [#15834](https://github.com/open-webui/open-webui/issues/15834)
+- 🔤 File attachment container layout issues when using RTL languages were resolved by applying chat direction settings to file containers across all message types. [#19891](https://github.com/open-webui/open-webui/pull/19891), [#19742](https://github.com/open-webui/open-webui/issues/19742)
+- 🔃 Ollama model list now automatically refreshes after model deletion, preventing deleted models from persisting in the UI and being inadvertently re-downloaded during subsequent pull operations. [#19912](https://github.com/open-webui/open-webui/pull/19912)
+- 🌐 Ollama Cloud web search now correctly applies domain filtering to search results. [Commit](https://github.com/open-webui/open-webui/commit/d4bd938a77c22409a1643c058b937a06e07baca9)
+- 📜 Tool specification serialization now preserves non-ASCII characters including Chinese text, improving LLM comprehension and tool selection accuracy by avoiding Unicode escape sequences. [#19942](https://github.com/open-webui/open-webui/pull/19942)
+- 🛟 Model editor stability was improved with null safety checks for tools, functions, and file input operations, preventing crashes when stores are undefined or file objects are invalid. [#19939](https://github.com/open-webui/open-webui/pull/19939)
+- 🗣️ MoA completion handling stability was improved with null safety checks for response objects, boolean casting for settings, and proper timeout type definitions. [#19921](https://github.com/open-webui/open-webui/pull/19921)
+- 🎛️ Chat functionality failures caused by empty logit_bias parameter values are now prevented by properly handling empty strings in the parameter parsing middleware. [#19982](https://github.com/open-webui/open-webui/issues/19982)
+- 🔏 Administrators can now delete read-only knowledge bases from deleted users, resolving permission issues that previously prevented cleanup of orphaned read-only content. [Commit](https://github.com/open-webui/open-webui/commit/59d6eb2badf46f9c2b1e879484ac33432915b575)
+- 💾 Cloned prompts and tools now correctly preserve their access control settings instead of being reset to null, preventing unintended visibility changes when duplicating private or restricted items. [#19960](https://github.com/open-webui/open-webui/pull/19960), [#19360](https://github.com/open-webui/open-webui/issues/19360)
+- 🎚️ Text scale adjustment buttons in Interface Settings were fixed to correctly increment and decrement the scale value. [#19699](https://github.com/open-webui/open-webui/pull/19699)
+- 🎭 Group channel invite button text visibility in light theme was corrected to display properly against dark backgrounds. [#19828](https://github.com/open-webui/open-webui/issues/19828)
+- 📁 The move button is now hidden when no folders exist, preventing display of non-functional controls. [#19705](https://github.com/open-webui/open-webui/pull/19705)
+- 📦 Qdrant client dependency was updated to resolve startup version incompatibility warnings. [#19757](https://github.com/open-webui/open-webui/pull/19757)
+- 🧮 The "ENABLE_ASYNC_EMBEDDING" environment variable is now correctly applied to embedding operations when configured exclusively via environment variables. [#19748](https://github.com/open-webui/open-webui/pull/19748)
+- 🌄 The "COMFYUI_WORKFLOW_NODES" and "IMAGES_EDIT_COMFYUI_WORKFLOW_NODES" environment variables are now correctly loaded and parsed as JSON lists, and the configuration key name was corrected from "COMFYUI_WORKFLOW" to "COMFYUI_WORKFLOW_NODES". [#19918](https://github.com/open-webui/open-webui/pull/19918), [#19886](https://github.com/open-webui/open-webui/issues/19886)
+- 💫 Channel name length is now limited to 128 characters with validation to prevent display issues caused by excessively long names. [Commit](https://github.com/open-webui/open-webui/commit/f509f5542dde384d34402f6df763f49a06bea109)
+- 🔐 Invalid PASSWORD_VALIDATION_REGEX_PATTERN configurations no longer cause startup warnings, with automatic fallback to the default pattern when regex compilation fails. [#20058](https://github.com/open-webui/open-webui/pull/20058)
+- 🔎 Bocha search with filter list functionality now works correctly by returning results as a list instead of a dictionary wrapper, ensuring compatibility with result filtering operations. [Commit](https://github.com/open-webui/open-webui/commit/b5bd8704fe1672da839bb3be6210d7cb494797ce), [#19733](https://github.com/open-webui/open-webui/issues/19733)
+
+### Changed
+
+- ⚠️ This release includes database schema changes; multi-worker, multi-server, or load-balanced deployments must update all instances simultaneously rather than performing rolling updates, as running mixed versions will cause application failures due to schema incompatibility between old and new instances.
+- 📡 WEB_SEARCH_CONCURRENT_REQUESTS default changed from 10 to 0 (unlimited) — This setting now applies to all search engines instead of only DuckDuckGo; previously users were implicitly limited to 10 concurrent queries, but now have unlimited parallel requests by default; set to 1 for sequential execution if using rate-limited APIs like Brave free tier. [#20070](https://github.com/open-webui/open-webui/pull/20070)
+- 💾 SQLCipher absolute path handling was fixed to properly support absolute database paths (e.g., "/app/data.db") instead of incorrectly stripping leading slashes and converting them to relative paths; this restores functionality for Docker volume mounts and explicit absolute path configurations while maintaining backward compatibility with relative paths. [#20074](https://github.com/open-webui/open-webui/pull/20074)
+- 🔌 Knowledge base file listing API was redesigned with paginated responses and new filtering parameters; the GET /knowledge/{id}/files endpoint now returns paginated results with user attribution instead of embedding all files in the knowledge object, which may require updates to custom integrations or scripts accessing knowledge base data programmatically. [Commit](https://github.com/open-webui/open-webui/commit/94a8439105f30203ea9d729787c9c5978f5c22a2)
+- 🗑️ Legacy knowledge base support for deprecated document collections and tag-based collections was removed; users with pre-knowledge base documents must migrate to the current knowledge base system as legacy items will no longer appear in selectors or command menus. [Commit](https://github.com/open-webui/open-webui/commit/a934dc997ed67a036dd7975e380f8036c447d3ed)
+- 🔨 Source-level log environment variables (AUDIO_LOG_LEVEL, CONFIG_LOG_LEVEL, MODELS_LOG_LEVEL, etc.) were removed as they provided limited configuration options and added significant complexity across 100+ files; the GLOBAL_LOG_LEVEL environment variable, which already took precedence over source-level settings, now serves as the exclusive logging configuration method. [#20045](https://github.com/open-webui/open-webui/pull/20045)
+- 🐍 LangChain was upgraded to version 1.2.0, representing a major dependency update and significant progress toward Python 3.13 compatibility while improving RAG pipeline functionality for document loading and retrieval operations. [#19991](https://github.com/open-webui/open-webui/pull/19991)
+
+## [0.6.41] - 2025-12-02
+
+### Added
+
+- 🚦 Sign-in rate limiting was implemented to protect against brute force attacks, limiting login attempts to 15 per 3-minute window per email address using Redis with automatic fallback to in-memory storage when Redis is unavailable. [Commit](https://github.com/open-webui/open-webui/commit/7b166370432414ce8f186747fb098e0c70fb2d6b)
+- 📂 Administrators can now globally disable the folders feature and control user-level folder permissions through the admin panel, enabling minimalist interface configurations for deployments that don't require workspace organization features. [#19529](https://github.com/open-webui/open-webui/pull/19529), [#19210](https://github.com/open-webui/open-webui/discussions/19210), [#18459](https://github.com/open-webui/open-webui/discussions/18459), [#18299](https://github.com/open-webui/open-webui/discussions/18299)
+- 👥 Group channels were introduced as a new channel type enabling membership-based collaboration spaces where users explicitly join as members rather than accessing through permissions, with support for public or private visibility, automatic member inclusion from specified user groups, member role tracking with invitation metadata, and post-creation member management allowing channel managers to add or remove members through the channel info modal. [Commit](https://github.com/open-webui/open-webui/commit/f589b7c1895a6a77166c047891acfa21bc0936c4), [Commit](https://github.com/open-webui/open-webui/commit/3f1d9ccbf8443a2fa5278f36202bad930a216680)
+- 💬 Direct Message channels were introduced with a dedicated channel type selector and multi-user member selection interface, enabling private conversations between specific users without requiring full channel visibility. [Commit](https://github.com/open-webui/open-webui/commit/64b4d5d9c280b926746584aaf92b447d09deb386)
+- 📨 Direct Message channels now support a complete user-to-user messaging system with member-based access control, automatic deduplication for one-on-one conversations, optional channel naming, and distinct visual presentation using participant avatars instead of channel icons. [Commit](https://github.com/open-webui/open-webui/commit/acccb9afdd557274d6296c70258bb897bbb6652f)
+- 🙈 Users can now hide Direct Message channels from their sidebar while preserving message history, with automatic reactivation when new messages arrive from other participants, providing a cleaner interface for managing active conversations. [Commit](https://github.com/open-webui/open-webui/commit/acccb9afdd557274d6296c70258bb897bbb6652f)
+- ☑️ A comprehensive user selection component was added to the channel creation modal, featuring search functionality, sortable user lists, pagination support, and multi-select checkboxes for building Direct Message participant lists. [Commit](https://github.com/open-webui/open-webui/commit/acccb9afdd557274d6296c70258bb897bbb6652f)
+- 🔴 Channel unread message count tracking was implemented with visual badge indicators in the sidebar, automatically updating counts in real-time and marking messages as read when users view channels, with join/leave functionality to manage membership status. [Commit](https://github.com/open-webui/open-webui/commit/64b4d5d9c280b926746584aaf92b447d09deb386)
+- 📌 Message pinning functionality was added to channels, allowing users to pin important messages for easy reference with visual highlighting, a dedicated pinned messages modal accessible from the navbar, and complete backend support for tracking pinned status, pin timestamp, and the user who pinned each message. [Commit](https://github.com/open-webui/open-webui/commit/64b4d5d9c280b926746584aaf92b447d09deb386), [Commit](https://github.com/open-webui/open-webui/commit/aae2fce17355419d9c29f8100409108037895201)
+- 🟢 Direct Message channels now display an active status indicator for one-on-one conversations, showing a green dot when the other participant is currently online or a gray dot when offline. [Commit](https://github.com/open-webui/open-webui/commit/4b6773885cd7527c5a56b963781dac5e95105eec), [Commit](https://github.com/open-webui/open-webui/commit/39645102d14f34e71b34e5ddce0625790be33f6f)
+- 🆔 Users can now start Direct Message conversations directly from user profile previews by clicking the "Message" button, enabling quick access to private messaging without navigating away from the current channel. [Commit](https://github.com/open-webui/open-webui/commit/a0826ec9fedb56320532616d568fa59dda831d4e)
+- ⚡ Channel messages now appear instantly when sent using optimistic UI rendering, displaying with a pending state while the server confirms delivery, providing a more responsive messaging experience. [Commit](https://github.com/open-webui/open-webui/commit/25994dd3da90600401f53596d4e4fb067c1b8eaa)
+- 👍 Channel message reactions now display the names of users who reacted when hovering over the emoji, showing up to three names with a count for additional reactors. [Commit](https://github.com/open-webui/open-webui/commit/05e79bdd0c7af70b631e958924e3656db1013b80)
+- 🛠️ Channel creators can now edit and delete their own group and DM channels without requiring administrator privileges, enabling users to manage the channels they create independently. [Commit](https://github.com/open-webui/open-webui/commit/f589b7c1895a6a77166c047891acfa21bc0936c4)
+- 🔌 A new API endpoint was added to directly get or create a Direct Message channel with a specific user by their ID, streamlining programmatic DM channel creation for integrations and frontend workflows. [Commit](https://github.com/open-webui/open-webui/commit/f589b7c1895a6a77166c047891acfa21bc0936c4)
+- 💭 Users can now set a custom status with an emoji and message that displays in profile previews, the sidebar user menu, and Direct Message channel items in the sidebar, with the ability to clear status at any time, providing visibility into availability or current focus similar to team communication platforms. [Commit](https://github.com/open-webui/open-webui/commit/51621ba91a982e52da168ce823abffd11ad3e4fa), [Commit](https://github.com/open-webui/open-webui/commit/f5e8d4d5a004115489c35725408b057e24dfe318)
+- 📤 A group export API endpoint was added, enabling administrators to export complete group data including member lists for backup and migration purposes. [Commit](https://github.com/open-webui/open-webui/commit/09b6ea38c579659f8ca43ae5ea3746df3ac561ad)
+- 📡 A new API endpoint was added to retrieve all users belonging to a specific group, enabling programmatic access to group membership information for administrative workflows. [Commit](https://github.com/open-webui/open-webui/commit/01868e856a10f474f74fbd1b4425dafdf949222f)
+- 👁️ The admin user list now displays an active status indicator next to each user, showing a visual green dot for users who have been active within the last three minutes. [Commit](https://github.com/open-webui/open-webui/commit/1b095d12ff2465b83afa94af89ded9593f8a8655)
+- 🔑 The admin user edit modal now displays OAuth identity information with a per-provider breakdown, showing each linked identity provider and its associated subject identifier separately. [#19573](https://github.com/open-webui/open-webui/pull/19573)
+- 🧩 OAuth role claim parsing now respects the "OAUTH_ROLES_SEPARATOR" configuration, enabling proper parsing of roles returned as comma-separated strings and providing consistent behavior with group claim handling. [#19514](https://github.com/open-webui/open-webui/pull/19514)
+- 🎛️ Channel feature access can now be controlled through both the "USER_PERMISSIONS_FEATURES_CHANNELS" environment variable and group permission toggles in the admin panel, allowing administrators to restrict channel functionality for specific users or groups while defaulting to enabled for all users. [Commit](https://github.com/open-webui/open-webui/commit/f589b7c1895a6a77166c047891acfa21bc0936c4)
+- 🎨 The model editor interface was refined with access control settings moved to a dedicated modal, group member counts now displayed when configuring permissions, reorganized layout with improved visual hierarchy, and redesigned prompt suggestions cards with tooltips for field guidance. [Commit](https://github.com/open-webui/open-webui/commit/e65d92fc6f49da5ca059e1c65a729e7973354b99), [Commit](https://github.com/open-webui/open-webui/commit/9d39b9b42c653ee2acf2674b2df343ecbceb4954)
+- 🏗️ Knowledge base file management was rebuilt with a dedicated database table replacing the previous JSON array storage, enabling pagination support for large knowledge bases, significantly faster file listing performance, and more reliable file-knowledge base relationship tracking. [Commit](https://github.com/open-webui/open-webui/commit/d19023288e2ca40f86e2dc3fd9f230540f3e70d7)
+- ☁️ Azure Document Intelligence model selection was added, allowing administrators to specify which model to use for document processing via the "DOCUMENT_INTELLIGENCE_MODEL" environment variable or admin UI setting, with "prebuilt-layout" as the default. [#19692](https://github.com/open-webui/open-webui/pull/19692), [Docs:#872](https://github.com/open-webui/docs/pull/872)
+- 🚀 Milvus multitenancy vector database performance was improved by removing manual flush calls after upsert operations, eliminating rate limit errors and reducing load on etcd and MinIO/S3 storage by allowing Milvus to manage segment persistence automatically via its WAL and auto-flush policies. [#19680](https://github.com/open-webui/open-webui/pull/19680)
+- ✨ Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌍 Translations for German, French, Portuguese (Brazil), Catalan, Simplified Chinese, and Traditional Chinese were enhanced and expanded.
+
+### Fixed
+
+- 🔄 Tool call response token duplication was fixed by removing redundant message history additions in non-native function calling mode, resolving an issue where tool results were included twice in the context and causing 2x token consumption. [#19656](https://github.com/open-webui/open-webui/issues/19656), [Commit](https://github.com/open-webui/open-webui/commit/52ccab8)
+- 🛡️ Web search domain filtering was corrected to properly block results when any resolved hostname or IP address matches a blocked domain, preventing blocked sites from appearing in search results due to permissive hostname resolution logic that previously allowed results through if any single resolved address passed the filter. [#19670](https://github.com/open-webui/open-webui/pull/19670), [#19669](https://github.com/open-webui/open-webui/issues/19669)
+- 🧠 Custom models based on Ollama or OpenAI now properly inherit the connection type from their base model, ensuring they appear correctly in the "Local" or "External" model selection tabs instead of only appearing under "All". [#19183](https://github.com/open-webui/open-webui/issues/19183), [Commit](https://github.com/open-webui/open-webui/commit/39f7575)
+- 🐍 SentenceTransformers embedding initialization was fixed by updating the transformers dependency to version 4.57.3, resolving a regression in v0.6.40 where document ingestion failed with "'NoneType' object has no attribute 'encode'" errors due to a bug in transformers 4.57.2. [#19512](https://github.com/open-webui/open-webui/issues/19512), [#19513](https://github.com/open-webui/open-webui/pull/19513)
+- 📈 Active user count accuracy was significantly improved by replacing the socket-based USER_POOL tracking with a database-backed heartbeat mechanism, resolving long-standing issues where Redis deployments displayed inflated user counts due to stale sessions never being cleaned up on disconnect. [#16074](https://github.com/open-webui/open-webui/discussions/16074), [Commit](https://github.com/open-webui/open-webui/commit/70948f8803e417459d5203839f8077fdbfbbb213)
+- 👥 Default group assignment now applies consistently across all user registration methods including OAuth/SSO, LDAP, and admin-created users, fixing an issue where the "DEFAULT_GROUP_ID" setting was only being applied to users who signed up via the email/password signup form. [#19685](https://github.com/open-webui/open-webui/pull/19685)
+- 🔦 Model list filtering in workspaces was corrected to properly include models shared with user groups, ensuring members can view models they have write access to through group permissions. [#19461](https://github.com/open-webui/open-webui/issues/19461), [Commit](https://github.com/open-webui/open-webui/commit/69722ba973768a5f689f2e2351bf583a8db9bba8)
+- 🖼️ User profile image display in preview contexts was fixed by resolving a Pydantic validation error that prevented proper rendering. [Commit](https://github.com/open-webui/open-webui/commit/c7eb7136893b0ddfdc5d55ffc7a05bd84a00f5d6)
+- 🔒 Redis TLS connection failures were resolved by updating the python-socketio dependency to version 5.15.0, restoring support for the "rediss://" URL schema. [#19480](https://github.com/open-webui/open-webui/issues/19480), [#19488](https://github.com/open-webui/open-webui/pull/19488)
+- 📝 MCP tool server configuration was corrected to properly handle the "Function Name Filter List" as both string and list types, preventing AttributeError when the field is empty and ensuring backward compatibility. [#19486](https://github.com/open-webui/open-webui/issues/19486), [Commit](https://github.com/open-webui/open-webui/commit/c5b73d71843edc024325d4a6e625ec939a747279), [Commit](https://github.com/open-webui/open-webui/commit/477097c2e42985c14892301d0127314629d07df1)
+- 📎 Web page attachment failures causing TypeError on metadata checks were resolved by correcting async threadpool parameter passing in vector database operations. [#19493](https://github.com/open-webui/open-webui/issues/19493), [Commit](https://github.com/open-webui/open-webui/commit/4370dee79e19d77062c03fba81780cb3b779fca3)
+- 💾 Model allowlist persistence in multi-worker deployments was fixed by implementing Redis-based shared state for the internal models dictionary, ensuring configuration changes are consistently visible across all worker processes. [#19395](https://github.com/open-webui/open-webui/issues/19395), [Commit](https://github.com/open-webui/open-webui/commit/b5e5617d7f7ad3e4eec9f15f4cc7f07cb5afc2fa)
+- ⏳ Chat history infinite loading was prevented by enhancing message data structure to properly track parent message relationships, resolving issues where missing parentId fields caused perpetual loading states. [#19225](https://github.com/open-webui/open-webui/issues/19225), [Commit](https://github.com/open-webui/open-webui/commit/ff4b1b9862d15adfa15eac17d2ce066c3d8ae38f)
+- 🩹 Database migration robustness was improved by automatically detecting and correcting missing primary key constraints on the user table, ensuring successful schema upgrades for databases with non-standard configurations. [#19487](https://github.com/open-webui/open-webui/discussions/19487), [Commit](https://github.com/open-webui/open-webui/commit/453ea9b9a167c0b03d86c46e6efd086bf10056ce)
+- 🏷️ OAuth group assignment now updates correctly on first login when users transition from admin to user role, ensuring group memberships reflect immediately when group management is enabled. [#19475](https://github.com/open-webui/open-webui/issues/19475), [#19476](https://github.com/open-webui/open-webui/pull/19476)
+- 💡 Knowledge base file tooltips now properly display the parent collection name when referencing files with the hash symbol, preventing confusion between identically-named files in different collections. [#19491](https://github.com/open-webui/open-webui/issues/19491), [Commit](https://github.com/open-webui/open-webui/commit/3fe5a47b0ff84ac97f8e4ff56a19fa2ec065bf66)
+- 🔐 Knowledge base file access inconsistencies were resolved where authorized non-admin users received "Not found" or permission errors for certain files due to race conditions during upload causing mismatched collection_name values, with file access validation now properly checking against knowledge base file associations. [#18689](https://github.com/open-webui/open-webui/issues/18689), [#19523](https://github.com/open-webui/open-webui/pull/19523), [Commit](https://github.com/open-webui/open-webui/commit/e301d1962e45900ababd3eabb7e9a2ad275a5761)
+- 📦 Knowledge API batch file addition endpoint was corrected to properly handle async operations, resolving 500 Internal Server Error responses when adding multiple files simultaneously. [#19538](https://github.com/open-webui/open-webui/issues/19538), [Commit](https://github.com/open-webui/open-webui/commit/28659f60d94feb4f6a99bb1a5b54d7f45e5ea10f)
+- 🤖 Embedding model auto-update functionality was fixed to properly respect the "RAG_EMBEDDING_MODEL_AUTO_UPDATE" setting by correctly passing the flag to the model path resolver, ensuring models update as expected when the auto-update option is enabled. [#19687](https://github.com/open-webui/open-webui/pull/19687)
+- 📉 API response payload sizes were dramatically reduced by removing base64-encoded profile images from most endpoints, eliminating multi-megabyte responses caused by high-resolution avatars and enabling better browser caching. [#19519](https://github.com/open-webui/open-webui/issues/19519), [Commit](https://github.com/open-webui/open-webui/commit/384753c4c17f62a68d38af4bbcf55a21ee08e0f2)
+- 📞 Redundant API calls on the admin user overview page were eliminated by consolidating reactive statements, reducing four duplicate requests to a single efficient call and significantly improving page load performance. [#19509](https://github.com/open-webui/open-webui/issues/19509), [Commit](https://github.com/open-webui/open-webui/commit/9f89cc5e9f7e1c6c9e2bc91177e08df7c79f66f9)
+- 🧹 Duplicate API calls on the workspace models page were eliminated by removing redundant model list fetching, reducing two identical requests to a single call and improving page responsiveness. [#19517](https://github.com/open-webui/open-webui/issues/19517), [Commit](https://github.com/open-webui/open-webui/commit/d1bbf6be7a4d1d53fa8ad46ca4f62fc4b2e6a8cb)
+- 🔘 The model valves button was corrected to prevent unintended form submission by adding explicit button type attribute, ensuring it no longer triggers message sending when the input area contains text. [#19534](https://github.com/open-webui/open-webui/pull/19534)
+- 🗑️ Ollama model deletion was fixed by correcting the request payload format and ensuring the model selector properly displays the placeholder option. [Commit](https://github.com/open-webui/open-webui/commit/0f3156651c64bc5af188a65fc2908bdcecf30c74)
+- 🎨 Image generation in temporary chats was fixed by correctly handling local chat sessions that are not persisted to the database. [Commit](https://github.com/open-webui/open-webui/commit/a7c7993bbf3a21cb7ba416525b89233cf2ad877f)
+- 🕵️‍♂️ Audit logging was fixed by correctly awaiting the async user authentication call, resolving failures where coroutine objects were passed instead of user data. [#19658](https://github.com/open-webui/open-webui/pull/19658), [Commit](https://github.com/open-webui/open-webui/commit/dba86bc)
+- 🌙 Dark mode select dropdown styling was corrected to use proper background colors, fixing an issue where dropdown borders and hover states appeared white instead of matching the dark theme. [#19693](https://github.com/open-webui/open-webui/pull/19693), [#19442](https://github.com/open-webui/open-webui/issues/19442)
+- 🔍 Milvus vector database query filtering was fixed by correcting string quote handling in filter expressions and using the proper parameter name for queries, resolving false "duplicate content detected" errors that prevented uploading multiple files to knowledge bases. [#19602](https://github.com/open-webui/open-webui/pull/19602), [#18119](https://github.com/open-webui/open-webui/issues/18119), [#16345](https://github.com/open-webui/open-webui/issues/16345), [#17088](https://github.com/open-webui/open-webui/issues/17088), [#18485](https://github.com/open-webui/open-webui/issues/18485)
+- 🆙 Milvus multitenancy vector database was updated to use query_iterator() for improved robustness and consistency with the standard Milvus implementation, fixing the same false duplicate detection errors and improving handling of large result sets in multi-tenant deployments. [#19695](https://github.com/open-webui/open-webui/pull/19695)
+
+### Changed
+
+- ⚠️ **IMPORTANT for Multi-Instance Deployments** — This release includes database schema changes; multi-worker, multi-server, or load-balanced deployments must update all instances simultaneously rather than performing rolling updates, as running mixed versions will cause application failures due to schema incompatibility between old and new instances.
+- 👮 Channel creation is now restricted to administrators only, with the channel add button hidden for regular users to maintain organizational control over communication channels. [Commit](https://github.com/open-webui/open-webui/commit/421aba7cd7cd708168b1f2565026c74525a67905)
+- ➖ The active user count indicator was removed from the bottom-left user menu in the sidebar to streamline the interface. [Commit](https://github.com/open-webui/open-webui/commit/848f3fd4d86ca66656e0ff0335773945af8d7d8d)
+- 🗂️ The user table was restructured with API keys migrated to a dedicated table supporting future multi-key functionality, OAuth data storage converted to a JSON structure enabling multiple identity providers per user account, and internal column types optimized from TEXT to JSON for the "info" and "settings" fields, with automatic migration preserving all existing data and associations. [#19573](https://github.com/open-webui/open-webui/pull/19573)
+- 🔄 The knowledge base API was restructured to support the new file relationship model.
+
+## [0.6.40] - 2025-11-25
+
+### Fixed
+
+- 🗄️ A critical PostgreSQL user listing performance issue was resolved by removing a redundant count operation that caused severe database slowdowns and potential timeouts when viewing user lists in admin panels.
+
+## [0.6.39] - 2025-11-25
+
+### Added
+
+- 💬 A user list modal was added to channels, displaying all users with access and featuring search, sorting, and pagination capabilities. [Commit](https://github.com/open-webui/open-webui/commit/c0e120353824be00a2ef63cbde8be5d625bd6fd0)
+- 💬 Channel navigation now displays the total number of users with access to the channel. [Commit](https://github.com/open-webui/open-webui/commit/3b5710d0cd445cf86423187f5ee7c40472a0df0b)
+- 🔌 Tool servers and MCP connections now support function name filtering, allowing administrators to selectively enable or block specific functions using allow/block lists. [Commit](https://github.com/open-webui/open-webui/commit/743199f2d097ae1458381bce450d9025a0ab3f3d)
+- ⚡ A toggle to disable parallel embedding processing was added via "ENABLE_ASYNC_EMBEDDING", allowing sequential processing for rate-limited or resource-constrained local embedding setups. [#19444](https://github.com/open-webui/open-webui/pull/19444)
+- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌐 Localization improvements were made for German (de-DE) and Portuguese (Brazil) translations.
+
+### Fixed
+
+- 📝 Inline citations now render correctly within markdown lists and nested elements instead of displaying as "undefined" values. [#19452](https://github.com/open-webui/open-webui/issues/19452)
+- 👥 Group member selection now works correctly without randomly selecting other users or causing the user list to jump around. [#19426](https://github.com/open-webui/open-webui/issues/19426)
+- 👥 Admin panel user list now displays the correct total user count and properly paginates 30 items per page after fixing database query issues with group member joins. [#19429](https://github.com/open-webui/open-webui/issues/19429)
+- 🔍 Knowledge base reindexing now works correctly after resolving async execution chain issues by implementing threadpool workers for embedding operations. [#19434](https://github.com/open-webui/open-webui/pull/19434)
+- 🖼️ OpenAI image generation now works correctly after fixing a connection adapter error caused by incorrect URL formatting. [#19435](https://github.com/open-webui/open-webui/pull/19435)
+
+### Changed
+
+- 🔧 BREAKING: Docling configuration has been consolidated from individual environment variables into a single "DOCLING_PARAMS" JSON configuration and now supports API key authentication via "DOCLING_API_KEY", requiring users to migrate existing Docling settings to the new format. [#16841](https://github.com/open-webui/open-webui/issues/16841), [#19427](https://github.com/open-webui/open-webui/pull/19427)
+- 🔧 The environment variable "REPLACE_IMAGE_URLS_IN_CHAT_RESPONSE" has been renamed to "ENABLE_CHAT_RESPONSE_BASE64_IMAGE_URL_CONVERSION" for naming consistency.
+
+## [0.6.38] - 2025-11-24
+
+### Fixed
+
+- 🔍 Hybrid search now works reliably after recent changes.
+- 🛠️ Tool server saving now handles errors gracefully, preventing failed saves from impacting the UI.
+- 🔐 SSO/OIDC code fixed to improve login reliability and better handle edge cases.
+
+## [0.6.37] - 2025-11-24
+
+### Added
+
+- 🔐 Granular sharing permissions are now available with two-tiered control separating group sharing from public sharing, allowing administrators to independently configure whether users can share workspace items with groups or make them publicly accessible, with separate permission toggles for models, knowledge bases, prompts, tools, and notes, configurable via "USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_SHARING", "USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING", and corresponding environment variables for other workspace item types, while groups can now be configured to opt-out of sharing via the "Allow Group Sharing" setting. [Commit](https://github.com/open-webui/open-webui/commit/7be750bcbb40da91912a0a66b7ab791effdcc3b6), [Commit](https://github.com/open-webui/open-webui/commit/f69e37a8507d6d57382d6670641b367f3127f90a)
+- 🔐 Password policy enforcement is now available with configurable validation rules, allowing administrators to require specific password complexity requirements via "ENABLE_PASSWORD_VALIDATION" and "PASSWORD_VALIDATION_REGEX_PATTERN" environment variables, with default pattern requiring minimum 8 characters including uppercase, lowercase, digit, and special character. [#17794](https://github.com/open-webui/open-webui/pull/17794)
+- 🔐 Granular import and export permissions are now available for workspace items, introducing six separate permission toggles for models, prompts, and tools that are disabled by default for enhanced security. [#19242](https://github.com/open-webui/open-webui/pull/19242)
+- 👥 Default group assignment is now available for new users, allowing administrators to automatically assign newly registered users to a specified group for streamlined access control to models, prompts, and tools, particularly useful for organizations with group-based model access policies. [#19325](https://github.com/open-webui/open-webui/pull/19325), [#17842](https://github.com/open-webui/open-webui/issues/17842)
+- 🔒 Password-based authentication can now be fully disabled via "ENABLE_PASSWORD_AUTH" environment variable, enforcing SSO-only authentication and preventing password login fallback when SSO is configured. [#19113](https://github.com/open-webui/open-webui/pull/19113)
+- 🖼️ Large stream chunk handling was implemented to support models that generate images directly in their output responses, with configurable buffer size via "CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE" environment variable, resolving compatibility issues with models like Gemini 2.5 Flash Image. [#18884](https://github.com/open-webui/open-webui/pull/18884), [#17626](https://github.com/open-webui/open-webui/issues/17626)
+- 🖼️ Streaming response middleware now handles images in delta updates with automatic base64 conversion, enabling proper display of images from models using the "choices[0].delta.images.image_url" format such as Gemini 2.5 Flash Image Preview on OpenRouter. [#19073](https://github.com/open-webui/open-webui/pull/19073), [#19019](https://github.com/open-webui/open-webui/issues/19019)
+- 📈 Model list API performance was optimized by pre-fetching user group memberships and removing profile image URLs from response payloads, significantly reducing both database queries and payload size for instances with large model lists, with profile images now served dynamically via dedicated endpoints. [#19097](https://github.com/open-webui/open-webui/pull/19097), [#18950](https://github.com/open-webui/open-webui/issues/18950)
+- ⏩ Batch file processing performance was improved by reducing database queries by 67% while ensuring data consistency between vector and relational databases. [#18953](https://github.com/open-webui/open-webui/pull/18953)
+- 🚀 Chat import performance was dramatically improved by replacing individual per-chat API requests with a bulk import endpoint, reducing import time by up to 95% for large chat collections and providing user feedback via toast notifications displaying the number of successfully imported chats. [#17861](https://github.com/open-webui/open-webui/pull/17861)
+- ⚡ Socket event broadcasting performance was optimized by implementing user-specific rooms, significantly reducing server overhead particularly for users with multiple concurrent sessions. [#18996](https://github.com/open-webui/open-webui/pull/18996)
+- 🗄️ Weaviate is now supported as a vector database option, providing an additional choice for RAG document storage alongside existing ChromaDB, Milvus, Qdrant, and OpenSearch integrations. [#14747](https://github.com/open-webui/open-webui/pull/14747)
+- 🗄️ PostgreSQL pgvector now supports HNSW index types and large dimensional embeddings exceeding 2000 dimensions through automatic halfvec type selection, with configurable index methods via "PGVECTOR_INDEX_METHOD", "PGVECTOR_HNSW_M", "PGVECTOR_HNSW_EF_CONSTRUCTION", and "PGVECTOR_IVFFLAT_LISTS" environment variables. [#19158](https://github.com/open-webui/open-webui/pull/19158), [#16890](https://github.com/open-webui/open-webui/issues/16890)
+- 🔍 Azure AI Search is now supported as a web search provider, enabling integration with Azure's cognitive search services via "AZURE_AI_SEARCH_API_KEY", "AZURE_AI_SEARCH_ENDPOINT", and "AZURE_AI_SEARCH_INDEX_NAME" configuration. [#19104](https://github.com/open-webui/open-webui/pull/19104)
+- ⚡ External embedding generation now processes API requests in parallel instead of sequential batches, reducing document processing time by 10-50x when using OpenAI, Azure OpenAI, or Ollama embedding providers, with large PDFs now processing in seconds instead of minutes. [#19296](https://github.com/open-webui/open-webui/pull/19296)
+- 💨 Base64 image conversion is now available for markdown content in chat responses, automatically uploading embedded images exceeding 1KB and replacing them with file URLs to reduce payload size and resource consumption, configurable via "REPLACE_IMAGE_URLS_IN_CHAT_RESPONSE" environment variable. [#19076](https://github.com/open-webui/open-webui/pull/19076)
+- 🎨 OpenAI image generation now supports additional API parameters including quality settings for GPT Image 1, configurable via "IMAGES_OPENAI_API_PARAMS" environment variable or through the admin interface, enabling cost-effective image generation with low, medium, or high quality options. [#19228](https://github.com/open-webui/open-webui/issues/19228)
+- 🖼️ Image editing can now be independently enabled or disabled via admin settings, allowing administrators to control whether sequential image prompts trigger image editing or new image generation, configurable via "ENABLE_IMAGE_EDIT" environment variable. [#19284](https://github.com/open-webui/open-webui/issues/19284)
+- 🔐 SSRF protection was implemented with a configurable URL blocklist that prevents access to cloud metadata endpoints and private networks, with default protections for AWS, Google Cloud, Azure, and Alibaba Cloud metadata services, customizable via "WEB_FETCH_FILTER_LIST" environment variable. [#19201](https://github.com/open-webui/open-webui/pull/19201)
+- ⚡ Workspace models page now supports server-side pagination dramatically improving load times and usability for instances with large numbers of workspace models.
+- 🔍 Hybrid search now indexes file metadata including filenames, titles, headings, sources, and snippets alongside document content, enabling keyword queries to surface documents where search terms appear only in metadata, configurable via "ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS" environment variable. [#19095](https://github.com/open-webui/open-webui/pull/19095)
+- 📂 Knowledge base upload page now supports folder drag-and-drop with recursive directory handling, enabling batch uploads of entire directory structures instead of requiring individual file selection. [#19320](https://github.com/open-webui/open-webui/pull/19320)
+- 🤖 Model cloning is now available in admin settings, allowing administrators to quickly create workspace models based on existing base models through a "Clone" option in the model dropdown menu. [#17937](https://github.com/open-webui/open-webui/pull/17937)
+- 🎨 UI scale adjustment is now available in interface settings, allowing users to increase the size of the entire interface from 1.0x to 1.5x for improved accessibility and readability, particularly beneficial for users with visual impairments. [#19186](https://github.com/open-webui/open-webui/pull/19186)
+- 📌 Default pinned models can now be configured by administrators for all new users, mirroring the behavior of default models where admin-configured defaults apply only to users who haven't customized their pinned models, configurable via "DEFAULT_PINNED_MODELS" environment variable. [#19273](https://github.com/open-webui/open-webui/pull/19273)
+- 🎙️ Text-to-Speech and Speech-to-Text services now receive user information headers when "ENABLE_FORWARD_USER_INFO_HEADERS" is enabled, allowing external TTS and STT providers to implement user-specific personalization, rate limiting, and usage tracking. [#19323](https://github.com/open-webui/open-webui/pull/19323), [#19312](https://github.com/open-webui/open-webui/issues/19312)
+- 🎙️ Voice mode now supports custom system prompts via "VOICE_MODE_PROMPT_TEMPLATE" configuration, allowing administrators to control response style and behavior for voice interactions. [#18607](https://github.com/open-webui/open-webui/pull/18607)
+- 🔧 WebSocket and Redis configuration options are now available including debug logging controls, custom ping timeout and interval settings, and arbitrary Redis connection options via "WEBSOCKET_SERVER_LOGGING", "WEBSOCKET_SERVER_ENGINEIO_LOGGING", "WEBSOCKET_SERVER_PING_TIMEOUT", "WEBSOCKET_SERVER_PING_INTERVAL", and "WEBSOCKET_REDIS_OPTIONS" environment variables. [#19091](https://github.com/open-webui/open-webui/pull/19091)
+- 🔧 MCP OAuth dynamic client registration now automatically detects and uses the appropriate token endpoint authentication method from server-supported options, enabling compatibility with OAuth servers that only support "client_secret_basic" instead of "client_secret_post". [#19193](https://github.com/open-webui/open-webui/issues/19193)
+- 🔧 Custom headers can now be configured for remote MCP and OpenAPI tool server connections, enabling integration with services that require additional authentication headers. [#18918](https://github.com/open-webui/open-webui/issues/18918)
+- 🔍 Perplexity Search now supports custom API endpoints via "PERPLEXITY_SEARCH_API_URL" configuration and automatically forwards user information headers to enable personalized search experiences. [#19147](https://github.com/open-webui/open-webui/pull/19147)
+- 🔍 User information headers can now be optionally forwarded to external web search engines when "ENABLE_FORWARD_USER_INFO_HEADERS" is enabled. [#19043](https://github.com/open-webui/open-webui/pull/19043)
+- 📊 Daily active user metric is now available for monitoring, tracking unique users active since midnight UTC via the "webui.users.active.today" Prometheus gauge. [#19236](https://github.com/open-webui/open-webui/pull/19236), [#19234](https://github.com/open-webui/open-webui/issues/19234)
+- 📊 Audit log file path is now configurable via "AUDIT_LOGS_FILE_PATH" environment variable, enabling storage in separate volumes or custom locations. [#19173](https://github.com/open-webui/open-webui/pull/19173)
+- 🎨 Sidebar collapse states for model lists and group information are now persistent across page refreshes, remembering user preferences through browser-based storage. [#19159](https://github.com/open-webui/open-webui/issues/19159)
+- 🎨 Background image display was enhanced with semi-transparent overlays for navbar and sidebar, creating a seamless and visually cohesive design across the entire interface. [#19157](https://github.com/open-webui/open-webui/issues/19157)
+- 📋 Tables in chat messages now include a copy button that appears on hover, enabling quick copying of table content alongside the existing CSV export functionality. [#19162](https://github.com/open-webui/open-webui/issues/19162)
+- 📝 Notes can now be created directly via the "/notes/new" URL endpoint with optional title and content query parameters, enabling faster note creation through bookmarks and shortcuts. [#19195](https://github.com/open-webui/open-webui/issues/19195)
+- 🏷️ Tag suggestions are now context-aware, displaying only relevant tags when creating or editing models versus chat conversations, preventing confusion between model and chat tags. [#19135](https://github.com/open-webui/open-webui/issues/19135)
+- ✍️ Prompt autocompletion is now available independently of the rich text input setting, improving accessibility to the feature. [#19150](https://github.com/open-webui/open-webui/issues/19150)
+- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌐 Translations for Simplified Chinese, Traditional Chinese, Portuguese (Brazil), Catalan, Spanish (Spain), Finnish, Irish, Farsi, Swedish, Danish, German, Korean, and Thai were improved and expanded.
+
+### Fixed
+
+- 🤖 Model update functionality now works correctly, resolving a database parameter binding error that prevented saving changes to model configurations via the Save & Update button. [#19335](https://github.com/open-webui/open-webui/issues/19335)
+- 🖼️ Multiple input images for image editing and generation are now correctly passed as an array using the "image[]" parameter syntax, enabling proper multi-image reference functionality with models like GPT Image 1. [#19339](https://github.com/open-webui/open-webui/issues/19339)
+- 📱 PWA installations on iOS now properly refresh after server container restarts, resolving freezing issues by automatically unregistering service workers when version or deployment changes are detected. [#19316](https://github.com/open-webui/open-webui/pull/19316)
+- 🗄️ S3 Vectors collection detection now correctly handles buckets with more than 2000 indexes by using direct index lookup instead of paginated list scanning, improving performance by approximately 8x and enabling RAG queries to work reliably at scale. [#19238](https://github.com/open-webui/open-webui/pull/19238), [#19233](https://github.com/open-webui/open-webui/issues/19233)
+- 📈 Feedback retrieval performance was optimized by eliminating N+1 query patterns through database joins, adding server-side pagination and sorting, significantly reducing database load for instances with large feedback datasets. [#17976](https://github.com/open-webui/open-webui/pull/17976)
+- 🔍 Chat search now works correctly with PostgreSQL when chat data contains null bytes, with comprehensive sanitization preventing null bytes during data writes, cleaning existing data on read, and stripping null bytes during search queries to ensure reliable search functionality. [#15616](https://github.com/open-webui/open-webui/issues/15616)
+- 🔍 Hybrid search with reranking now correctly handles attribute validation, preventing errors when collection results lack expected structure. [#19025](https://github.com/open-webui/open-webui/pull/19025), [#17046](https://github.com/open-webui/open-webui/issues/17046)
+- 🔎 Reranking functionality now works correctly after recent refactoring, resolving crashes caused by incorrect function argument handling. [#19270](https://github.com/open-webui/open-webui/pull/19270)
+- 🤖 Azure OpenAI models now support the "reasoning_effort" parameter, enabling proper configuration of reasoning capabilities for models like GPT-5.1 which default to no reasoning without this setting. [#19290](https://github.com/open-webui/open-webui/issues/19290)
+- 🤖 Models with very long IDs can now be deleted correctly, resolving URL length limitations that previously prevented management operations on such models. [#18230](https://github.com/open-webui/open-webui/pull/18230)
+- 🤖 Model-level streaming settings now correctly apply to API requests, ensuring "Stream Chat Response" toggle properly controls the streaming parameter. [#19154](https://github.com/open-webui/open-webui/issues/19154)
+- 🖼️ Image editing configuration now correctly preserves independent OpenAI API endpoints and keys, preventing them from being overwritten by image generation settings. [#19003](https://github.com/open-webui/open-webui/issues/19003)
+- 🎨 Gemini image edit settings now display correctly in the admin panel, fixing an incorrect configuration key reference that prevented proper rendering of edit options. [#19200](https://github.com/open-webui/open-webui/pull/19200)
+- 🖌️ Image generation settings menu now loads correctly, resolving validation errors with AUTOMATIC1111 API authentication parameters. [#19187](https://github.com/open-webui/open-webui/issues/19187), [#19246](https://github.com/open-webui/open-webui/issues/19246)
+- 📅 Date formatting in chat search and admin user chat search now correctly respects the "DEFAULT_LOCALE" environment variable, displaying dates according to the configured locale instead of always using MM/DD/YYYY format. [#19305](https://github.com/open-webui/open-webui/pull/19305), [#19020](https://github.com/open-webui/open-webui/issues/19020)
+- 📝 RAG template query placeholder escaping logic was corrected to prevent unintended replacements of context values when query placeholders appear in retrieved content. [#19102](https://github.com/open-webui/open-webui/pull/19102), [#19101](https://github.com/open-webui/open-webui/issues/19101)
+- 📄 RAG template prompt duplication was eliminated by removing redundant user query section from the default template. [#19099](https://github.com/open-webui/open-webui/pull/19099), [#19098](https://github.com/open-webui/open-webui/issues/19098)
+- 📋 MinerU local mode configuration no longer incorrectly requires an API key, allowing proper use of local content extraction without external API credentials. [#19258](https://github.com/open-webui/open-webui/issues/19258)
+- 📊 Excel file uploads now work correctly with the addition of the missing msoffcrypto-tool dependency, resolving import errors introduced by the unstructured package upgrade. [#19153](https://github.com/open-webui/open-webui/issues/19153)
+- 📑 Docling parameters now properly handle JSON serialization, preventing exceptions and ensuring configuration changes are saved correctly. [#19072](https://github.com/open-webui/open-webui/pull/19072)
+- 🛠️ UserValves configuration now correctly isolates settings per tool, preventing configuration contamination when multiple tools with UserValves are used simultaneously. [#19185](https://github.com/open-webui/open-webui/pull/19185), [#15569](https://github.com/open-webui/open-webui/issues/15569)
+- 🔧 Tool selection prompt now correctly handles user messages without duplication, removing redundant query prefixes and improving prompt clarity. [#19122](https://github.com/open-webui/open-webui/pull/19122), [#19121](https://github.com/open-webui/open-webui/issues/19121)
+- 📝 Notes chat feature now correctly submits messages to the completions endpoint, resolving errors that prevented AI model interactions. [#19079](https://github.com/open-webui/open-webui/pull/19079)
+- 📝 Note PDF downloads now sanitize HTML content using DOMPurify before rendering, preventing potential DOM-based XSS attacks from malicious content in notes. [Commit](https://github.com/open-webui/open-webui/commit/03cc6ce8eb5c055115406e2304fbf7e3338b8dce)
+- 📁 Archived chats now have their folder associations automatically removed to prevent unintended deletion when their previous folder is deleted. [#14578](https://github.com/open-webui/open-webui/issues/14578)
+- 🔐 ElevenLabs API key is now properly obfuscated in the admin settings page, preventing plain text exposure of sensitive credentials. [#19262](https://github.com/open-webui/open-webui/pull/19262), [#19260](https://github.com/open-webui/open-webui/issues/19260)
+- 🔧 MCP OAuth server metadata discovery now follows the correct specification order, ensuring proper authentication flow compliance. [#19244](https://github.com/open-webui/open-webui/pull/19244)
+- 🔒 API key endpoint restrictions now properly enforce access controls for all endpoints including SCIM, preventing unintended access when "API_KEY_ALLOWED_ENDPOINTS" is configured. [#19168](https://github.com/open-webui/open-webui/issues/19168)
+- 🔓 OAuth role claim parsing now supports both flat and nested claim structures, enabling compatibility with OAuth providers that deliver claims as direct properties on the user object rather than nested structures. [#19286](https://github.com/open-webui/open-webui/pull/19286)
+- 🔑 OAuth MCP server verification now correctly extracts the access token value for authorization headers instead of sending the entire token dictionary. [#19149](https://github.com/open-webui/open-webui/pull/19149), [#19148](https://github.com/open-webui/open-webui/issues/19148)
+- ⚙️ OAuth dynamic client registration now correctly converts empty strings to None for optional fields, preventing validation failures in MCP package integration. [#19144](https://github.com/open-webui/open-webui/pull/19144), [#19129](https://github.com/open-webui/open-webui/issues/19129)
+- 🔐 OIDC authentication now correctly passes client credentials in access token requests, ensuring compatibility with providers that require these parameters per RFC 6749. [#19132](https://github.com/open-webui/open-webui/pull/19132), [#19131](https://github.com/open-webui/open-webui/issues/19131)
+- 🔗 OAuth client creation now respects configured token endpoint authentication methods instead of defaulting to basic authentication, preventing failures with servers that don't support basic auth. [#19165](https://github.com/open-webui/open-webui/pull/19165)
+- 📋 Text copied from chat responses in Chrome now pastes without background formatting, improving readability when pasting into word processors. [#19083](https://github.com/open-webui/open-webui/issues/19083)
+
+### Changed
+
+- 🗄️ Group membership data storage was refactored from JSON arrays to a dedicated relational database table, significantly improving query performance and scalability for instances with large numbers of users and groups, while API responses now return member counts instead of full user ID arrays. [#19239](https://github.com/open-webui/open-webui/pull/19239)
+- 📄 MinerU parameter handling was refactored to pass parameters directly to the API, improving flexibility and fixing VLM backend configuration. [#19105](https://github.com/open-webui/open-webui/pull/19105), [#18446](https://github.com/open-webui/open-webui/discussions/18446)
+- 🔐 API key creation is now controlled by granular user and group permissions, with the "ENABLE_API_KEY" environment variable renamed to "ENABLE_API_KEYS" and disabled by default, requiring explicit configuration at both the global and user permission levels, while related environment variables "ENABLE_API_KEY_ENDPOINT_RESTRICTIONS" and "API_KEY_ALLOWED_ENDPOINTS" were renamed to "ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS" and "API_KEYS_ALLOWED_ENDPOINTS" respectively. [#18336](https://github.com/open-webui/open-webui/pull/18336)
+
 ## [0.6.36] - 2025-11-07
 
 ### Added

Dockerfile

@@ -13,6 +13,7 @@ ARG USE_CUDA_VER=cu128
 # IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
 ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
 ARG USE_RERANKING_MODEL=""
+ARG USE_AUXILIARY_EMBEDDING_MODEL=TaylorAI/bge-micro-v2
 
 # Tiktoken encoding name; models to use can be found at https://huggingface.co/models?library=tiktoken
 ARG USE_TIKTOKEN_ENCODING_NAME="cl100k_base"
@@ -42,7 +43,7 @@ ENV APP_BUILD_HASH=${BUILD_HASH}
 RUN npm run build
 
 ######## WebUI backend ########
-FROM python:3.11-slim-bookworm AS base
+FROM python:3.11.14-slim-bookworm AS base
 
 # Use args
 ARG USE_CUDA
@@ -52,9 +53,13 @@ ARG USE_SLIM
 ARG USE_PERMISSION_HARDENING
 ARG USE_EMBEDDING_MODEL
 ARG USE_RERANKING_MODEL
+ARG USE_AUXILIARY_EMBEDDING_MODEL
 ARG UID
 ARG GID
 
+# Python settings
+ENV PYTHONUNBUFFERED=1
+
 ## Basis ##
 ENV ENV=prod \
     PORT=8080 \
@@ -64,7 +69,8 @@ ENV ENV=prod \
     USE_SLIM_DOCKER=${USE_SLIM} \
     USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
     USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL} \
-    USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL}
+    USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL} \
+    USE_AUXILIARY_EMBEDDING_MODEL_DOCKER=${USE_AUXILIARY_EMBEDDING_MODEL}
 
 ## Basis URL Config ##
 ENV OLLAMA_BASE_URL="/ollama" \
@@ -85,6 +91,7 @@ ENV WHISPER_MODEL="base" \
 ## RAG Embedding model settings ##
 ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
     RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
+    AUXILIARY_EMBEDDING_MODEL="$USE_AUXILIARY_EMBEDDING_MODEL_DOCKER" \
     SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
 
 ## Tiktoken model settings ##
@@ -133,6 +140,7 @@ RUN pip3 install --no-cache-dir uv && \
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
+    python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ.get('AUXILIARY_EMBEDDING_MODEL', 'TaylorAI/bge-micro-v2'), device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     else \
@@ -140,6 +148,7 @@ RUN pip3 install --no-cache-dir uv && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     if [ "$USE_SLIM" != "true" ]; then \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
+    python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ.get('AUXILIARY_EMBEDDING_MODEL', 'TaylorAI/bge-micro-v2'), device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
     python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     fi; \

INSTALLATION.md

@@ -1,35 +0,0 @@
-### Installing Both Ollama and Open WebUI Using Kustomize
-
-For cpu-only pod
-
-```bash
-kubectl apply -f ./kubernetes/manifest/base
-```
-
-For gpu-enabled pod
-
-```bash
-kubectl apply -k ./kubernetes/manifest
-```
-
-### Installing Both Ollama and Open WebUI Using Helm
-
-Package Helm file first
-
-```bash
-helm package ./kubernetes/helm/
-```
-
-For cpu-only pod
-
-```bash
-helm install ollama-webui ./ollama-webui-*.tgz
-```
-
-For gpu-enabled pod
-
-```bash
-helm install ollama-webui ./ollama-webui-*.tgz --set ollama.resources.limits.nvidia.com/gpu="1"
-```
-
-Check the `kubernetes/helm/values.yaml` file to know which parameters are available for customization

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2023-2025 Timothy Jaeryang Baek (Open WebUI)
+Copyright (c) 2023- Open WebUI Inc. [Created by Timothy Jaeryang Baek]
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

README.md

@@ -10,11 +10,13 @@
 [![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
 [![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/tjbck)
 
+![Open WebUI Banner](./banner.png)
+
 **Open WebUI is an [extensible](https://docs.openwebui.com/features/plugin/), feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline.** It supports various LLM runners like **Ollama** and **OpenAI-compatible APIs**, with **built-in inference engine** for RAG, making it a **powerful AI deployment solution**.
 
 Passionate about open-source AI? [Join our team →](https://careers.openwebui.com/)
 
-![Open WebUI Demo](./demo.gif)
+![Open WebUI Demo](./demo.png)
 
 > [!TIP]  
 > **Looking for an [Enterprise Plan](https://docs.openwebui.com/enterprise)?** – **[Speak with Our Sales Team Today!](https://docs.openwebui.com/enterprise)**
@@ -31,32 +33,44 @@ For more information, be sure to check out our [Open WebUI Documentation](https:
 
 - 🛡️ **Granular Permissions and User Groups**: By allowing administrators to create detailed user roles and permissions, we ensure a secure user environment. This granularity not only enhances security but also allows for customized user experiences, fostering a sense of ownership and responsibility amongst users.
 
-- 🔄 **SCIM 2.0 Support**: Enterprise-grade user and group provisioning through SCIM 2.0 protocol, enabling seamless integration with identity providers like Okta, Azure AD, and Google Workspace for automated user lifecycle management.
-
 - 📱 **Responsive Design**: Enjoy a seamless experience across Desktop PC, Laptop, and Mobile devices.
 
 - 📱 **Progressive Web App (PWA) for Mobile**: Enjoy a native app-like experience on your mobile device with our PWA, providing offline access on localhost and a seamless user interface.
 
 - ✒️🔢 **Full Markdown and LaTeX Support**: Elevate your LLM experience with comprehensive Markdown and LaTeX capabilities for enriched interaction.
 
-- 🎤📹 **Hands-Free Voice/Video Call**: Experience seamless communication with integrated hands-free voice and video call features, allowing for a more dynamic and interactive chat environment.
+- 🎤📹 **Hands-Free Voice/Video Call**: Experience seamless communication with integrated hands-free voice and video call features using multiple Speech-to-Text providers (Local Whisper, OpenAI, Deepgram, Azure) and Text-to-Speech engines (Azure, ElevenLabs, OpenAI, Transformers, WebAPI), allowing for dynamic and interactive chat environments.
 
 - 🛠️ **Model Builder**: Easily create Ollama models via the Web UI. Create and add custom characters/agents, customize chat elements, and import models effortlessly through [Open WebUI Community](https://openwebui.com/) integration.
 
 - 🐍 **Native Python Function Calling Tool**: Enhance your LLMs with built-in code editor support in the tools workspace. Bring Your Own Function (BYOF) by simply adding your pure Python functions, enabling seamless integration with LLMs.
 
-- 📚 **Local RAG Integration**: Dive into the future of chat interactions with groundbreaking Retrieval Augmented Generation (RAG) support. This feature seamlessly integrates document interactions into your chat experience. You can load documents directly into the chat or add files to your document library, effortlessly accessing them using the `#` command before a query.
+- 💾 **Persistent Artifact Storage**: Built-in key-value storage API for artifacts, enabling features like journals, trackers, leaderboards, and collaborative tools with both personal and shared data scopes across sessions.
 
-- 🔍 **Web Search for RAG**: Perform web searches using providers like `SearXNG`, `Google PSE`, `Brave Search`, `serpstack`, `serper`, `Serply`, `DuckDuckGo`, `TavilySearch`, `SearchApi` and `Bing` and inject the results directly into your chat experience.
+- 📚 **Local RAG Integration**: Dive into the future of chat interactions with groundbreaking Retrieval Augmented Generation (RAG) support using your choice of 9 vector databases and multiple content extraction engines (Tika, Docling, Document Intelligence, Mistral OCR, External loaders). Load documents directly into chat or add files to your document library, effortlessly accessing them using the `#` command before a query.
+
+- 🔍 **Web Search for RAG**: Perform web searches using 15+ providers including `SearXNG`, `Google PSE`, `Brave Search`, `Kagi`, `Mojeek`, `Tavily`, `Perplexity`, `serpstack`, `serper`, `Serply`, `DuckDuckGo`, `SearchApi`, `SerpApi`, `Bing`, `Jina`, `Exa`, `Sougou`, `Azure AI Search`, and `Ollama Cloud`, injecting results directly into your chat experience.
 
 - 🌐 **Web Browsing Capability**: Seamlessly integrate websites into your chat experience using the `#` command followed by a URL. This feature allows you to incorporate web content directly into your conversations, enhancing the richness and depth of your interactions.
 
-- 🎨 **Image Generation Integration**: Seamlessly incorporate image generation capabilities using options such as AUTOMATIC1111 API or ComfyUI (local), and OpenAI's DALL-E (external), enriching your chat experience with dynamic visual content.
+- 🎨 **Image Generation & Editing Integration**: Create and edit images using multiple engines including OpenAI's DALL-E, Gemini, ComfyUI (local), and AUTOMATIC1111 (local), with support for both generation and prompt-based editing workflows.
 
 - ⚙️ **Many Models Conversations**: Effortlessly engage with various models simultaneously, harnessing their unique strengths for optimal responses. Enhance your experience by leveraging a diverse set of models in parallel.
 
 - 🔐 **Role-Based Access Control (RBAC)**: Ensure secure access with restricted permissions; only authorized individuals can access your Ollama, and exclusive model creation/pulling rights are reserved for administrators.
 
+- 🗄️ **Flexible Database & Storage Options**: Choose from SQLite (with optional encryption), PostgreSQL, or configure cloud storage backends (S3, Google Cloud Storage, Azure Blob Storage) for scalable deployments.
+
+- 🔍 **Advanced Vector Database Support**: Select from 9 vector database options including ChromaDB, PGVector, Qdrant, Milvus, Elasticsearch, OpenSearch, Pinecone, S3Vector, and Oracle 23ai for optimal RAG performance.
+
+- 🔐 **Enterprise Authentication**: Full support for LDAP/Active Directory integration, SCIM 2.0 automated provisioning, and SSO via trusted headers alongside OAuth providers. Enterprise-grade user and group provisioning through SCIM 2.0 protocol, enabling seamless integration with identity providers like Okta, Azure AD, and Google Workspace for automated user lifecycle management.
+
+- ☁️ **Cloud-Native Integration**: Native support for Google Drive and OneDrive/SharePoint file picking, enabling seamless document import from enterprise cloud storage.
+
+- 📊 **Production Observability**: Built-in OpenTelemetry support for traces, metrics, and logs, enabling comprehensive monitoring with your existing observability stack.
+
+- ⚖️ **Horizontal Scalability**: Redis-backed session management and WebSocket support for multi-worker and multi-node deployments behind load balancers.
+
 - 🌐🌍 **Multilingual Support**: Experience Open WebUI in your preferred language with our internationalization (i18n) support. Join us in expanding our supported languages! We're actively seeking contributors!
 
 - 🧩 **Pipelines, Open WebUI Plugin Support**: Seamlessly integrate custom logic and Python libraries into Open WebUI using [Pipelines Plugin Framework](https://github.com/open-webui/pipelines). Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. [Examples](https://github.com/open-webui/pipelines/tree/main/examples) include **Function Calling**, User **Rate Limiting** to control access, **Usage Monitoring** with tools like Langfuse, **Live Translation with LibreTranslate** for multilingual support, **Toxic Message Filtering** and much more.
@@ -176,14 +190,6 @@ docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=
 
 ### Keeping Your Docker Installation Up-to-Date
 
-In case you want to update your local Docker installation to the latest version, you can do it with [Watchtower](https://containrrr.dev/watchtower/):
-
-```bash
-docker run --rm --volume /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower --run-once open-webui
-```
-
-In the last part of the command, replace `open-webui` with your container name if it is different.
-
 Check our Updating Guide available in our [Open WebUI Documentation](https://docs.openwebui.com/getting-started/updating).
 
 ### Using the Dev Branch 🌙

backend/open_webui/config.py

@@ -19,6 +19,7 @@ from authlib.integrations.starlette_client import OAuth
 from open_webui.env import (
     DATA_DIR,
     DATABASE_URL,
+    ENABLE_DB_MIGRATIONS,
     ENV,
     REDIS_URL,
     REDIS_KEY_PREFIX,
@@ -67,7 +68,8 @@ def run_migrations():
         log.exception(f"Error running migrations: {e}")
 
 
-run_migrations()
+if ENABLE_DB_MIGRATIONS:
+    run_migrations()
 
 
 class Config(Base):
@@ -287,25 +289,30 @@ class AppConfig:
 # WEBUI_AUTH (Required for security)
 ####################################
 
-ENABLE_API_KEY = PersistentConfig(
-    "ENABLE_API_KEY",
-    "auth.api_key.enable",
-    os.environ.get("ENABLE_API_KEY", "True").lower() == "true",
+ENABLE_API_KEYS = PersistentConfig(
+    "ENABLE_API_KEYS",
+    "auth.enable_api_keys",
+    os.environ.get("ENABLE_API_KEYS", "False").lower() == "true",
 )
 
-ENABLE_API_KEY_ENDPOINT_RESTRICTIONS = PersistentConfig(
-    "ENABLE_API_KEY_ENDPOINT_RESTRICTIONS",
+ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS = PersistentConfig(
+    "ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS",
     "auth.api_key.endpoint_restrictions",
-    os.environ.get("ENABLE_API_KEY_ENDPOINT_RESTRICTIONS", "False").lower() == "true",
+    os.environ.get(
+        "ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS",
+        os.environ.get("ENABLE_API_KEY_ENDPOINT_RESTRICTIONS", "False"),
+    ).lower()
+    == "true",
 )
 
-API_KEY_ALLOWED_ENDPOINTS = PersistentConfig(
-    "API_KEY_ALLOWED_ENDPOINTS",
+API_KEYS_ALLOWED_ENDPOINTS = PersistentConfig(
+    "API_KEYS_ALLOWED_ENDPOINTS",
     "auth.api_key.allowed_endpoints",
-    os.environ.get("API_KEY_ALLOWED_ENDPOINTS", ""),
+    os.environ.get(
+        "API_KEYS_ALLOWED_ENDPOINTS", os.environ.get("API_KEY_ALLOWED_ENDPOINTS", "")
+    ),
 )
 
-
 JWT_EXPIRES_IN = PersistentConfig(
     "JWT_EXPIRES_IN", "auth.jwt_expiry", os.environ.get("JWT_EXPIRES_IN", "4w")
 )
@@ -578,14 +585,16 @@ OAUTH_ROLES_CLAIM = PersistentConfig(
     os.environ.get("OAUTH_ROLES_CLAIM", "roles"),
 )
 
-SEP = os.environ.get("OAUTH_ROLES_SEPARATOR", ",")
+OAUTH_ROLES_SEPARATOR = os.environ.get("OAUTH_ROLES_SEPARATOR", ",")
 
 OAUTH_ALLOWED_ROLES = PersistentConfig(
     "OAUTH_ALLOWED_ROLES",
     "oauth.allowed_roles",
     [
         role.strip()
-        for role in os.environ.get("OAUTH_ALLOWED_ROLES", f"user{SEP}admin").split(SEP)
+        for role in os.environ.get(
+            "OAUTH_ALLOWED_ROLES", f"user{OAUTH_ROLES_SEPARATOR}admin"
+        ).split(OAUTH_ROLES_SEPARATOR)
         if role
     ],
 )
@@ -595,7 +604,9 @@ OAUTH_ADMIN_ROLES = PersistentConfig(
     "oauth.admin_roles",
     [
         role.strip()
-        for role in os.environ.get("OAUTH_ADMIN_ROLES", "admin").split(SEP)
+        for role in os.environ.get("OAUTH_ADMIN_ROLES", "admin").split(
+            OAUTH_ROLES_SEPARATOR
+        )
         if role
     ],
 )
@@ -615,6 +626,17 @@ OAUTH_UPDATE_PICTURE_ON_LOGIN = PersistentConfig(
     os.environ.get("OAUTH_UPDATE_PICTURE_ON_LOGIN", "False").lower() == "true",
 )
 
+OAUTH_ACCESS_TOKEN_REQUEST_INCLUDE_CLIENT_ID = (
+    os.environ.get("OAUTH_ACCESS_TOKEN_REQUEST_INCLUDE_CLIENT_ID", "False").lower()
+    == "true"
+)
+
+OAUTH_AUDIENCE = PersistentConfig(
+    "OAUTH_AUDIENCE",
+    "oauth.audience",
+    os.environ.get("OAUTH_AUDIENCE", ""),
+)
+
 
 def load_oauth_providers():
     OAUTH_PROVIDERS.clear()
@@ -1124,6 +1146,7 @@ ENABLE_LOGIN_FORM = PersistentConfig(
     os.environ.get("ENABLE_LOGIN_FORM", "True").lower() == "true",
 )
 
+ENABLE_PASSWORD_AUTH = os.environ.get("ENABLE_PASSWORD_AUTH", "True").lower() == "true"
 
 DEFAULT_LOCALE = PersistentConfig(
     "DEFAULT_LOCALE",
@@ -1135,6 +1158,12 @@ DEFAULT_MODELS = PersistentConfig(
     "DEFAULT_MODELS", "ui.default_models", os.environ.get("DEFAULT_MODELS", None)
 )
 
+DEFAULT_PINNED_MODELS = PersistentConfig(
+    "DEFAULT_PINNED_MODELS",
+    "ui.default_pinned_models",
+    os.environ.get("DEFAULT_PINNED_MODELS", None),
+)
+
 try:
     default_prompt_suggestions = json.loads(
         os.environ.get("DEFAULT_PROMPT_SUGGESTIONS", "[]")
@@ -1191,6 +1220,12 @@ DEFAULT_USER_ROLE = PersistentConfig(
     os.getenv("DEFAULT_USER_ROLE", "pending"),
 )
 
+DEFAULT_GROUP_ID = PersistentConfig(
+    "DEFAULT_GROUP_ID",
+    "ui.default_group_id",
+    os.environ.get("DEFAULT_GROUP_ID", ""),
+)
+
 PENDING_USER_OVERLAY_TITLE = PersistentConfig(
     "PENDING_USER_OVERLAY_TITLE",
     "ui.pending_user_overlay_title",
@@ -1230,6 +1265,40 @@ USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS = (
     os.environ.get("USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS", "False").lower() == "true"
 )
 
+USER_PERMISSIONS_WORKSPACE_MODELS_IMPORT = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_MODELS_IMPORT", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_MODELS_EXPORT = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_MODELS_EXPORT", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_PROMPTS_IMPORT = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_PROMPTS_IMPORT", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_PROMPTS_EXPORT = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_PROMPTS_EXPORT", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_TOOLS_IMPORT = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_TOOLS_IMPORT", "False").lower() == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_TOOLS_EXPORT = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_TOOLS_EXPORT", "False").lower() == "true"
+)
+
+
+USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_SHARING = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_SHARING", "False").lower()
+    == "true"
+)
+
 USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING = (
     os.environ.get(
         "USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING", "False"
@@ -1237,8 +1306,10 @@ USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING = (
     == "true"
 )
 
-USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING = (
-    os.environ.get("USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING", "False").lower()
+USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_SHARING = (
+    os.environ.get(
+        "USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_SHARING", "False"
+    ).lower()
     == "true"
 )
 
@@ -1249,6 +1320,11 @@ USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_PUBLIC_SHARING = (
     == "true"
 )
 
+USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_SHARING = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_SHARING", "False").lower()
+    == "true"
+)
+
 USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_PUBLIC_SHARING = (
     os.environ.get(
         "USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_PUBLIC_SHARING", "False"
@@ -1256,6 +1332,12 @@ USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_PUBLIC_SHARING = (
     == "true"
 )
 
+
+USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_SHARING = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_SHARING", "False").lower()
+    == "true"
+)
+
 USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_PUBLIC_SHARING = (
     os.environ.get(
         "USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_PUBLIC_SHARING", "False"
@@ -1264,6 +1346,16 @@ USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_PUBLIC_SHARING = (
 )
 
 
+USER_PERMISSIONS_NOTES_ALLOW_SHARING = (
+    os.environ.get("USER_PERMISSIONS_NOTES_ALLOW_SHARING", "False").lower() == "true"
+)
+
+USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING = (
+    os.environ.get("USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING", "False").lower()
+    == "true"
+)
+
+
 USER_PERMISSIONS_CHAT_CONTROLS = (
     os.environ.get("USER_PERMISSIONS_CHAT_CONTROLS", "True").lower() == "true"
 )
@@ -1362,10 +1454,31 @@ USER_PERMISSIONS_FEATURES_CODE_INTERPRETER = (
     == "true"
 )
 
+USER_PERMISSIONS_FEATURES_FOLDERS = (
+    os.environ.get("USER_PERMISSIONS_FEATURES_FOLDERS", "True").lower() == "true"
+)
+
 USER_PERMISSIONS_FEATURES_NOTES = (
     os.environ.get("USER_PERMISSIONS_FEATURES_NOTES", "True").lower() == "true"
 )
 
+USER_PERMISSIONS_FEATURES_CHANNELS = (
+    os.environ.get("USER_PERMISSIONS_FEATURES_CHANNELS", "True").lower() == "true"
+)
+
+USER_PERMISSIONS_FEATURES_API_KEYS = (
+    os.environ.get("USER_PERMISSIONS_FEATURES_API_KEYS", "False").lower() == "true"
+)
+
+USER_PERMISSIONS_FEATURES_MEMORIES = (
+    os.environ.get("USER_PERMISSIONS_FEATURES_MEMORIES", "True").lower() == "true"
+)
+
+
+USER_PERMISSIONS_SETTINGS_INTERFACE = (
+    os.environ.get("USER_PERMISSIONS_SETTINGS_INTERFACE", "True").lower() == "true"
+)
+
 
 DEFAULT_USER_PERMISSIONS = {
     "workspace": {
@@ -1373,12 +1486,23 @@ DEFAULT_USER_PERMISSIONS = {
         "knowledge": USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ACCESS,
         "prompts": USER_PERMISSIONS_WORKSPACE_PROMPTS_ACCESS,
         "tools": USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS,
+        "models_import": USER_PERMISSIONS_WORKSPACE_MODELS_IMPORT,
+        "models_export": USER_PERMISSIONS_WORKSPACE_MODELS_EXPORT,
+        "prompts_import": USER_PERMISSIONS_WORKSPACE_PROMPTS_IMPORT,
+        "prompts_export": USER_PERMISSIONS_WORKSPACE_PROMPTS_EXPORT,
+        "tools_import": USER_PERMISSIONS_WORKSPACE_TOOLS_IMPORT,
+        "tools_export": USER_PERMISSIONS_WORKSPACE_TOOLS_EXPORT,
     },
     "sharing": {
+        "models": USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_SHARING,
         "public_models": USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING,
+        "knowledge": USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_SHARING,
         "public_knowledge": USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_PUBLIC_SHARING,
+        "prompts": USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_SHARING,
         "public_prompts": USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_PUBLIC_SHARING,
+        "tools": USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_SHARING,
         "public_tools": USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_PUBLIC_SHARING,
+        "notes": USER_PERMISSIONS_NOTES_ALLOW_SHARING,
         "public_notes": USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING,
     },
     "chat": {
@@ -1403,11 +1527,20 @@ DEFAULT_USER_PERMISSIONS = {
         "temporary_enforced": USER_PERMISSIONS_CHAT_TEMPORARY_ENFORCED,
     },
     "features": {
+        # General features
+        "api_keys": USER_PERMISSIONS_FEATURES_API_KEYS,
+        "notes": USER_PERMISSIONS_FEATURES_NOTES,
+        "folders": USER_PERMISSIONS_FEATURES_FOLDERS,
+        "channels": USER_PERMISSIONS_FEATURES_CHANNELS,
         "direct_tool_servers": USER_PERMISSIONS_FEATURES_DIRECT_TOOL_SERVERS,
+        # Chat features
         "web_search": USER_PERMISSIONS_FEATURES_WEB_SEARCH,
         "image_generation": USER_PERMISSIONS_FEATURES_IMAGE_GENERATION,
         "code_interpreter": USER_PERMISSIONS_FEATURES_CODE_INTERPRETER,
-        "notes": USER_PERMISSIONS_FEATURES_NOTES,
+        "memories": USER_PERMISSIONS_FEATURES_MEMORIES,
+    },
+    "settings": {
+        "interface": USER_PERMISSIONS_SETTINGS_INTERFACE,
     },
 }
 
@@ -1417,6 +1550,18 @@ USER_PERMISSIONS = PersistentConfig(
     DEFAULT_USER_PERMISSIONS,
 )
 
+ENABLE_FOLDERS = PersistentConfig(
+    "ENABLE_FOLDERS",
+    "folders.enable",
+    os.environ.get("ENABLE_FOLDERS", "True").lower() == "true",
+)
+
+FOLDER_MAX_FILE_COUNT = PersistentConfig(
+    "FOLDER_MAX_FILE_COUNT",
+    "folders.max_file_count",
+    os.environ.get("FOLDER_MAX_FILE_COUNT", ""),
+)
+
 ENABLE_CHANNELS = PersistentConfig(
     "ENABLE_CHANNELS",
     "channels.enable",
@@ -1429,6 +1574,12 @@ ENABLE_NOTES = PersistentConfig(
     os.environ.get("ENABLE_NOTES", "True").lower() == "true",
 )
 
+ENABLE_USER_STATUS = PersistentConfig(
+    "ENABLE_USER_STATUS",
+    "users.enable_status",
+    os.environ.get("ENABLE_USER_STATUS", "True").lower() == "true",
+)
+
 ENABLE_EVALUATION_ARENA_MODELS = PersistentConfig(
     "ENABLE_EVALUATION_ARENA_MODELS",
     "evaluation.arena.enable",
@@ -1816,6 +1967,38 @@ Output:
 #### Output:
 """
 
+
+VOICE_MODE_PROMPT_TEMPLATE = PersistentConfig(
+    "VOICE_MODE_PROMPT_TEMPLATE",
+    "task.voice.prompt_template",
+    os.environ.get("VOICE_MODE_PROMPT_TEMPLATE", ""),
+)
+
+DEFAULT_VOICE_MODE_PROMPT_TEMPLATE = """You are a friendly, concise voice assistant.
+
+Everything you say will be spoken aloud.
+Keep responses short, clear, and natural.
+
+STYLE:
+- Use simple words and short sentences.
+- Sound warm and conversational.
+- Avoid long explanations, lists, or complex phrasing.
+
+BEHAVIOR:
+- Give the quickest helpful answer first.
+- Offer extra detail only if needed.
+- Ask for clarification only when necessary.
+
+VOICE OPTIMIZATION:
+- Break information into small, easy-to-hear chunks.
+- Avoid dense wording or anything that sounds like reading text.
+
+ERROR HANDLING:
+- If unsure, say so briefly and offer options.
+- If something is unsafe or impossible, decline kindly and suggest a safe alternative.
+
+Stay consistent, helpful, and easy to listen to."""
+
 TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = PersistentConfig(
     "TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE",
     "task.tools.prompt_template",
@@ -1911,6 +2094,12 @@ ENABLE_CODE_INTERPRETER = PersistentConfig(
     os.environ.get("ENABLE_CODE_INTERPRETER", "True").lower() == "true",
 )
 
+ENABLE_MEMORIES = PersistentConfig(
+    "ENABLE_MEMORIES",
+    "memories.enable",
+    os.environ.get("ENABLE_MEMORIES", "True").lower() == "true",
+)
+
 CODE_INTERPRETER_ENGINE = PersistentConfig(
     "CODE_INTERPRETER_ENGINE",
     "code_interpreter.engine",
@@ -2056,6 +2245,11 @@ ENABLE_QDRANT_MULTITENANCY_MODE = (
 )
 QDRANT_COLLECTION_PREFIX = os.environ.get("QDRANT_COLLECTION_PREFIX", "open-webui")
 
+WEAVIATE_HTTP_HOST = os.environ.get("WEAVIATE_HTTP_HOST", "")
+WEAVIATE_HTTP_PORT = int(os.environ.get("WEAVIATE_HTTP_PORT", "8080"))
+WEAVIATE_GRPC_PORT = int(os.environ.get("WEAVIATE_GRPC_PORT", "50051"))
+WEAVIATE_API_KEY = os.environ.get("WEAVIATE_API_KEY")
+
 # OpenSearch
 OPENSEARCH_URI = os.environ.get("OPENSEARCH_URI", "https://localhost:9200")
 OPENSEARCH_SSL = os.environ.get("OPENSEARCH_SSL", "true").lower() == "true"
@@ -2086,6 +2280,16 @@ PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH = int(
     os.environ.get("PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH", "1536")
 )
 
+PGVECTOR_USE_HALFVEC = os.getenv("PGVECTOR_USE_HALFVEC", "false").lower() == "true"
+
+if PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH > 2000 and not PGVECTOR_USE_HALFVEC:
+    raise ValueError(
+        "PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH is set to "
+        f"{PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH}, which exceeds the 2000 dimension limit of the "
+        "'vector' type. Set PGVECTOR_USE_HALFVEC=true to enable the 'halfvec' "
+        "type required for high-dimensional embeddings."
+    )
+
 PGVECTOR_CREATE_EXTENSION = (
     os.getenv("PGVECTOR_CREATE_EXTENSION", "true").lower() == "true"
 )
@@ -2135,6 +2339,85 @@ else:
     except Exception:
         PGVECTOR_POOL_RECYCLE = 3600
 
+PGVECTOR_INDEX_METHOD = os.getenv("PGVECTOR_INDEX_METHOD", "").strip().lower()
+if PGVECTOR_INDEX_METHOD not in ("ivfflat", "hnsw", ""):
+    PGVECTOR_INDEX_METHOD = ""
+
+PGVECTOR_HNSW_M = os.environ.get("PGVECTOR_HNSW_M", 16)
+
+if PGVECTOR_HNSW_M == "":
+    PGVECTOR_HNSW_M = 16
+else:
+    try:
+        PGVECTOR_HNSW_M = int(PGVECTOR_HNSW_M)
+    except Exception:
+        PGVECTOR_HNSW_M = 16
+
+PGVECTOR_HNSW_EF_CONSTRUCTION = os.environ.get("PGVECTOR_HNSW_EF_CONSTRUCTION", 64)
+
+if PGVECTOR_HNSW_EF_CONSTRUCTION == "":
+    PGVECTOR_HNSW_EF_CONSTRUCTION = 64
+else:
+    try:
+        PGVECTOR_HNSW_EF_CONSTRUCTION = int(PGVECTOR_HNSW_EF_CONSTRUCTION)
+    except Exception:
+        PGVECTOR_HNSW_EF_CONSTRUCTION = 64
+
+PGVECTOR_IVFFLAT_LISTS = os.environ.get("PGVECTOR_IVFFLAT_LISTS", 100)
+
+if PGVECTOR_IVFFLAT_LISTS == "":
+    PGVECTOR_IVFFLAT_LISTS = 100
+else:
+    try:
+        PGVECTOR_IVFFLAT_LISTS = int(PGVECTOR_IVFFLAT_LISTS)
+    except Exception:
+        PGVECTOR_IVFFLAT_LISTS = 100
+
+# openGauss
+OPENGAUSS_DB_URL = os.environ.get("OPENGAUSS_DB_URL", DATABASE_URL)
+
+OPENGAUSS_INITIALIZE_MAX_VECTOR_LENGTH = int(
+    os.environ.get("OPENGAUSS_INITIALIZE_MAX_VECTOR_LENGTH", "1536")
+)
+
+OPENGAUSS_POOL_SIZE = os.environ.get("OPENGAUSS_POOL_SIZE", None)
+
+if OPENGAUSS_POOL_SIZE != None:
+    try:
+        OPENGAUSS_POOL_SIZE = int(OPENGAUSS_POOL_SIZE)
+    except Exception:
+        OPENGAUSS_POOL_SIZE = None
+
+OPENGAUSS_POOL_MAX_OVERFLOW = os.environ.get("OPENGAUSS_POOL_MAX_OVERFLOW", 0)
+
+if OPENGAUSS_POOL_MAX_OVERFLOW == "":
+    OPENGAUSS_POOL_MAX_OVERFLOW = 0
+else:
+    try:
+        OPENGAUSS_POOL_MAX_OVERFLOW = int(OPENGAUSS_POOL_MAX_OVERFLOW)
+    except Exception:
+        OPENGAUSS_POOL_MAX_OVERFLOW = 0
+
+OPENGAUSS_POOL_TIMEOUT = os.environ.get("OPENGAUSS_POOL_TIMEOUT", 30)
+
+if OPENGAUSS_POOL_TIMEOUT == "":
+    OPENGAUSS_POOL_TIMEOUT = 30
+else:
+    try:
+        OPENGAUSS_POOL_TIMEOUT = int(OPENGAUSS_POOL_TIMEOUT)
+    except Exception:
+        OPENGAUSS_POOL_TIMEOUT = 30
+
+OPENGAUSS_POOL_RECYCLE = os.environ.get("OPENGAUSS_POOL_RECYCLE", 3600)
+
+if OPENGAUSS_POOL_RECYCLE == "":
+    OPENGAUSS_POOL_RECYCLE = 3600
+else:
+    try:
+        OPENGAUSS_POOL_RECYCLE = int(OPENGAUSS_POOL_RECYCLE)
+    except Exception:
+        OPENGAUSS_POOL_RECYCLE = 3600
+
 # Pinecone
 PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY", None)
 PINECONE_ENVIRONMENT = os.environ.get("PINECONE_ENVIRONMENT", None)
@@ -2318,6 +2601,12 @@ MINERU_API_URL = PersistentConfig(
     os.environ.get("MINERU_API_URL", "http://localhost:8000"),
 )
 
+MINERU_API_TIMEOUT = PersistentConfig(
+    "MINERU_API_TIMEOUT",
+    "rag.mineru_api_timeout",
+    os.environ.get("MINERU_API_TIMEOUT", "300"),
+)
+
 MINERU_API_KEY = PersistentConfig(
     "MINERU_API_KEY",
     "rag.mineru_api_key",
@@ -2360,6 +2649,12 @@ DOCLING_SERVER_URL = PersistentConfig(
     os.getenv("DOCLING_SERVER_URL", "http://docling:5001"),
 )
 
+DOCLING_API_KEY = PersistentConfig(
+    "DOCLING_API_KEY",
+    "rag.docling_api_key",
+    os.getenv("DOCLING_API_KEY", ""),
+)
+
 docling_params = os.getenv("DOCLING_PARAMS", "")
 try:
     docling_params = json.loads(docling_params)
@@ -2372,88 +2667,6 @@ DOCLING_PARAMS = PersistentConfig(
     docling_params,
 )
 
-DOCLING_DO_OCR = PersistentConfig(
-    "DOCLING_DO_OCR",
-    "rag.docling_do_ocr",
-    os.getenv("DOCLING_DO_OCR", "True").lower() == "true",
-)
-
-DOCLING_FORCE_OCR = PersistentConfig(
-    "DOCLING_FORCE_OCR",
-    "rag.docling_force_ocr",
-    os.getenv("DOCLING_FORCE_OCR", "False").lower() == "true",
-)
-
-DOCLING_OCR_ENGINE = PersistentConfig(
-    "DOCLING_OCR_ENGINE",
-    "rag.docling_ocr_engine",
-    os.getenv("DOCLING_OCR_ENGINE", "tesseract"),
-)
-
-DOCLING_OCR_LANG = PersistentConfig(
-    "DOCLING_OCR_LANG",
-    "rag.docling_ocr_lang",
-    os.getenv("DOCLING_OCR_LANG", "eng,fra,deu,spa"),
-)
-
-DOCLING_PDF_BACKEND = PersistentConfig(
-    "DOCLING_PDF_BACKEND",
-    "rag.docling_pdf_backend",
-    os.getenv("DOCLING_PDF_BACKEND", "dlparse_v4"),
-)
-
-DOCLING_TABLE_MODE = PersistentConfig(
-    "DOCLING_TABLE_MODE",
-    "rag.docling_table_mode",
-    os.getenv("DOCLING_TABLE_MODE", "accurate"),
-)
-
-DOCLING_PIPELINE = PersistentConfig(
-    "DOCLING_PIPELINE",
-    "rag.docling_pipeline",
-    os.getenv("DOCLING_PIPELINE", "standard"),
-)
-
-DOCLING_DO_PICTURE_DESCRIPTION = PersistentConfig(
-    "DOCLING_DO_PICTURE_DESCRIPTION",
-    "rag.docling_do_picture_description",
-    os.getenv("DOCLING_DO_PICTURE_DESCRIPTION", "False").lower() == "true",
-)
-
-DOCLING_PICTURE_DESCRIPTION_MODE = PersistentConfig(
-    "DOCLING_PICTURE_DESCRIPTION_MODE",
-    "rag.docling_picture_description_mode",
-    os.getenv("DOCLING_PICTURE_DESCRIPTION_MODE", ""),
-)
-
-
-docling_picture_description_local = os.getenv("DOCLING_PICTURE_DESCRIPTION_LOCAL", "")
-try:
-    docling_picture_description_local = json.loads(docling_picture_description_local)
-except json.JSONDecodeError:
-    docling_picture_description_local = {}
-
-
-DOCLING_PICTURE_DESCRIPTION_LOCAL = PersistentConfig(
-    "DOCLING_PICTURE_DESCRIPTION_LOCAL",
-    "rag.docling_picture_description_local",
-    docling_picture_description_local,
-)
-
-docling_picture_description_api = os.getenv("DOCLING_PICTURE_DESCRIPTION_API", "")
-try:
-    docling_picture_description_api = json.loads(docling_picture_description_api)
-except json.JSONDecodeError:
-    docling_picture_description_api = {}
-
-
-DOCLING_PICTURE_DESCRIPTION_API = PersistentConfig(
-    "DOCLING_PICTURE_DESCRIPTION_API",
-    "rag.docling_picture_description_api",
-    docling_picture_description_api,
-)
-
-
 DOCUMENT_INTELLIGENCE_ENDPOINT = PersistentConfig(
     "DOCUMENT_INTELLIGENCE_ENDPOINT",
     "rag.document_intelligence_endpoint",
@@ -2466,6 +2679,12 @@ DOCUMENT_INTELLIGENCE_KEY = PersistentConfig(
     os.getenv("DOCUMENT_INTELLIGENCE_KEY", ""),
 )
 
+DOCUMENT_INTELLIGENCE_MODEL = PersistentConfig(
+    "DOCUMENT_INTELLIGENCE_MODEL",
+    "rag.document_intelligence_model",
+    os.getenv("DOCUMENT_INTELLIGENCE_MODEL", "prebuilt-layout"),
+)
+
 MISTRAL_OCR_API_BASE_URL = PersistentConfig(
     "MISTRAL_OCR_API_BASE_URL",
     "rag.MISTRAL_OCR_API_BASE_URL",
@@ -2510,6 +2729,13 @@ ENABLE_RAG_HYBRID_SEARCH = PersistentConfig(
     os.environ.get("ENABLE_RAG_HYBRID_SEARCH", "").lower() == "true",
 )
 
+ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS = PersistentConfig(
+    "ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS",
+    "rag.enable_hybrid_search_enriched_texts",
+    os.environ.get("ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS", "False").lower()
+    == "true",
+)
+
 RAG_FULL_CONTEXT = PersistentConfig(
     "RAG_FULL_CONTEXT",
     "rag.full_context",
@@ -2604,6 +2830,12 @@ RAG_EMBEDDING_BATCH_SIZE = PersistentConfig(
     ),
 )
 
+ENABLE_ASYNC_EMBEDDING = PersistentConfig(
+    "ENABLE_ASYNC_EMBEDDING",
+    "rag.enable_async_embedding",
+    os.environ.get("ENABLE_ASYNC_EMBEDDING", "True").lower() == "true",
+)
+
 RAG_EMBEDDING_QUERY_PREFIX = os.environ.get("RAG_EMBEDDING_QUERY_PREFIX", None)
 
 RAG_EMBEDDING_CONTENT_PREFIX = os.environ.get("RAG_EMBEDDING_CONTENT_PREFIX", None)
@@ -2648,6 +2880,12 @@ RAG_EXTERNAL_RERANKER_API_KEY = PersistentConfig(
     os.environ.get("RAG_EXTERNAL_RERANKER_API_KEY", ""),
 )
 
+RAG_EXTERNAL_RERANKER_TIMEOUT = PersistentConfig(
+    "RAG_EXTERNAL_RERANKER_TIMEOUT",
+    "rag.external_reranker_timeout",
+    os.environ.get("RAG_EXTERNAL_RERANKER_TIMEOUT", ""),
+)
+
 
 RAG_TEXT_SPLITTER = PersistentConfig(
     "RAG_TEXT_SPLITTER",
@@ -2655,6 +2893,12 @@ RAG_TEXT_SPLITTER = PersistentConfig(
     os.environ.get("RAG_TEXT_SPLITTER", ""),
 )
 
+ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER = PersistentConfig(
+    "ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER",
+    "rag.enable_markdown_header_text_splitter",
+    os.environ.get("ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER", "True").lower() == "true",
+)
+
 
 TIKTOKEN_CACHE_DIR = os.environ.get("TIKTOKEN_CACHE_DIR", f"{CACHE_DIR}/tiktoken")
 TIKTOKEN_ENCODING_NAME = PersistentConfig(
@@ -2667,6 +2911,13 @@ TIKTOKEN_ENCODING_NAME = PersistentConfig(
 CHUNK_SIZE = PersistentConfig(
     "CHUNK_SIZE", "rag.chunk_size", int(os.environ.get("CHUNK_SIZE", "1000"))
 )
+
+CHUNK_MIN_SIZE_TARGET = PersistentConfig(
+    "CHUNK_MIN_SIZE_TARGET",
+    "rag.chunk_min_size_target",
+    int(os.environ.get("CHUNK_MIN_SIZE_TARGET", "0")),
+)
+
 CHUNK_OVERLAP = PersistentConfig(
     "CHUNK_OVERLAP",
     "rag.chunk_overlap",
@@ -2697,10 +2948,6 @@ Provide a clear and direct response to the user's query, including inline citati
 <context>
 {{CONTEXT}}
 </context>
-
-<user_query>
-{{QUERY}}
-</user_query>
 """
 
 RAG_TEMPLATE = PersistentConfig(
@@ -2753,6 +3000,26 @@ ENABLE_RAG_LOCAL_WEB_FETCH = (
     os.getenv("ENABLE_RAG_LOCAL_WEB_FETCH", "False").lower() == "true"
 )
 
+
+DEFAULT_WEB_FETCH_FILTER_LIST = [
+    "!169.254.169.254",
+    "!fd00:ec2::254",
+    "!metadata.google.internal",
+    "!metadata.azure.com",
+    "!100.100.100.200",
+]
+
+web_fetch_filter_list = os.getenv("WEB_FETCH_FILTER_LIST", "")
+if web_fetch_filter_list == "":
+    web_fetch_filter_list = []
+else:
+    web_fetch_filter_list = [
+        item.strip() for item in web_fetch_filter_list.split(",") if item.strip()
+    ]
+
+WEB_FETCH_FILTER_LIST = list(set(DEFAULT_WEB_FETCH_FILTER_LIST + web_fetch_filter_list))
+
+
 YOUTUBE_LOADER_LANGUAGE = PersistentConfig(
     "YOUTUBE_LOADER_LANGUAGE",
     "rag.youtube_loader_language",
@@ -2811,13 +3078,14 @@ WEB_SEARCH_DOMAIN_FILTER_LIST = PersistentConfig(
         # "wikipedia.com",
         # "wikimedia.org",
         # "wikidata.org",
+        # "!stackoverflow.com",
     ],
 )
 
 WEB_SEARCH_CONCURRENT_REQUESTS = PersistentConfig(
     "WEB_SEARCH_CONCURRENT_REQUESTS",
     "rag.web.search.concurrent_requests",
-    int(os.getenv("WEB_SEARCH_CONCURRENT_REQUESTS", "10")),
+    int(os.getenv("WEB_SEARCH_CONCURRENT_REQUESTS", "0")),
 )
 
 
@@ -2834,6 +3102,12 @@ WEB_LOADER_CONCURRENT_REQUESTS = PersistentConfig(
     int(os.getenv("WEB_LOADER_CONCURRENT_REQUESTS", "10")),
 )
 
+WEB_LOADER_TIMEOUT = PersistentConfig(
+    "WEB_LOADER_TIMEOUT",
+    "rag.web.loader.timeout",
+    os.getenv("WEB_LOADER_TIMEOUT", ""),
+)
+
 
 ENABLE_WEB_LOADER_SSL_VERIFICATION = PersistentConfig(
     "ENABLE_WEB_LOADER_SSL_VERIFICATION",
@@ -2860,6 +3134,12 @@ SEARXNG_QUERY_URL = PersistentConfig(
     os.getenv("SEARXNG_QUERY_URL", ""),
 )
 
+SEARXNG_LANGUAGE = PersistentConfig(
+    "SEARXNG_LANGUAGE",
+    "rag.web.search.searxng_language",
+    os.getenv("SEARXNG_LANGUAGE", "all"),
+)
+
 YACY_QUERY_URL = PersistentConfig(
     "YACY_QUERY_URL",
     "rag.web.search.yacy_query_url",
@@ -2938,12 +3218,24 @@ SERPLY_API_KEY = PersistentConfig(
     os.getenv("SERPLY_API_KEY", ""),
 )
 
+DDGS_BACKEND = PersistentConfig(
+    "DDGS_BACKEND",
+    "rag.web.search.ddgs_backend",
+    os.getenv("DDGS_BACKEND", "auto"),
+)
+
 JINA_API_KEY = PersistentConfig(
     "JINA_API_KEY",
     "rag.web.search.jina_api_key",
     os.getenv("JINA_API_KEY", ""),
 )
 
+JINA_API_BASE_URL = PersistentConfig(
+    "JINA_API_BASE_URL",
+    "rag.web.search.jina_api_base_url",
+    os.getenv("JINA_API_BASE_URL", ""),
+)
+
 SEARCHAPI_API_KEY = PersistentConfig(
     "SEARCHAPI_API_KEY",
     "rag.web.search.searchapi_api_key",
@@ -2982,6 +3274,24 @@ BING_SEARCH_V7_SUBSCRIPTION_KEY = PersistentConfig(
     os.environ.get("BING_SEARCH_V7_SUBSCRIPTION_KEY", ""),
 )
 
+AZURE_AI_SEARCH_API_KEY = PersistentConfig(
+    "AZURE_AI_SEARCH_API_KEY",
+    "rag.web.search.azure_ai_search_api_key",
+    os.environ.get("AZURE_AI_SEARCH_API_KEY", ""),
+)
+
+AZURE_AI_SEARCH_ENDPOINT = PersistentConfig(
+    "AZURE_AI_SEARCH_ENDPOINT",
+    "rag.web.search.azure_ai_search_endpoint",
+    os.environ.get("AZURE_AI_SEARCH_ENDPOINT", ""),
+)
+
+AZURE_AI_SEARCH_INDEX_NAME = PersistentConfig(
+    "AZURE_AI_SEARCH_INDEX_NAME",
+    "rag.web.search.azure_ai_search_index_name",
+    os.environ.get("AZURE_AI_SEARCH_INDEX_NAME", ""),
+)
+
 EXA_API_KEY = PersistentConfig(
     "EXA_API_KEY",
     "rag.web.search.exa_api_key",
@@ -3006,6 +3316,12 @@ PERPLEXITY_SEARCH_CONTEXT_USAGE = PersistentConfig(
     os.getenv("PERPLEXITY_SEARCH_CONTEXT_USAGE", "medium"),
 )
 
+PERPLEXITY_SEARCH_API_URL = PersistentConfig(
+    "PERPLEXITY_SEARCH_API_URL",
+    "rag.web.search.perplexity_search_api_url",
+    os.getenv("PERPLEXITY_SEARCH_API_URL", "https://api.perplexity.ai/search"),
+)
+
 SOUGOU_API_SID = PersistentConfig(
     "SOUGOU_API_SID",
     "rag.web.search.sougou_api_sid",
@@ -3054,6 +3370,12 @@ FIRECRAWL_API_BASE_URL = PersistentConfig(
     os.environ.get("FIRECRAWL_API_BASE_URL", "https://api.firecrawl.dev"),
 )
 
+FIRECRAWL_TIMEOUT = PersistentConfig(
+    "FIRECRAWL_TIMEOUT",
+    "rag.web.loader.firecrawl_timeout",
+    os.environ.get("FIRECRAWL_TIMEOUT", ""),
+)
+
 EXTERNAL_WEB_SEARCH_URL = PersistentConfig(
     "EXTERNAL_WEB_SEARCH_URL",
     "rag.web.search.external_web_search_url",
@@ -3131,10 +3453,9 @@ try:
 except json.JSONDecodeError:
     automatic1111_params = {}
 
-
 AUTOMATIC1111_PARAMS = PersistentConfig(
     "AUTOMATIC1111_PARAMS",
-    "image_generation.automatic1111.api_auth",
+    "image_generation.automatic1111.api_params",
     automatic1111_params,
 )
 
@@ -3267,10 +3588,16 @@ COMFYUI_WORKFLOW = PersistentConfig(
     os.getenv("COMFYUI_WORKFLOW", COMFYUI_DEFAULT_WORKFLOW),
 )
 
+comfyui_workflow_nodes = os.getenv("COMFYUI_WORKFLOW_NODES", "")
+try:
+    comfyui_workflow_nodes = json.loads(comfyui_workflow_nodes)
+except json.JSONDecodeError:
+    comfyui_workflow_nodes = []
+
 COMFYUI_WORKFLOW_NODES = PersistentConfig(
-    "COMFYUI_WORKFLOW",
+    "COMFYUI_WORKFLOW_NODES",
     "image_generation.comfyui.nodes",
-    [],
+    comfyui_workflow_nodes,
 )
 
 IMAGES_OPENAI_API_BASE_URL = PersistentConfig(
@@ -3290,6 +3617,18 @@ IMAGES_OPENAI_API_KEY = PersistentConfig(
     os.getenv("IMAGES_OPENAI_API_KEY", OPENAI_API_KEY),
 )
 
+images_openai_params = os.getenv("IMAGES_OPENAI_PARAMS", "")
+try:
+    images_openai_params = json.loads(images_openai_params)
+except json.JSONDecodeError:
+    images_openai_params = {}
+
+
+IMAGES_OPENAI_API_PARAMS = PersistentConfig(
+    "IMAGES_OPENAI_API_PARAMS", "image_generation.openai.params", images_openai_params
+)
+
+
 IMAGES_GEMINI_API_BASE_URL = PersistentConfig(
     "IMAGES_GEMINI_API_BASE_URL",
     "image_generation.gemini.api_base_url",
@@ -3307,6 +3646,11 @@ IMAGES_GEMINI_ENDPOINT_METHOD = PersistentConfig(
     os.getenv("IMAGES_GEMINI_ENDPOINT_METHOD", ""),
 )
 
+ENABLE_IMAGE_EDIT = PersistentConfig(
+    "ENABLE_IMAGE_EDIT",
+    "images.edit.enable",
+    os.environ.get("ENABLE_IMAGE_EDIT", "").lower() == "true",
+)
 
 IMAGE_EDIT_ENGINE = PersistentConfig(
     "IMAGE_EDIT_ENGINE",
@@ -3370,10 +3714,16 @@ IMAGES_EDIT_COMFYUI_WORKFLOW = PersistentConfig(
     os.getenv("IMAGES_EDIT_COMFYUI_WORKFLOW", ""),
 )
 
+images_edit_comfyui_workflow_nodes = os.getenv("IMAGES_EDIT_COMFYUI_WORKFLOW_NODES", "")
+try:
+    images_edit_comfyui_workflow_nodes = json.loads(images_edit_comfyui_workflow_nodes)
+except json.JSONDecodeError:
+    images_edit_comfyui_workflow_nodes = []
+
 IMAGES_EDIT_COMFYUI_WORKFLOW_NODES = PersistentConfig(
     "IMAGES_EDIT_COMFYUI_WORKFLOW_NODES",
     "images.edit.comfyui.nodes",
-    [],
+    images_edit_comfyui_workflow_nodes,
 )
 
 ####################################
@@ -3387,17 +3737,16 @@ WHISPER_MODEL = PersistentConfig(
     os.getenv("WHISPER_MODEL", "base"),
 )
 
+WHISPER_COMPUTE_TYPE = os.getenv("WHISPER_COMPUTE_TYPE", "int8")
 WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
 WHISPER_MODEL_AUTO_UPDATE = (
     not OFFLINE_MODE
     and os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
 )
 
-WHISPER_VAD_FILTER = PersistentConfig(
-    "WHISPER_VAD_FILTER",
-    "audio.stt.whisper_vad_filter",
-    os.getenv("WHISPER_VAD_FILTER", "False").lower() == "true",
-)
+WHISPER_VAD_FILTER = os.getenv("WHISPER_VAD_FILTER", "False").lower() == "true"
+
+WHISPER_MULTILINGUAL = os.getenv("WHISPER_MULTILINGUAL", "False").lower() == "true"
 
 WHISPER_LANGUAGE = os.getenv("WHISPER_LANGUAGE", "").lower() or None
 

backend/open_webui/constants.py

@@ -45,7 +45,7 @@ class ERROR_MESSAGES(str, Enum):
     )
     INVALID_CRED = "The email or password provided is incorrect. Please check for typos and try logging in again."
     INVALID_EMAIL_FORMAT = "The email format you entered is invalid. Please double-check and make sure you're using a valid email address (e.g., yourname@example.com)."
-    INVALID_PASSWORD = (
+    INCORRECT_PASSWORD = (
         "The password provided is incorrect. Please check for typos and try again."
     )
     INVALID_TRUSTED_HEADER = "Your provider has not provided a trusted header. Please contact your administrator for assistance."
@@ -105,6 +105,10 @@ class ERROR_MESSAGES(str, Enum):
     )
     FILE_NOT_PROCESSED = "Extracted content is not available for this file. Please ensure that the file is processed before proceeding."
 
+    INVALID_PASSWORD = lambda err="": (
+        err if err else "The password does not meet the required validation criteria."
+    )
+
 
 class TASKS(str, Enum):
     def __str__(self) -> str:

backend/open_webui/env.py

@@ -8,6 +8,8 @@ import shutil
 from uuid import uuid4
 from pathlib import Path
 from cryptography.hazmat.primitives import serialization
+import re
+
 
 import markdown
 from bs4 import BeautifulSoup
@@ -83,32 +85,7 @@ if "cuda_error" in locals():
     log.exception(cuda_error)
     del cuda_error
 
-log_sources = [
-    "AUDIO",
-    "COMFYUI",
-    "CONFIG",
-    "DB",
-    "IMAGES",
-    "MAIN",
-    "MODELS",
-    "OLLAMA",
-    "OPENAI",
-    "RAG",
-    "WEBHOOK",
-    "SOCKET",
-    "OAUTH",
-]
-
-SRC_LOG_LEVELS = {}
-
-for source in log_sources:
-    log_env_var = source + "_LOG_LEVEL"
-    SRC_LOG_LEVELS[source] = os.environ.get(log_env_var, "").upper()
-    if SRC_LOG_LEVELS[source] not in logging.getLevelNamesMapping():
-        SRC_LOG_LEVELS[source] = GLOBAL_LOG_LEVEL
-    log.info(f"{log_env_var}: {SRC_LOG_LEVELS[source]}")
-
-log.setLevel(SRC_LOG_LEVELS["CONFIG"])
+SRC_LOG_LEVELS = {}  # Legacy variable, do not remove
 
 WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
 if WEBUI_NAME != "Open WebUI":
@@ -135,8 +112,13 @@ else:
         PACKAGE_DATA = {"version": "0.0.0"}
 
 VERSION = PACKAGE_DATA["version"]
+
+
+DEPLOYMENT_ID = os.environ.get("DEPLOYMENT_ID", "")
 INSTANCE_ID = os.environ.get("INSTANCE_ID", str(uuid4()))
 
+ENABLE_DB_MIGRATIONS = os.environ.get("ENABLE_DB_MIGRATIONS", "True").lower() == "true"
+
 
 # Function to parse each section
 def parse_section(section):
@@ -359,6 +341,11 @@ if DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL is not None:
     except Exception:
         DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL = 0.0
 
+# Enable public visibility of active user count (when disabled, only admins can see it)
+ENABLE_PUBLIC_ACTIVE_USERS_COUNT = (
+    os.environ.get("ENABLE_PUBLIC_ACTIVE_USERS_COUNT", "True").lower() == "true"
+)
+
 RESET_CONFIG_ON_START = (
     os.environ.get("RESET_CONFIG_ON_START", "False").lower() == "true"
 )
@@ -369,6 +356,8 @@ ENABLE_REALTIME_CHAT_SAVE = (
 
 ENABLE_QUERIES_CACHE = os.environ.get("ENABLE_QUERIES_CACHE", "False").lower() == "true"
 
+RAG_SYSTEM_CONTEXT = os.environ.get("RAG_SYSTEM_CONTEXT", "False").lower() == "true"
+
 ####################################
 # REDIS
 ####################################
@@ -390,6 +379,13 @@ try:
 except ValueError:
     REDIS_SENTINEL_MAX_RETRY_COUNT = 2
 
+
+REDIS_SOCKET_CONNECT_TIMEOUT = os.environ.get("REDIS_SOCKET_CONNECT_TIMEOUT", "")
+try:
+    REDIS_SOCKET_CONNECT_TIMEOUT = float(REDIS_SOCKET_CONNECT_TIMEOUT)
+except ValueError:
+    REDIS_SOCKET_CONNECT_TIMEOUT = None
+
 ####################################
 # UVICORN WORKERS
 ####################################
@@ -417,6 +413,16 @@ ENABLE_SIGNUP_PASSWORD_CONFIRMATION = (
     os.environ.get("ENABLE_SIGNUP_PASSWORD_CONFIRMATION", "False").lower() == "true"
 )
 
+####################################
+# Admin Account Runtime Creation
+####################################
+
+# Optional env vars for creating an admin account on startup
+# Useful for headless/automated deployments
+WEBUI_ADMIN_EMAIL = os.environ.get("WEBUI_ADMIN_EMAIL", "")
+WEBUI_ADMIN_PASSWORD = os.environ.get("WEBUI_ADMIN_PASSWORD", "")
+WEBUI_ADMIN_NAME = os.environ.get("WEBUI_ADMIN_NAME", "Admin")
+
 WEBUI_AUTH_TRUSTED_EMAIL_HEADER = os.environ.get(
     "WEBUI_AUTH_TRUSTED_EMAIL_HEADER", None
 )
@@ -426,6 +432,25 @@ WEBUI_AUTH_TRUSTED_GROUPS_HEADER = os.environ.get(
 )
 
 
+ENABLE_PASSWORD_VALIDATION = (
+    os.environ.get("ENABLE_PASSWORD_VALIDATION", "False").lower() == "true"
+)
+PASSWORD_VALIDATION_REGEX_PATTERN = os.environ.get(
+    "PASSWORD_VALIDATION_REGEX_PATTERN",
+    "^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[^\w\s]).{8,}$",
+)
+
+
+try:
+    PASSWORD_VALIDATION_REGEX_PATTERN = rf"{PASSWORD_VALIDATION_REGEX_PATTERN}"
+    PASSWORD_VALIDATION_REGEX_PATTERN = re.compile(PASSWORD_VALIDATION_REGEX_PATTERN)
+except Exception as e:
+    log.error(f"Invalid PASSWORD_VALIDATION_REGEX_PATTERN: {e}")
+    PASSWORD_VALIDATION_REGEX_PATTERN = re.compile(
+        r"^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[^\w\s]).{8,}$"
+    )
+
+
 BYPASS_MODEL_ACCESS_CONTROL = (
     os.environ.get("BYPASS_MODEL_ACCESS_CONTROL", "False").lower() == "true"
 )
@@ -493,7 +518,10 @@ OAUTH_SESSION_TOKEN_ENCRYPTION_KEY = os.environ.get(
 # SCIM Configuration
 ####################################
 
-SCIM_ENABLED = os.environ.get("SCIM_ENABLED", "False").lower() == "true"
+ENABLE_SCIM = (
+    os.environ.get("ENABLE_SCIM", os.environ.get("SCIM_ENABLED", "False")).lower()
+    == "true"
+)
 SCIM_TOKEN = os.environ.get("SCIM_TOKEN", "")
 
 ####################################
@@ -527,6 +555,10 @@ if LICENSE_PUBLIC_KEY:
 # MODELS
 ####################################
 
+ENABLE_CUSTOM_MODEL_FALLBACK = (
+    os.environ.get("ENABLE_CUSTOM_MODEL_FALLBACK", "False").lower() == "true"
+)
+
 MODELS_CACHE_TTL = os.environ.get("MODELS_CACHE_TTL", "1")
 if MODELS_CACHE_TTL == "":
     MODELS_CACHE_TTL = None
@@ -541,6 +573,11 @@ else:
 # CHAT
 ####################################
 
+ENABLE_CHAT_RESPONSE_BASE64_IMAGE_URL_CONVERSION = (
+    os.environ.get("ENABLE_CHAT_RESPONSE_BASE64_IMAGE_URL_CONVERSION", "False").lower()
+    == "true"
+)
+
 CHAT_RESPONSE_STREAM_DELTA_CHUNK_SIZE = os.environ.get(
     "CHAT_RESPONSE_STREAM_DELTA_CHUNK_SIZE", "1"
 )
@@ -569,6 +606,21 @@ else:
         CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = 30
 
 
+CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = os.environ.get(
+    "CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE", ""
+)
+
+if CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE == "":
+    CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = None
+else:
+    try:
+        CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = int(
+            CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE
+        )
+    except Exception:
+        CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = None
+
+
 ####################################
 # WEBSOCKET SUPPORT
 ####################################
@@ -580,6 +632,24 @@ ENABLE_WEBSOCKET_SUPPORT = (
 
 WEBSOCKET_MANAGER = os.environ.get("WEBSOCKET_MANAGER", "")
 
+WEBSOCKET_REDIS_OPTIONS = os.environ.get("WEBSOCKET_REDIS_OPTIONS", "")
+
+
+if WEBSOCKET_REDIS_OPTIONS == "":
+    if REDIS_SOCKET_CONNECT_TIMEOUT:
+        WEBSOCKET_REDIS_OPTIONS = {
+            "socket_connect_timeout": REDIS_SOCKET_CONNECT_TIMEOUT
+        }
+    else:
+        log.debug("No WEBSOCKET_REDIS_OPTIONS provided, defaulting to None")
+        WEBSOCKET_REDIS_OPTIONS = None
+else:
+    try:
+        WEBSOCKET_REDIS_OPTIONS = json.loads(WEBSOCKET_REDIS_OPTIONS)
+    except Exception:
+        log.warning("Invalid WEBSOCKET_REDIS_OPTIONS, defaulting to None")
+        WEBSOCKET_REDIS_OPTIONS = None
+
 WEBSOCKET_REDIS_URL = os.environ.get("WEBSOCKET_REDIS_URL", REDIS_URL)
 WEBSOCKET_REDIS_CLUSTER = (
     os.environ.get("WEBSOCKET_REDIS_CLUSTER", str(REDIS_CLUSTER)).lower() == "true"
@@ -594,7 +664,26 @@ except ValueError:
 
 WEBSOCKET_SENTINEL_HOSTS = os.environ.get("WEBSOCKET_SENTINEL_HOSTS", "")
 WEBSOCKET_SENTINEL_PORT = os.environ.get("WEBSOCKET_SENTINEL_PORT", "26379")
+WEBSOCKET_SERVER_LOGGING = (
+    os.environ.get("WEBSOCKET_SERVER_LOGGING", "False").lower() == "true"
+)
+WEBSOCKET_SERVER_ENGINEIO_LOGGING = (
+    os.environ.get("WEBSOCKET_SERVER_LOGGING", "False").lower() == "true"
+)
+WEBSOCKET_SERVER_PING_TIMEOUT = os.environ.get("WEBSOCKET_SERVER_PING_TIMEOUT", "20")
+try:
+    WEBSOCKET_SERVER_PING_TIMEOUT = int(WEBSOCKET_SERVER_PING_TIMEOUT)
+except ValueError:
+    WEBSOCKET_SERVER_PING_TIMEOUT = 20
 
+WEBSOCKET_SERVER_PING_INTERVAL = os.environ.get("WEBSOCKET_SERVER_PING_INTERVAL", "25")
+try:
+    WEBSOCKET_SERVER_PING_INTERVAL = int(WEBSOCKET_SERVER_PING_INTERVAL)
+except ValueError:
+    WEBSOCKET_SERVER_PING_INTERVAL = 25
+
+
+REQUESTS_VERIFY = os.environ.get("REQUESTS_VERIFY", "True").lower() == "true"
 
 AIOHTTP_CLIENT_TIMEOUT = os.environ.get("AIOHTTP_CLIENT_TIMEOUT", "")
 
@@ -689,6 +778,16 @@ else:
     except Exception:
         SENTENCE_TRANSFORMERS_CROSS_ENCODER_MODEL_KWARGS = None
 
+# Whether to apply sigmoid normalization to CrossEncoder reranking scores.
+# When enabled (default), scores are normalized to 0-1 range for proper
+# relevance threshold behavior with MS MARCO models.
+SENTENCE_TRANSFORMERS_CROSS_ENCODER_SIGMOID_ACTIVATION_FUNCTION = (
+    os.environ.get(
+        "SENTENCE_TRANSFORMERS_CROSS_ENCODER_SIGMOID_ACTIVATION_FUNCTION", "True"
+    ).lower()
+    == "true"
+)
+
 ####################################
 # OFFLINE_MODE
 ####################################
@@ -705,8 +804,15 @@ if OFFLINE_MODE:
 ####################################
 # AUDIT LOGGING
 ####################################
+
+
+ENABLE_AUDIT_STDOUT = os.getenv("ENABLE_AUDIT_STDOUT", "False").lower() == "true"
+ENABLE_AUDIT_LOGS_FILE = os.getenv("ENABLE_AUDIT_LOGS_FILE", "True").lower() == "true"
+
 # Where to store log file
-AUDIT_LOGS_FILE_PATH = f"{DATA_DIR}/audit.log"
+# Defaults to the DATA_DIR/audit.log. To set AUDIT_LOGS_FILE_PATH you need to
+# provide the whole path, like: /app/audit.log
+AUDIT_LOGS_FILE_PATH = os.getenv("AUDIT_LOGS_FILE_PATH", f"{DATA_DIR}/audit.log")
 # Maximum size of a file before rotating into a new log file
 AUDIT_LOG_FILE_ROTATION_SIZE = os.getenv("AUDIT_LOG_FILE_ROTATION_SIZE", "10MB")
 

backend/open_webui/functions.py

@@ -37,7 +37,7 @@ from open_webui.utils.plugin import (
 from open_webui.utils.tools import get_tools
 from open_webui.utils.access_control import has_access
 
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.env import GLOBAL_LOG_LEVEL
 
 from open_webui.utils.misc import (
     add_or_update_system_message,
@@ -54,7 +54,6 @@ from open_webui.utils.payload import (
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 def get_function_module_by_id(request: Request, pipe_id: str):

backend/open_webui/internal/db.py

@@ -9,23 +9,22 @@ from open_webui.env import (
     OPEN_WEBUI_DIR,
     DATABASE_URL,
     DATABASE_SCHEMA,
-    SRC_LOG_LEVELS,
     DATABASE_POOL_MAX_OVERFLOW,
     DATABASE_POOL_RECYCLE,
     DATABASE_POOL_SIZE,
     DATABASE_POOL_TIMEOUT,
     DATABASE_ENABLE_SQLITE_WAL,
+    ENABLE_DB_MIGRATIONS,
 )
 from peewee_migrate import Router
 from sqlalchemy import Dialect, create_engine, MetaData, event, types
 from sqlalchemy.ext.declarative import declarative_base
-from sqlalchemy.orm import scoped_session, sessionmaker
+from sqlalchemy.orm import scoped_session, sessionmaker, Session
 from sqlalchemy.pool import QueuePool, NullPool
 from sqlalchemy.sql.type_api import _T
 from typing_extensions import Self
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["DB"])
 
 
 class JSONField(types.TypeDecorator):
@@ -77,7 +76,8 @@ def handle_peewee_migration(DATABASE_URL):
         assert db.is_closed(), "Database connection is still open."
 
 
-handle_peewee_migration(DATABASE_URL)
+if ENABLE_DB_MIGRATIONS:
+    handle_peewee_migration(DATABASE_URL)
 
 
 SQLALCHEMY_DATABASE_URL = DATABASE_URL
@@ -92,8 +92,6 @@ if SQLALCHEMY_DATABASE_URL.startswith("sqlite+sqlcipher://"):
 
     # Extract database path from SQLCipher URL
     db_path = SQLALCHEMY_DATABASE_URL.replace("sqlite+sqlcipher://", "")
-    if db_path.startswith("/"):
-        db_path = db_path[1:]  # Remove leading slash for relative paths
 
     # Create a custom creator function that uses sqlcipher3
     def create_sqlcipher_connection():
@@ -150,7 +148,7 @@ SessionLocal = sessionmaker(
 )
 metadata_obj = MetaData(schema=DATABASE_SCHEMA)
 Base = declarative_base(metadata=metadata_obj)
-Session = scoped_session(SessionLocal)
+ScopedSession = scoped_session(SessionLocal)
 
 
 def get_session():
@@ -162,3 +160,12 @@ def get_session():
 
 
 get_db = contextmanager(get_session)
+
+
+@contextmanager
+def get_db_context(db: Optional[Session] = None):
+    if isinstance(db, Session):
+        yield db
+    else:
+        with get_db() as session:
+            yield session

backend/open_webui/internal/wrappers.py

@@ -2,7 +2,6 @@ import logging
 import os
 from contextvars import ContextVar
 
-from open_webui.env import SRC_LOG_LEVELS
 from peewee import *
 from peewee import InterfaceError as PeeWeeInterfaceError
 from peewee import PostgresqlDatabase
@@ -10,7 +9,6 @@ from playhouse.db_url import connect, parse
 from playhouse.shortcuts import ReconnectMixin
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["DB"])
 
 db_state_default = {"closed": None, "conn": None, "ctx": None, "transactions": None}
 db_state = ContextVar("db_state", default=db_state_default.copy())
@@ -56,8 +54,6 @@ def register_connection(db_url):
         # Parse the database path from SQLCipher URL
         # Convert sqlite+sqlcipher:///path/to/db.sqlite to /path/to/db.sqlite
         db_path = db_url.replace("sqlite+sqlcipher://", "")
-        if db_path.startswith("/"):
-            db_path = db_path[1:]  # Remove leading slash for relative paths
 
         # Use Peewee's native SqlCipherDatabase with encryption
         db = SqlCipherDatabase(db_path, passphrase=database_password)

backend/open_webui/main.py

@@ -61,11 +61,11 @@ from open_webui.utils import logger
 from open_webui.utils.audit import AuditLevel, AuditLoggingMiddleware
 from open_webui.utils.logger import start_logger
 from open_webui.socket.main import (
+    MODELS,
     app as socket_app,
     periodic_usage_pool_cleanup,
     get_event_emitter,
     get_models_in_use,
-    get_active_user_ids,
 )
 from open_webui.routers import (
     audio,
@@ -102,7 +102,9 @@ from open_webui.routers.retrieval import (
     get_rf,
 )
 
-from open_webui.internal.db import Session, engine
+
+from sqlalchemy.orm import Session
+from open_webui.internal.db import ScopedSession, engine, get_session
 
 from open_webui.models.functions import Functions
 from open_webui.models.models import Models
@@ -143,6 +145,7 @@ from open_webui.config import (
     CODE_INTERPRETER_JUPYTER_AUTH_TOKEN,
     CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD,
     CODE_INTERPRETER_JUPYTER_TIMEOUT,
+    ENABLE_MEMORIES,
     # Image
     AUTOMATIC1111_API_AUTH,
     AUTOMATIC1111_BASE_URL,
@@ -160,9 +163,11 @@ from open_webui.config import (
     IMAGES_OPENAI_API_BASE_URL,
     IMAGES_OPENAI_API_VERSION,
     IMAGES_OPENAI_API_KEY,
+    IMAGES_OPENAI_API_PARAMS,
     IMAGES_GEMINI_API_BASE_URL,
     IMAGES_GEMINI_API_KEY,
     IMAGES_GEMINI_ENDPOINT_METHOD,
+    ENABLE_IMAGE_EDIT,
     IMAGE_EDIT_ENGINE,
     IMAGE_EDIT_MODEL,
     IMAGE_EDIT_SIZE,
@@ -204,8 +209,10 @@ from open_webui.config import (
     PLAYWRIGHT_TIMEOUT,
     FIRECRAWL_API_BASE_URL,
     FIRECRAWL_API_KEY,
+    FIRECRAWL_TIMEOUT,
     WEB_LOADER_ENGINE,
     WEB_LOADER_CONCURRENT_REQUESTS,
+    WEB_LOADER_TIMEOUT,
     WHISPER_MODEL,
     WHISPER_VAD_FILTER,
     WHISPER_LANGUAGE,
@@ -224,10 +231,12 @@ from open_webui.config import (
     RAG_RERANKING_MODEL,
     RAG_EXTERNAL_RERANKER_URL,
     RAG_EXTERNAL_RERANKER_API_KEY,
+    RAG_EXTERNAL_RERANKER_TIMEOUT,
     RAG_RERANKING_MODEL_AUTO_UPDATE,
     RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
     RAG_EMBEDDING_ENGINE,
     RAG_EMBEDDING_BATCH_SIZE,
+    ENABLE_ASYNC_EMBEDDING,
     RAG_TOP_K,
     RAG_TOP_K_RERANKER,
     RAG_RELEVANCE_THRESHOLD,
@@ -245,6 +254,7 @@ from open_webui.config import (
     RAG_OLLAMA_BASE_URL,
     RAG_OLLAMA_API_KEY,
     CHUNK_OVERLAP,
+    CHUNK_MIN_SIZE_TARGET,
     CHUNK_SIZE,
     CONTENT_EXTRACTION_ENGINE,
     DATALAB_MARKER_API_KEY,
@@ -260,29 +270,22 @@ from open_webui.config import (
     MINERU_API_MODE,
     MINERU_API_URL,
     MINERU_API_KEY,
+    MINERU_API_TIMEOUT,
     MINERU_PARAMS,
     DATALAB_MARKER_USE_LLM,
     EXTERNAL_DOCUMENT_LOADER_URL,
     EXTERNAL_DOCUMENT_LOADER_API_KEY,
     TIKA_SERVER_URL,
     DOCLING_SERVER_URL,
+    DOCLING_API_KEY,
     DOCLING_PARAMS,
-    DOCLING_DO_OCR,
-    DOCLING_FORCE_OCR,
-    DOCLING_OCR_ENGINE,
-    DOCLING_OCR_LANG,
-    DOCLING_PDF_BACKEND,
-    DOCLING_TABLE_MODE,
-    DOCLING_PIPELINE,
-    DOCLING_DO_PICTURE_DESCRIPTION,
-    DOCLING_PICTURE_DESCRIPTION_MODE,
-    DOCLING_PICTURE_DESCRIPTION_LOCAL,
-    DOCLING_PICTURE_DESCRIPTION_API,
     DOCUMENT_INTELLIGENCE_ENDPOINT,
     DOCUMENT_INTELLIGENCE_KEY,
+    DOCUMENT_INTELLIGENCE_MODEL,
     MISTRAL_OCR_API_BASE_URL,
     MISTRAL_OCR_API_KEY,
     RAG_TEXT_SPLITTER,
+    ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER,
     TIKTOKEN_ENCODING_NAME,
     PDF_EXTRACT_IMAGES,
     YOUTUBE_LOADER_LANGUAGE,
@@ -298,16 +301,19 @@ from open_webui.config import (
     WEB_SEARCH_DOMAIN_FILTER_LIST,
     OLLAMA_CLOUD_WEB_SEARCH_API_KEY,
     JINA_API_KEY,
+    JINA_API_BASE_URL,
     SEARCHAPI_API_KEY,
     SEARCHAPI_ENGINE,
     SERPAPI_API_KEY,
     SERPAPI_ENGINE,
     SEARXNG_QUERY_URL,
+    SEARXNG_LANGUAGE,
     YACY_QUERY_URL,
     YACY_USERNAME,
     YACY_PASSWORD,
     SERPER_API_KEY,
     SERPLY_API_KEY,
+    DDGS_BACKEND,
     SERPSTACK_API_KEY,
     SERPSTACK_HTTPS,
     TAVILY_API_KEY,
@@ -319,6 +325,7 @@ from open_webui.config import (
     PERPLEXITY_API_KEY,
     PERPLEXITY_MODEL,
     PERPLEXITY_SEARCH_CONTEXT_USAGE,
+    PERPLEXITY_SEARCH_API_URL,
     SOUGOU_API_SID,
     SOUGOU_API_SK,
     KAGI_SEARCH_API_KEY,
@@ -336,6 +343,7 @@ from open_webui.config import (
     ENABLE_ONEDRIVE_PERSONAL,
     ENABLE_ONEDRIVE_BUSINESS,
     ENABLE_RAG_HYBRID_SEARCH,
+    ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS,
     ENABLE_RAG_LOCAL_WEB_FETCH,
     ENABLE_WEB_LOADER_SSL_VERIFICATION,
     ENABLE_GOOGLE_DRIVE_INTEGRATION,
@@ -354,11 +362,14 @@ from open_webui.config import (
     JWT_EXPIRES_IN,
     ENABLE_SIGNUP,
     ENABLE_LOGIN_FORM,
-    ENABLE_API_KEY,
-    ENABLE_API_KEY_ENDPOINT_RESTRICTIONS,
-    API_KEY_ALLOWED_ENDPOINTS,
+    ENABLE_API_KEYS,
+    ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS,
+    API_KEYS_ALLOWED_ENDPOINTS,
+    ENABLE_FOLDERS,
+    FOLDER_MAX_FILE_COUNT,
     ENABLE_CHANNELS,
     ENABLE_NOTES,
+    ENABLE_USER_STATUS,
     ENABLE_COMMUNITY_SHARING,
     ENABLE_MESSAGE_RATING,
     ENABLE_USER_WEBHOOKS,
@@ -366,10 +377,12 @@ from open_webui.config import (
     BYPASS_ADMIN_ACCESS_CONTROL,
     USER_PERMISSIONS,
     DEFAULT_USER_ROLE,
+    DEFAULT_GROUP_ID,
     PENDING_USER_OVERLAY_CONTENT,
     PENDING_USER_OVERLAY_TITLE,
     DEFAULT_PROMPT_SUGGESTIONS,
     DEFAULT_MODELS,
+    DEFAULT_PINNED_MODELS,
     DEFAULT_ARENA_MODEL,
     MODEL_ORDER_LIST,
     EVALUATION_ARENA_MODELS,
@@ -428,6 +441,7 @@ from open_webui.config import (
     TAGS_GENERATION_PROMPT_TEMPLATE,
     IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE,
     TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE,
+    VOICE_MODE_PROMPT_TEMPLATE,
     QUERY_GENERATION_PROMPT_TEMPLATE,
     AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE,
     AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH,
@@ -435,6 +449,7 @@ from open_webui.config import (
     reset_config,
 )
 from open_webui.env import (
+    ENABLE_CUSTOM_MODEL_FALLBACK,
     LICENSE_KEY,
     AUDIT_EXCLUDED_PATHS,
     AUDIT_LOG_LEVEL,
@@ -447,8 +462,8 @@ from open_webui.env import (
     GLOBAL_LOG_LEVEL,
     MAX_BODY_LOG_SIZE,
     SAFE_MODE,
-    SRC_LOG_LEVELS,
     VERSION,
+    DEPLOYMENT_ID,
     INSTANCE_ID,
     WEBUI_BUILD_HASH,
     WEBUI_SECRET_KEY,
@@ -459,7 +474,7 @@ from open_webui.env import (
     WEBUI_AUTH_TRUSTED_NAME_HEADER,
     WEBUI_AUTH_SIGNOUT_REDIRECT_URL,
     # SCIM
-    SCIM_ENABLED,
+    ENABLE_SCIM,
     SCIM_TOKEN,
     ENABLE_COMPRESSION_MIDDLEWARE,
     ENABLE_WEBSOCKET_SUPPORT,
@@ -470,6 +485,11 @@ from open_webui.env import (
     EXTERNAL_PWA_MANIFEST_URL,
     AIOHTTP_CLIENT_SESSION_SSL,
     ENABLE_STAR_SESSIONS_MIDDLEWARE,
+    ENABLE_PUBLIC_ACTIVE_USERS_COUNT,
+    # Admin Account Runtime Creation
+    WEBUI_ADMIN_EMAIL,
+    WEBUI_ADMIN_PASSWORD,
+    WEBUI_ADMIN_NAME,
 )
 
 
@@ -494,6 +514,7 @@ from open_webui.utils.auth import (
     decode_token,
     get_admin_user,
     get_verified_user,
+    create_admin_user,
 )
 from open_webui.utils.plugin import install_tool_and_function_dependencies
 from open_webui.utils.oauth import (
@@ -527,7 +548,6 @@ if SAFE_MODE:
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 class SPAStaticFiles(StaticFiles):
@@ -573,6 +593,12 @@ async def lifespan(app: FastAPI):
     if LICENSE_KEY:
         get_license_data(app, LICENSE_KEY)
 
+    # Create admin account from env vars if specified and no users exist
+    if WEBUI_ADMIN_EMAIL and WEBUI_ADMIN_PASSWORD:
+        if create_admin_user(WEBUI_ADMIN_EMAIL, WEBUI_ADMIN_PASSWORD, WEBUI_ADMIN_NAME):
+            # Disable signup since we now have an admin
+            app.state.config.ENABLE_SIGNUP = False
+
     # This should be blocking (sync) so functions are not deactivated on first /get_models calls
     # when the first user lands on the / route.
     log.info("Installing external dependencies of functions and tools...")
@@ -715,7 +741,7 @@ app.state.config.ENABLE_DIRECT_CONNECTIONS = ENABLE_DIRECT_CONNECTIONS
 #
 ########################################
 
-app.state.SCIM_ENABLED = SCIM_ENABLED
+app.state.ENABLE_SCIM = ENABLE_SCIM
 app.state.SCIM_TOKEN = SCIM_TOKEN
 
 ########################################
@@ -737,11 +763,11 @@ app.state.config.WEBUI_URL = WEBUI_URL
 app.state.config.ENABLE_SIGNUP = ENABLE_SIGNUP
 app.state.config.ENABLE_LOGIN_FORM = ENABLE_LOGIN_FORM
 
-app.state.config.ENABLE_API_KEY = ENABLE_API_KEY
-app.state.config.ENABLE_API_KEY_ENDPOINT_RESTRICTIONS = (
-    ENABLE_API_KEY_ENDPOINT_RESTRICTIONS
+app.state.config.ENABLE_API_KEYS = ENABLE_API_KEYS
+app.state.config.ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS = (
+    ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS
 )
-app.state.config.API_KEY_ALLOWED_ENDPOINTS = API_KEY_ALLOWED_ENDPOINTS
+app.state.config.API_KEYS_ALLOWED_ENDPOINTS = API_KEYS_ALLOWED_ENDPOINTS
 
 app.state.config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
 
@@ -750,8 +776,13 @@ app.state.config.ADMIN_EMAIL = ADMIN_EMAIL
 
 
 app.state.config.DEFAULT_MODELS = DEFAULT_MODELS
+app.state.config.DEFAULT_PINNED_MODELS = DEFAULT_PINNED_MODELS
+app.state.config.MODEL_ORDER_LIST = MODEL_ORDER_LIST
+
+
 app.state.config.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
 app.state.config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
+app.state.config.DEFAULT_GROUP_ID = DEFAULT_GROUP_ID
 
 app.state.config.PENDING_USER_OVERLAY_CONTENT = PENDING_USER_OVERLAY_CONTENT
 app.state.config.PENDING_USER_OVERLAY_TITLE = PENDING_USER_OVERLAY_TITLE
@@ -761,14 +792,16 @@ app.state.config.RESPONSE_WATERMARK = RESPONSE_WATERMARK
 app.state.config.USER_PERMISSIONS = USER_PERMISSIONS
 app.state.config.WEBHOOK_URL = WEBHOOK_URL
 app.state.config.BANNERS = WEBUI_BANNERS
-app.state.config.MODEL_ORDER_LIST = MODEL_ORDER_LIST
 
 
+app.state.config.ENABLE_FOLDERS = ENABLE_FOLDERS
+app.state.config.FOLDER_MAX_FILE_COUNT = FOLDER_MAX_FILE_COUNT
 app.state.config.ENABLE_CHANNELS = ENABLE_CHANNELS
 app.state.config.ENABLE_NOTES = ENABLE_NOTES
 app.state.config.ENABLE_COMMUNITY_SHARING = ENABLE_COMMUNITY_SHARING
 app.state.config.ENABLE_MESSAGE_RATING = ENABLE_MESSAGE_RATING
 app.state.config.ENABLE_USER_WEBHOOKS = ENABLE_USER_WEBHOOKS
+app.state.config.ENABLE_USER_STATUS = ENABLE_USER_STATUS
 
 app.state.config.ENABLE_EVALUATION_ARENA_MODELS = ENABLE_EVALUATION_ARENA_MODELS
 app.state.config.EVALUATION_ARENA_MODELS = EVALUATION_ARENA_MODELS
@@ -839,6 +872,9 @@ app.state.config.FILE_IMAGE_COMPRESSION_HEIGHT = FILE_IMAGE_COMPRESSION_HEIGHT
 app.state.config.RAG_FULL_CONTEXT = RAG_FULL_CONTEXT
 app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL = BYPASS_EMBEDDING_AND_RETRIEVAL
 app.state.config.ENABLE_RAG_HYBRID_SEARCH = ENABLE_RAG_HYBRID_SEARCH
+app.state.config.ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS = (
+    ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS
+)
 app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION = ENABLE_WEB_LOADER_SSL_VERIFICATION
 
 app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
@@ -859,41 +895,41 @@ app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = EXTERNAL_DOCUMENT_LOADER_URL
 app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY = EXTERNAL_DOCUMENT_LOADER_API_KEY
 app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
 app.state.config.DOCLING_SERVER_URL = DOCLING_SERVER_URL
+app.state.config.DOCLING_API_KEY = DOCLING_API_KEY
 app.state.config.DOCLING_PARAMS = DOCLING_PARAMS
-app.state.config.DOCLING_DO_OCR = DOCLING_DO_OCR
-app.state.config.DOCLING_FORCE_OCR = DOCLING_FORCE_OCR
-app.state.config.DOCLING_OCR_ENGINE = DOCLING_OCR_ENGINE
-app.state.config.DOCLING_OCR_LANG = DOCLING_OCR_LANG
-app.state.config.DOCLING_PDF_BACKEND = DOCLING_PDF_BACKEND
-app.state.config.DOCLING_TABLE_MODE = DOCLING_TABLE_MODE
-app.state.config.DOCLING_PIPELINE = DOCLING_PIPELINE
-app.state.config.DOCLING_DO_PICTURE_DESCRIPTION = DOCLING_DO_PICTURE_DESCRIPTION
-app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE = DOCLING_PICTURE_DESCRIPTION_MODE
-app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL = DOCLING_PICTURE_DESCRIPTION_LOCAL
-app.state.config.DOCLING_PICTURE_DESCRIPTION_API = DOCLING_PICTURE_DESCRIPTION_API
 app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT
 app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
+app.state.config.DOCUMENT_INTELLIGENCE_MODEL = DOCUMENT_INTELLIGENCE_MODEL
 app.state.config.MISTRAL_OCR_API_BASE_URL = MISTRAL_OCR_API_BASE_URL
 app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY
 app.state.config.MINERU_API_MODE = MINERU_API_MODE
 app.state.config.MINERU_API_URL = MINERU_API_URL
 app.state.config.MINERU_API_KEY = MINERU_API_KEY
+app.state.config.MINERU_API_TIMEOUT = MINERU_API_TIMEOUT
 app.state.config.MINERU_PARAMS = MINERU_PARAMS
 
 app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
+app.state.config.ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER = (
+    ENABLE_MARKDOWN_HEADER_TEXT_SPLITTER
+)
+
 app.state.config.TIKTOKEN_ENCODING_NAME = TIKTOKEN_ENCODING_NAME
 
 app.state.config.CHUNK_SIZE = CHUNK_SIZE
+app.state.config.CHUNK_MIN_SIZE_TARGET = CHUNK_MIN_SIZE_TARGET
 app.state.config.CHUNK_OVERLAP = CHUNK_OVERLAP
 
+
 app.state.config.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
 app.state.config.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
 app.state.config.RAG_EMBEDDING_BATCH_SIZE = RAG_EMBEDDING_BATCH_SIZE
+app.state.config.ENABLE_ASYNC_EMBEDDING = ENABLE_ASYNC_EMBEDDING
 
 app.state.config.RAG_RERANKING_ENGINE = RAG_RERANKING_ENGINE
 app.state.config.RAG_RERANKING_MODEL = RAG_RERANKING_MODEL
 app.state.config.RAG_EXTERNAL_RERANKER_URL = RAG_EXTERNAL_RERANKER_URL
 app.state.config.RAG_EXTERNAL_RERANKER_API_KEY = RAG_EXTERNAL_RERANKER_API_KEY
+app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT = RAG_EXTERNAL_RERANKER_TIMEOUT
 
 app.state.config.RAG_TEMPLATE = RAG_TEMPLATE
 
@@ -921,6 +957,7 @@ app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS = WEB_SEARCH_CONCURRENT_REQUESTS
 
 app.state.config.WEB_LOADER_ENGINE = WEB_LOADER_ENGINE
 app.state.config.WEB_LOADER_CONCURRENT_REQUESTS = WEB_LOADER_CONCURRENT_REQUESTS
+app.state.config.WEB_LOADER_TIMEOUT = WEB_LOADER_TIMEOUT
 
 app.state.config.WEB_SEARCH_TRUST_ENV = WEB_SEARCH_TRUST_ENV
 app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
@@ -933,6 +970,7 @@ app.state.config.ENABLE_ONEDRIVE_INTEGRATION = ENABLE_ONEDRIVE_INTEGRATION
 
 app.state.config.OLLAMA_CLOUD_WEB_SEARCH_API_KEY = OLLAMA_CLOUD_WEB_SEARCH_API_KEY
 app.state.config.SEARXNG_QUERY_URL = SEARXNG_QUERY_URL
+app.state.config.SEARXNG_LANGUAGE = SEARXNG_LANGUAGE
 app.state.config.YACY_QUERY_URL = YACY_QUERY_URL
 app.state.config.YACY_USERNAME = YACY_USERNAME
 app.state.config.YACY_PASSWORD = YACY_PASSWORD
@@ -946,18 +984,21 @@ app.state.config.SERPSTACK_API_KEY = SERPSTACK_API_KEY
 app.state.config.SERPSTACK_HTTPS = SERPSTACK_HTTPS
 app.state.config.SERPER_API_KEY = SERPER_API_KEY
 app.state.config.SERPLY_API_KEY = SERPLY_API_KEY
+app.state.config.DDGS_BACKEND = DDGS_BACKEND
 app.state.config.TAVILY_API_KEY = TAVILY_API_KEY
 app.state.config.SEARCHAPI_API_KEY = SEARCHAPI_API_KEY
 app.state.config.SEARCHAPI_ENGINE = SEARCHAPI_ENGINE
 app.state.config.SERPAPI_API_KEY = SERPAPI_API_KEY
 app.state.config.SERPAPI_ENGINE = SERPAPI_ENGINE
 app.state.config.JINA_API_KEY = JINA_API_KEY
+app.state.config.JINA_API_BASE_URL = JINA_API_BASE_URL
 app.state.config.BING_SEARCH_V7_ENDPOINT = BING_SEARCH_V7_ENDPOINT
 app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY = BING_SEARCH_V7_SUBSCRIPTION_KEY
 app.state.config.EXA_API_KEY = EXA_API_KEY
 app.state.config.PERPLEXITY_API_KEY = PERPLEXITY_API_KEY
 app.state.config.PERPLEXITY_MODEL = PERPLEXITY_MODEL
 app.state.config.PERPLEXITY_SEARCH_CONTEXT_USAGE = PERPLEXITY_SEARCH_CONTEXT_USAGE
+app.state.config.PERPLEXITY_SEARCH_API_URL = PERPLEXITY_SEARCH_API_URL
 app.state.config.SOUGOU_API_SID = SOUGOU_API_SID
 app.state.config.SOUGOU_API_SK = SOUGOU_API_SK
 app.state.config.EXTERNAL_WEB_SEARCH_URL = EXTERNAL_WEB_SEARCH_URL
@@ -970,6 +1011,7 @@ app.state.config.PLAYWRIGHT_WS_URL = PLAYWRIGHT_WS_URL
 app.state.config.PLAYWRIGHT_TIMEOUT = PLAYWRIGHT_TIMEOUT
 app.state.config.FIRECRAWL_API_BASE_URL = FIRECRAWL_API_BASE_URL
 app.state.config.FIRECRAWL_API_KEY = FIRECRAWL_API_KEY
+app.state.config.FIRECRAWL_TIMEOUT = FIRECRAWL_TIMEOUT
 app.state.config.TAVILY_EXTRACT_DEPTH = TAVILY_EXTRACT_DEPTH
 
 app.state.EMBEDDING_FUNCTION = None
@@ -982,9 +1024,7 @@ app.state.YOUTUBE_LOADER_TRANSLATION = None
 
 try:
     app.state.ef = get_ef(
-        app.state.config.RAG_EMBEDDING_ENGINE,
-        app.state.config.RAG_EMBEDDING_MODEL,
-        RAG_EMBEDDING_MODEL_AUTO_UPDATE,
+        app.state.config.RAG_EMBEDDING_ENGINE, app.state.config.RAG_EMBEDDING_MODEL
     )
     if (
         app.state.config.ENABLE_RAG_HYBRID_SEARCH
@@ -995,7 +1035,7 @@ try:
             app.state.config.RAG_RERANKING_MODEL,
             app.state.config.RAG_EXTERNAL_RERANKER_URL,
             app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
-            RAG_RERANKING_MODEL_AUTO_UPDATE,
+            app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT,
         )
     else:
         app.state.rf = None
@@ -1032,6 +1072,7 @@ app.state.EMBEDDING_FUNCTION = get_embedding_function(
         if app.state.config.RAG_EMBEDDING_ENGINE == "azure_openai"
         else None
     ),
+    enable_async=app.state.config.ENABLE_ASYNC_EMBEDDING,
 )
 
 app.state.RERANKING_FUNCTION = get_reranking_function(
@@ -1079,6 +1120,7 @@ app.state.config.CODE_INTERPRETER_JUPYTER_TIMEOUT = CODE_INTERPRETER_JUPYTER_TIM
 app.state.config.IMAGE_GENERATION_ENGINE = IMAGE_GENERATION_ENGINE
 app.state.config.ENABLE_IMAGE_GENERATION = ENABLE_IMAGE_GENERATION
 app.state.config.ENABLE_IMAGE_PROMPT_GENERATION = ENABLE_IMAGE_PROMPT_GENERATION
+app.state.config.ENABLE_MEMORIES = ENABLE_MEMORIES
 
 app.state.config.IMAGE_GENERATION_MODEL = IMAGE_GENERATION_MODEL
 app.state.config.IMAGE_SIZE = IMAGE_SIZE
@@ -1087,6 +1129,7 @@ app.state.config.IMAGE_STEPS = IMAGE_STEPS
 app.state.config.IMAGES_OPENAI_API_BASE_URL = IMAGES_OPENAI_API_BASE_URL
 app.state.config.IMAGES_OPENAI_API_VERSION = IMAGES_OPENAI_API_VERSION
 app.state.config.IMAGES_OPENAI_API_KEY = IMAGES_OPENAI_API_KEY
+app.state.config.IMAGES_OPENAI_API_PARAMS = IMAGES_OPENAI_API_PARAMS
 
 app.state.config.IMAGES_GEMINI_API_BASE_URL = IMAGES_GEMINI_API_BASE_URL
 app.state.config.IMAGES_GEMINI_API_KEY = IMAGES_GEMINI_API_KEY
@@ -1102,6 +1145,7 @@ app.state.config.COMFYUI_WORKFLOW = COMFYUI_WORKFLOW
 app.state.config.COMFYUI_WORKFLOW_NODES = COMFYUI_WORKFLOW_NODES
 
 
+app.state.config.ENABLE_IMAGE_EDIT = ENABLE_IMAGE_EDIT
 app.state.config.IMAGE_EDIT_ENGINE = IMAGE_EDIT_ENGINE
 app.state.config.IMAGE_EDIT_MODEL = IMAGE_EDIT_MODEL
 app.state.config.IMAGE_EDIT_SIZE = IMAGE_EDIT_SIZE
@@ -1130,7 +1174,6 @@ app.state.config.STT_OPENAI_API_BASE_URL = AUDIO_STT_OPENAI_API_BASE_URL
 app.state.config.STT_OPENAI_API_KEY = AUDIO_STT_OPENAI_API_KEY
 
 app.state.config.WHISPER_MODEL = WHISPER_MODEL
-app.state.config.WHISPER_VAD_FILTER = WHISPER_VAD_FILTER
 app.state.config.DEEPGRAM_API_KEY = DEEPGRAM_API_KEY
 
 app.state.config.AUDIO_STT_AZURE_API_KEY = AUDIO_STT_AZURE_API_KEY
@@ -1206,6 +1249,7 @@ app.state.config.AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE = (
 app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH = (
     AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH
 )
+app.state.config.VOICE_MODE_PROMPT_TEMPLATE = VOICE_MODE_PROMPT_TEMPLATE
 
 
 ########################################
@@ -1214,7 +1258,11 @@ app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH = (
 #
 ########################################
 
-app.state.MODELS = {}
+app.state.MODELS = MODELS
+
+# Add the middleware to the app
+if ENABLE_COMPRESSION_MIDDLEWARE:
+    app.add_middleware(CompressMiddleware)
 
 
 class RedirectMiddleware(BaseHTTPMiddleware):
@@ -1257,19 +1305,58 @@ class RedirectMiddleware(BaseHTTPMiddleware):
         return response
 
 
-# Add the middleware to the app
-if ENABLE_COMPRESSION_MIDDLEWARE:
-    app.add_middleware(CompressMiddleware)
-
 app.add_middleware(RedirectMiddleware)
 app.add_middleware(SecurityHeadersMiddleware)
 
 
+class APIKeyRestrictionMiddleware(BaseHTTPMiddleware):
+    async def dispatch(self, request: Request, call_next):
+        auth_header = request.headers.get("Authorization")
+        token = None
+
+        if auth_header:
+            scheme, token = auth_header.split(" ")
+
+        # Only apply restrictions if an sk- API key is used
+        if token and token.startswith("sk-"):
+            # Check if restrictions are enabled
+            if request.app.state.config.ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS:
+                allowed_paths = [
+                    path.strip()
+                    for path in str(
+                        request.app.state.config.API_KEYS_ALLOWED_ENDPOINTS
+                    ).split(",")
+                    if path.strip()
+                ]
+
+                request_path = request.url.path
+
+                # Match exact path or prefix path
+                is_allowed = any(
+                    request_path == allowed or request_path.startswith(allowed + "/")
+                    for allowed in allowed_paths
+                )
+
+                if not is_allowed:
+                    return JSONResponse(
+                        status_code=status.HTTP_403_FORBIDDEN,
+                        content={
+                            "detail": "API key not allowed to access this endpoint."
+                        },
+                    )
+
+        response = await call_next(request)
+        return response
+
+
+app.add_middleware(APIKeyRestrictionMiddleware)
+
+
 @app.middleware("http")
 async def commit_session_after_request(request: Request, call_next):
     response = await call_next(request)
     # log.debug("Commit session after request")
-    Session.commit()
+    ScopedSession.commit()
     return response
 
 
@@ -1280,7 +1367,7 @@ async def check_url(request: Request, call_next):
         request.headers.get("Authorization")
     )
 
-    request.state.enable_api_key = app.state.config.ENABLE_API_KEY
+    request.state.enable_api_keys = app.state.config.ENABLE_API_KEYS
     response = await call_next(request)
     process_time = int(time.time()) - start_time
     response.headers["X-Process-Time"] = str(process_time)
@@ -1355,7 +1442,7 @@ app.include_router(
 app.include_router(utils.router, prefix="/api/v1/utils", tags=["utils"])
 
 # SCIM 2.0 API for identity management
-if SCIM_ENABLED:
+if ENABLE_SCIM:
     app.include_router(scim.router, prefix="/api/v1/scim/v2", tags=["scim"])
 
 
@@ -1392,6 +1479,10 @@ async def get_models(
         if "pipeline" in model and model["pipeline"].get("type", None) == "filter":
             continue
 
+        # Remove profile image URL to reduce payload size
+        if model.get("info", {}).get("meta", {}).get("profile_image_url"):
+            model["info"]["meta"].pop("profile_image_url", None)
+
         try:
             model_tags = [
                 tag.get("name")
@@ -1481,6 +1572,7 @@ async def chat_completion(
 
     metadata = {}
     try:
+        model_info = None
         if not model_item.get("direct", False):
             if model_id not in request.app.state.MODELS:
                 raise Exception("Model not found")
@@ -1498,7 +1590,6 @@ async def chat_completion(
                     raise e
         else:
             model = model_item
-            model_info = None
 
             request.state.direct = True
             request.state.model = model
@@ -1507,6 +1598,26 @@ async def chat_completion(
             model_info.params.model_dump() if model_info and model_info.params else {}
         )
 
+        # Check base model existence for custom models
+        if model_info_params.get("base_model_id"):
+            base_model_id = model_info_params.get("base_model_id")
+            if base_model_id not in request.app.state.MODELS:
+                if ENABLE_CUSTOM_MODEL_FALLBACK:
+                    default_models = (
+                        request.app.state.config.DEFAULT_MODELS or ""
+                    ).split(",")
+
+                    fallback_model_id = (
+                        default_models[0].strip() if default_models[0] else None
+                    )
+
+                    if fallback_model_id:
+                        request.base_model_id = fallback_model_id
+                    else:
+                        raise Exception("Model not found")
+                else:
+                    raise Exception("Model not found")
+
         # Chat Params
         stream_delta_chunk_size = form_data.get("params", {}).get(
             "stream_delta_chunk_size"
@@ -1514,6 +1625,9 @@ async def chat_completion(
         reasoning_tags = form_data.get("params", {}).get("reasoning_tags")
 
         # Model Params
+        if model_info_params.get("stream_response") is not None:
+            form_data["stream"] = model_info_params.get("stream_response")
+
         if model_info_params.get("stream_delta_chunk_size"):
             stream_delta_chunk_size = model_info_params.get("stream_delta_chunk_size")
 
@@ -1524,6 +1638,8 @@ async def chat_completion(
             "user_id": user.id,
             "chat_id": form_data.pop("chat_id", None),
             "message_id": form_data.pop("id", None),
+            "parent_message": form_data.pop("parent_message", None),
+            "parent_message_id": form_data.pop("parent_id", None),
             "session_id": form_data.pop("session_id", None),
             "filter_ids": form_data.pop("filter_ids", []),
             "tool_ids": form_data.get("tool_ids", None),
@@ -1547,15 +1663,38 @@ async def chat_completion(
             },
         }
 
-        if metadata.get("chat_id") and (user and user.role != "admin"):
-            if not metadata["chat_id"].startswith("local:"):
+        if metadata.get("chat_id") and user:
+            if not metadata["chat_id"].startswith(
+                "local:"
+            ):  # temporary chats are not stored
+
+                # Verify chat ownership
                 chat = Chats.get_chat_by_id_and_user_id(metadata["chat_id"], user.id)
-                if chat is None:
+                if chat is None and user.role != "admin":  # admins can access any chat
                     raise HTTPException(
                         status_code=status.HTTP_404_NOT_FOUND,
                         detail=ERROR_MESSAGES.DEFAULT(),
                     )
 
+                # Insert chat files from parent message if any
+                parent_message = metadata.get("parent_message") or {}
+                parent_message_files = parent_message.get("files", [])
+                if parent_message_files:
+                    try:
+                        Chats.insert_chat_files(
+                            metadata["chat_id"],
+                            parent_message.get("id"),
+                            [
+                                file_item.get("id")
+                                for file_item in parent_message_files
+                                if file_item.get("type") == "file"
+                            ],
+                            user.id,
+                        )
+                    except Exception as e:
+                        log.debug(f"Error inserting chat files: {e}")
+                        pass
+
         request.state.metadata = metadata
         form_data["metadata"] = metadata
 
@@ -1580,6 +1719,7 @@ async def chat_completion(
                             metadata["chat_id"],
                             metadata["message_id"],
                             {
+                                "parentId": metadata.get("parent_message_id", None),
                                 "model": model_id,
                             },
                         )
@@ -1612,6 +1752,7 @@ async def chat_completion(
                             metadata["chat_id"],
                             metadata["message_id"],
                             {
+                                "parentId": metadata.get("parent_message_id", None),
                                 "error": {"content": str(e)},
                             },
                         )
@@ -1783,14 +1924,17 @@ async def get_app_config(request: Request):
             "auth_trusted_header": bool(app.state.AUTH_TRUSTED_EMAIL_HEADER),
             "enable_signup_password_confirmation": ENABLE_SIGNUP_PASSWORD_CONFIRMATION,
             "enable_ldap": app.state.config.ENABLE_LDAP,
-            "enable_api_key": app.state.config.ENABLE_API_KEY,
+            "enable_api_keys": app.state.config.ENABLE_API_KEYS,
             "enable_signup": app.state.config.ENABLE_SIGNUP,
             "enable_login_form": app.state.config.ENABLE_LOGIN_FORM,
             "enable_websocket": ENABLE_WEBSOCKET_SUPPORT,
             "enable_version_update_check": ENABLE_VERSION_UPDATE_CHECK,
+            "enable_public_active_users_count": ENABLE_PUBLIC_ACTIVE_USERS_COUNT,
             **(
                 {
                     "enable_direct_connections": app.state.config.ENABLE_DIRECT_CONNECTIONS,
+                    "enable_folders": app.state.config.ENABLE_FOLDERS,
+                    "folder_max_file_count": app.state.config.FOLDER_MAX_FILE_COUNT,
                     "enable_channels": app.state.config.ENABLE_CHANNELS,
                     "enable_notes": app.state.config.ENABLE_NOTES,
                     "enable_web_search": app.state.config.ENABLE_WEB_SEARCH,
@@ -1801,10 +1945,12 @@ async def get_app_config(request: Request):
                     "enable_community_sharing": app.state.config.ENABLE_COMMUNITY_SHARING,
                     "enable_message_rating": app.state.config.ENABLE_MESSAGE_RATING,
                     "enable_user_webhooks": app.state.config.ENABLE_USER_WEBHOOKS,
+                    "enable_user_status": app.state.config.ENABLE_USER_STATUS,
                     "enable_admin_export": ENABLE_ADMIN_EXPORT,
                     "enable_admin_chat_access": ENABLE_ADMIN_CHAT_ACCESS,
                     "enable_google_drive_integration": app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
                     "enable_onedrive_integration": app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
+                    "enable_memories": app.state.config.ENABLE_MEMORIES,
                     **(
                         {
                             "enable_onedrive_personal": ENABLE_ONEDRIVE_PERSONAL,
@@ -1821,6 +1967,7 @@ async def get_app_config(request: Request):
         **(
             {
                 "default_models": app.state.config.DEFAULT_MODELS,
+                "default_pinned_models": app.state.config.DEFAULT_PINNED_MODELS,
                 "default_prompt_suggestions": app.state.config.DEFAULT_PROMPT_SUGGESTIONS,
                 "user_count": user_count,
                 "code": {
@@ -1922,6 +2069,7 @@ async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
 async def get_app_version():
     return {
         "version": VERSION,
+        "deployment_id": DEPLOYMENT_ID,
     }
 
 
@@ -1961,7 +2109,19 @@ async def get_current_usage(user=Depends(get_verified_user)):
     This is an experimental endpoint and subject to change.
     """
     try:
-        return {"model_ids": get_models_in_use(), "user_ids": get_active_user_ids()}
+        # If public visibility is disabled, only allow admins to access this endpoint
+        if not ENABLE_PUBLIC_ACTIVE_USERS_COUNT and user.role != "admin":
+            raise HTTPException(
+                status_code=status.HTTP_403_FORBIDDEN,
+                detail="Access denied. Only administrators can view usage statistics.",
+            )
+
+        return {
+            "model_ids": get_models_in_use(),
+            "user_count": Users.get_active_user_count(),
+        }
+    except HTTPException:
+        raise
     except Exception as e:
         log.error(f"Error getting usage statistics: {e}")
         raise HTTPException(status_code=500, detail="Internal Server Error")
@@ -2024,7 +2184,7 @@ except Exception as e:
     )
 
 
-async def register_client(self, request, client_id: str) -> bool:
+async def register_client(request, client_id: str) -> bool:
     server_type, server_id = client_id.split(":", 1)
 
     connection = None
@@ -2155,8 +2315,13 @@ async def oauth_login(provider: str, request: Request):
 #    - Email addresses are considered unique, so we fail registration if the email address is already taken
 @app.get("/oauth/{provider}/login/callback")
 @app.get("/oauth/{provider}/callback")  # Legacy endpoint
-async def oauth_login_callback(provider: str, request: Request, response: Response):
-    return await oauth_manager.handle_callback(request, provider, response)
+async def oauth_login_callback(
+    provider: str,
+    request: Request,
+    response: Response,
+    db: Session = Depends(get_session),
+):
+    return await oauth_manager.handle_callback(request, provider, response, db=db)
 
 
 @app.get("/manifest.json")
@@ -2215,7 +2380,7 @@ async def healthcheck():
 
 @app.get("/health/db")
 async def healthcheck_with_db():
-    Session.execute(text("SELECT 1;")).all()
+    ScopedSession.execute(text("SELECT 1;")).all()
     return {"status": True}
 
 

backend/open_webui/migrations/versions/2f1211949ecc_update_message_and_channel_member_table.py

@@ -0,0 +1,103 @@
+"""Update messages and channel member table
+
+Revision ID: 2f1211949ecc
+Revises: 37f288994c47
+Create Date: 2025-11-27 03:07:56.200231
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import open_webui.internal.db
+
+
+# revision identifiers, used by Alembic.
+revision: str = "2f1211949ecc"
+down_revision: Union[str, None] = "37f288994c47"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # New columns to be added to channel_member table
+    op.add_column("channel_member", sa.Column("status", sa.Text(), nullable=True))
+    op.add_column(
+        "channel_member",
+        sa.Column(
+            "is_active",
+            sa.Boolean(),
+            nullable=False,
+            default=True,
+            server_default=sa.sql.expression.true(),
+        ),
+    )
+
+    op.add_column(
+        "channel_member",
+        sa.Column(
+            "is_channel_muted",
+            sa.Boolean(),
+            nullable=False,
+            default=False,
+            server_default=sa.sql.expression.false(),
+        ),
+    )
+    op.add_column(
+        "channel_member",
+        sa.Column(
+            "is_channel_pinned",
+            sa.Boolean(),
+            nullable=False,
+            default=False,
+            server_default=sa.sql.expression.false(),
+        ),
+    )
+
+    op.add_column("channel_member", sa.Column("data", sa.JSON(), nullable=True))
+    op.add_column("channel_member", sa.Column("meta", sa.JSON(), nullable=True))
+
+    op.add_column(
+        "channel_member", sa.Column("joined_at", sa.BigInteger(), nullable=False)
+    )
+    op.add_column(
+        "channel_member", sa.Column("left_at", sa.BigInteger(), nullable=True)
+    )
+
+    op.add_column(
+        "channel_member", sa.Column("last_read_at", sa.BigInteger(), nullable=True)
+    )
+
+    op.add_column(
+        "channel_member", sa.Column("updated_at", sa.BigInteger(), nullable=True)
+    )
+
+    # New columns to be added to message table
+    op.add_column(
+        "message",
+        sa.Column(
+            "is_pinned",
+            sa.Boolean(),
+            nullable=False,
+            default=False,
+            server_default=sa.sql.expression.false(),
+        ),
+    )
+    op.add_column("message", sa.Column("pinned_at", sa.BigInteger(), nullable=True))
+    op.add_column("message", sa.Column("pinned_by", sa.Text(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("channel_member", "updated_at")
+    op.drop_column("channel_member", "last_read_at")
+
+    op.drop_column("channel_member", "meta")
+    op.drop_column("channel_member", "data")
+
+    op.drop_column("channel_member", "is_channel_pinned")
+    op.drop_column("channel_member", "is_channel_muted")
+
+    op.drop_column("message", "pinned_by")
+    op.drop_column("message", "pinned_at")
+    op.drop_column("message", "is_pinned")

backend/open_webui/migrations/versions/37f288994c47_add_group_member_table.py

@@ -0,0 +1,146 @@
+"""add_group_member_table
+
+Revision ID: 37f288994c47
+Revises: a5c220713937
+Create Date: 2025-11-17 03:45:25.123939
+
+"""
+
+import uuid
+import time
+import json
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "37f288994c47"
+down_revision: Union[str, None] = "a5c220713937"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # 1. Create new table
+    op.create_table(
+        "group_member",
+        sa.Column("id", sa.Text(), primary_key=True, unique=True, nullable=False),
+        sa.Column(
+            "group_id",
+            sa.Text(),
+            sa.ForeignKey("group.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column(
+            "user_id",
+            sa.Text(),
+            sa.ForeignKey("user.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("created_at", sa.BigInteger(), nullable=True),
+        sa.Column("updated_at", sa.BigInteger(), nullable=True),
+        sa.UniqueConstraint("group_id", "user_id", name="uq_group_member_group_user"),
+    )
+
+    connection = op.get_bind()
+
+    # 2. Read existing group with user_ids JSON column
+    group_table = sa.Table(
+        "group",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+        sa.Column("user_ids", sa.JSON()),  # JSON stored as text in SQLite + PG
+    )
+
+    results = connection.execute(
+        sa.select(group_table.c.id, group_table.c.user_ids)
+    ).fetchall()
+
+    print(results)
+
+    # 3. Insert members into group_member table
+    gm_table = sa.Table(
+        "group_member",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+        sa.Column("group_id", sa.Text()),
+        sa.Column("user_id", sa.Text()),
+        sa.Column("created_at", sa.BigInteger()),
+        sa.Column("updated_at", sa.BigInteger()),
+    )
+
+    now = int(time.time())
+    for group_id, user_ids in results:
+        if not user_ids:
+            continue
+
+        if isinstance(user_ids, str):
+            try:
+                user_ids = json.loads(user_ids)
+            except Exception:
+                continue  # skip invalid JSON
+
+        if not isinstance(user_ids, list):
+            continue
+
+        rows = [
+            {
+                "id": str(uuid.uuid4()),
+                "group_id": group_id,
+                "user_id": uid,
+                "created_at": now,
+                "updated_at": now,
+            }
+            for uid in user_ids
+        ]
+
+        if rows:
+            connection.execute(gm_table.insert(), rows)
+
+    # 4. Optionally drop the old column
+    with op.batch_alter_table("group") as batch:
+        batch.drop_column("user_ids")
+
+
+def downgrade():
+    # Reverse: restore user_ids column
+    with op.batch_alter_table("group") as batch:
+        batch.add_column(sa.Column("user_ids", sa.JSON()))
+
+    connection = op.get_bind()
+    gm_table = sa.Table(
+        "group_member",
+        sa.MetaData(),
+        sa.Column("group_id", sa.Text()),
+        sa.Column("user_id", sa.Text()),
+        sa.Column("created_at", sa.BigInteger()),
+        sa.Column("updated_at", sa.BigInteger()),
+    )
+
+    group_table = sa.Table(
+        "group",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+        sa.Column("user_ids", sa.JSON()),
+    )
+
+    # Build JSON arrays again
+    results = connection.execute(sa.select(group_table.c.id)).fetchall()
+
+    for (group_id,) in results:
+        members = connection.execute(
+            sa.select(gm_table.c.user_id).where(gm_table.c.group_id == group_id)
+        ).fetchall()
+
+        member_ids = [m[0] for m in members]
+
+        connection.execute(
+            group_table.update()
+            .where(group_table.c.id == group_id)
+            .values(user_ids=member_ids)
+        )
+
+    # Drop the new table
+    op.drop_table("group_member")

backend/open_webui/migrations/versions/38d63c18f30f_add_oauth_session_table.py

@@ -20,18 +20,46 @@ depends_on: Union[str, Sequence[str], None] = None
 
 
 def upgrade() -> None:
+    # Ensure 'id' column in 'user' table is unique and primary key (ForeignKey constraint)
+    inspector = sa.inspect(op.get_bind())
+    columns = inspector.get_columns("user")
+
+    pk_columns = inspector.get_pk_constraint("user")["constrained_columns"]
+    id_column = next((col for col in columns if col["name"] == "id"), None)
+
+    if id_column and not id_column.get("unique", False):
+        unique_constraints = inspector.get_unique_constraints("user")
+        unique_columns = {tuple(u["column_names"]) for u in unique_constraints}
+
+        with op.batch_alter_table("user") as batch_op:
+            # If primary key is wrong, drop it
+            if pk_columns and pk_columns != ["id"]:
+                batch_op.drop_constraint(
+                    inspector.get_pk_constraint("user")["name"], type_="primary"
+                )
+
+            # Add unique constraint if missing
+            if ("id",) not in unique_columns:
+                batch_op.create_unique_constraint("uq_user_id", ["id"])
+
+            # Re-create correct primary key
+            batch_op.create_primary_key("pk_user_id", ["id"])
+
     # Create oauth_session table
     op.create_table(
         "oauth_session",
-        sa.Column("id", sa.Text(), nullable=False),
-        sa.Column("user_id", sa.Text(), nullable=False),
+        sa.Column("id", sa.Text(), primary_key=True, nullable=False, unique=True),
+        sa.Column(
+            "user_id",
+            sa.Text(),
+            sa.ForeignKey("user.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
         sa.Column("provider", sa.Text(), nullable=False),
         sa.Column("token", sa.Text(), nullable=False),
         sa.Column("expires_at", sa.BigInteger(), nullable=False),
         sa.Column("created_at", sa.BigInteger(), nullable=False),
         sa.Column("updated_at", sa.BigInteger(), nullable=False),
-        sa.PrimaryKeyConstraint("id"),
-        sa.ForeignKeyConstraint(["user_id"], ["user.id"], ondelete="CASCADE"),
     )
 
     # Create indexes for better performance

backend/open_webui/migrations/versions/3e0e00844bb0_add_knowledge_file_table.py

@@ -0,0 +1,169 @@
+"""Add knowledge_file table
+
+Revision ID: 3e0e00844bb0
+Revises: 90ef40d4714e
+Create Date: 2025-12-02 06:54:19.401334
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy import inspect
+import open_webui.internal.db
+
+import time
+import json
+import uuid
+
+# revision identifiers, used by Alembic.
+revision: str = "3e0e00844bb0"
+down_revision: Union[str, None] = "90ef40d4714e"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "knowledge_file",
+        sa.Column("id", sa.Text(), primary_key=True),
+        sa.Column("user_id", sa.Text(), nullable=False),
+        sa.Column(
+            "knowledge_id",
+            sa.Text(),
+            sa.ForeignKey("knowledge.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column(
+            "file_id",
+            sa.Text(),
+            sa.ForeignKey("file.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("created_at", sa.BigInteger(), nullable=False),
+        sa.Column("updated_at", sa.BigInteger(), nullable=False),
+        # indexes
+        sa.Index("ix_knowledge_file_knowledge_id", "knowledge_id"),
+        sa.Index("ix_knowledge_file_file_id", "file_id"),
+        sa.Index("ix_knowledge_file_user_id", "user_id"),
+        # unique constraints
+        sa.UniqueConstraint(
+            "knowledge_id", "file_id", name="uq_knowledge_file_knowledge_file"
+        ),  # prevent duplicate entries
+    )
+
+    connection = op.get_bind()
+
+    # 2. Read existing group with user_ids JSON column
+    knowledge_table = sa.Table(
+        "knowledge",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+        sa.Column("user_id", sa.Text()),
+        sa.Column("data", sa.JSON()),  # JSON stored as text in SQLite + PG
+    )
+
+    results = connection.execute(
+        sa.select(
+            knowledge_table.c.id, knowledge_table.c.user_id, knowledge_table.c.data
+        )
+    ).fetchall()
+
+    # 3. Insert members into group_member table
+    kf_table = sa.Table(
+        "knowledge_file",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+        sa.Column("user_id", sa.Text()),
+        sa.Column("knowledge_id", sa.Text()),
+        sa.Column("file_id", sa.Text()),
+        sa.Column("created_at", sa.BigInteger()),
+        sa.Column("updated_at", sa.BigInteger()),
+    )
+
+    file_table = sa.Table(
+        "file",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+    )
+
+    now = int(time.time())
+    for knowledge_id, user_id, data in results:
+        if not data:
+            continue
+
+        if isinstance(data, str):
+            try:
+                data = json.loads(data)
+            except Exception:
+                continue  # skip invalid JSON
+
+        if not isinstance(data, dict):
+            continue
+
+        file_ids = data.get("file_ids", [])
+
+        for file_id in file_ids:
+            file_exists = connection.execute(
+                sa.select(file_table.c.id).where(file_table.c.id == file_id)
+            ).fetchone()
+
+            if not file_exists:
+                continue  # skip non-existing files
+
+            row = {
+                "id": str(uuid.uuid4()),
+                "user_id": user_id,
+                "knowledge_id": knowledge_id,
+                "file_id": file_id,
+                "created_at": now,
+                "updated_at": now,
+            }
+            connection.execute(kf_table.insert().values(**row))
+
+    with op.batch_alter_table("knowledge") as batch:
+        batch.drop_column("data")
+
+
+def downgrade() -> None:
+    # 1. Add back the old data column
+    op.add_column("knowledge", sa.Column("data", sa.JSON(), nullable=True))
+
+    connection = op.get_bind()
+
+    # 2. Read knowledge_file entries and reconstruct data JSON
+    knowledge_table = sa.Table(
+        "knowledge",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+        sa.Column("data", sa.JSON()),
+    )
+
+    kf_table = sa.Table(
+        "knowledge_file",
+        sa.MetaData(),
+        sa.Column("id", sa.Text()),
+        sa.Column("knowledge_id", sa.Text()),
+        sa.Column("file_id", sa.Text()),
+    )
+
+    results = connection.execute(sa.select(knowledge_table.c.id)).fetchall()
+
+    for (knowledge_id,) in results:
+        file_ids = connection.execute(
+            sa.select(kf_table.c.file_id).where(kf_table.c.knowledge_id == knowledge_id)
+        ).fetchall()
+
+        file_ids_list = [fid for (fid,) in file_ids]
+
+        data_json = {"file_ids": file_ids_list}
+
+        connection.execute(
+            knowledge_table.update()
+            .where(knowledge_table.c.id == knowledge_id)
+            .values(data=data_json)
+        )
+
+    # 3. Drop the knowledge_file table
+    op.drop_table("knowledge_file")

backend/open_webui/migrations/versions/6283dc0e4d8d_add_channel_file_table.py

@@ -0,0 +1,54 @@
+"""Add channel file table
+
+Revision ID: 6283dc0e4d8d
+Revises: 3e0e00844bb0
+Create Date: 2025-12-10 15:11:39.424601
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import open_webui.internal.db
+
+
+# revision identifiers, used by Alembic.
+revision: str = "6283dc0e4d8d"
+down_revision: Union[str, None] = "3e0e00844bb0"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "channel_file",
+        sa.Column("id", sa.Text(), primary_key=True),
+        sa.Column("user_id", sa.Text(), nullable=False),
+        sa.Column(
+            "channel_id",
+            sa.Text(),
+            sa.ForeignKey("channel.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column(
+            "file_id",
+            sa.Text(),
+            sa.ForeignKey("file.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("created_at", sa.BigInteger(), nullable=False),
+        sa.Column("updated_at", sa.BigInteger(), nullable=False),
+        # indexes
+        sa.Index("ix_channel_file_channel_id", "channel_id"),
+        sa.Index("ix_channel_file_file_id", "file_id"),
+        sa.Index("ix_channel_file_user_id", "user_id"),
+        # unique constraints
+        sa.UniqueConstraint(
+            "channel_id", "file_id", name="uq_channel_file_channel_file"
+        ),  # prevent duplicate entries
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("channel_file")

backend/open_webui/migrations/versions/81cc2ce44d79_update_channel_file_and_knowledge_table.py

@@ -0,0 +1,49 @@
+"""Update channel file and knowledge table
+
+Revision ID: 81cc2ce44d79
+Revises: 6283dc0e4d8d
+Create Date: 2025-12-10 16:07:58.001282
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import open_webui.internal.db
+
+
+# revision identifiers, used by Alembic.
+revision: str = "81cc2ce44d79"
+down_revision: Union[str, None] = "6283dc0e4d8d"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Add message_id column to channel_file table
+    with op.batch_alter_table("channel_file", schema=None) as batch_op:
+        batch_op.add_column(
+            sa.Column(
+                "message_id",
+                sa.Text(),
+                sa.ForeignKey(
+                    "message.id", ondelete="CASCADE", name="fk_channel_file_message_id"
+                ),
+                nullable=True,
+            )
+        )
+
+    # Add data column to knowledge table
+    with op.batch_alter_table("knowledge", schema=None) as batch_op:
+        batch_op.add_column(sa.Column("data", sa.JSON(), nullable=True))
+
+
+def downgrade() -> None:
+    # Remove message_id column from channel_file table
+    with op.batch_alter_table("channel_file", schema=None) as batch_op:
+        batch_op.drop_column("message_id")
+
+    # Remove data column from knowledge table
+    with op.batch_alter_table("knowledge", schema=None) as batch_op:
+        batch_op.drop_column("data")

backend/open_webui/migrations/versions/90ef40d4714e_update_channel_and_channel_members_table.py

@@ -0,0 +1,81 @@
+"""Update channel and channel members table
+
+Revision ID: 90ef40d4714e
+Revises: b10670c03dd5
+Create Date: 2025-11-30 06:33:38.790341
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import open_webui.internal.db
+
+
+# revision identifiers, used by Alembic.
+revision: str = "90ef40d4714e"
+down_revision: Union[str, None] = "b10670c03dd5"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Update 'channel' table
+    op.add_column("channel", sa.Column("is_private", sa.Boolean(), nullable=True))
+
+    op.add_column("channel", sa.Column("archived_at", sa.BigInteger(), nullable=True))
+    op.add_column("channel", sa.Column("archived_by", sa.Text(), nullable=True))
+
+    op.add_column("channel", sa.Column("deleted_at", sa.BigInteger(), nullable=True))
+    op.add_column("channel", sa.Column("deleted_by", sa.Text(), nullable=True))
+
+    op.add_column("channel", sa.Column("updated_by", sa.Text(), nullable=True))
+
+    # Update 'channel_member' table
+    op.add_column("channel_member", sa.Column("role", sa.Text(), nullable=True))
+    op.add_column("channel_member", sa.Column("invited_by", sa.Text(), nullable=True))
+    op.add_column(
+        "channel_member", sa.Column("invited_at", sa.BigInteger(), nullable=True)
+    )
+
+    #  Create 'channel_webhook' table
+    op.create_table(
+        "channel_webhook",
+        sa.Column("id", sa.Text(), primary_key=True, unique=True, nullable=False),
+        sa.Column("user_id", sa.Text(), nullable=False),
+        sa.Column(
+            "channel_id",
+            sa.Text(),
+            sa.ForeignKey("channel.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("name", sa.Text(), nullable=False),
+        sa.Column("profile_image_url", sa.Text(), nullable=True),
+        sa.Column("token", sa.Text(), nullable=False),
+        sa.Column("last_used_at", sa.BigInteger(), nullable=True),
+        sa.Column("created_at", sa.BigInteger(), nullable=False),
+        sa.Column("updated_at", sa.BigInteger(), nullable=False),
+    )
+
+    pass
+
+
+def downgrade() -> None:
+    # Downgrade 'channel' table
+    op.drop_column("channel", "is_private")
+    op.drop_column("channel", "archived_at")
+    op.drop_column("channel", "archived_by")
+    op.drop_column("channel", "deleted_at")
+    op.drop_column("channel", "deleted_by")
+    op.drop_column("channel", "updated_by")
+
+    # Downgrade 'channel_member' table
+    op.drop_column("channel_member", "role")
+    op.drop_column("channel_member", "invited_by")
+    op.drop_column("channel_member", "invited_at")
+
+    # Drop 'channel_webhook' table
+    op.drop_table("channel_webhook")
+
+    pass

backend/open_webui/migrations/versions/b10670c03dd5_update_user_table.py

@@ -0,0 +1,251 @@
+"""Update user table
+
+Revision ID: b10670c03dd5
+Revises: 2f1211949ecc
+Create Date: 2025-11-28 04:55:31.737538
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+import open_webui.internal.db
+import json
+import time
+
+# revision identifiers, used by Alembic.
+revision: str = "b10670c03dd5"
+down_revision: Union[str, None] = "2f1211949ecc"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def _drop_sqlite_indexes_for_column(table_name, column_name, conn):
+    """
+    SQLite requires manual removal of any indexes referencing a column
+    before ALTER TABLE ... DROP COLUMN can succeed.
+    """
+    indexes = conn.execute(sa.text(f"PRAGMA index_list('{table_name}')")).fetchall()
+
+    for idx in indexes:
+        index_name = idx[1]  # index name
+        # Get indexed columns
+        idx_info = conn.execute(
+            sa.text(f"PRAGMA index_info('{index_name}')")
+        ).fetchall()
+
+        indexed_cols = [row[2] for row in idx_info]  # col names
+        if column_name in indexed_cols:
+            conn.execute(sa.text(f"DROP INDEX IF EXISTS {index_name}"))
+
+
+def _convert_column_to_json(table: str, column: str):
+    conn = op.get_bind()
+    dialect = conn.dialect.name
+
+    # SQLite cannot ALTER COLUMN → must recreate column
+    if dialect == "sqlite":
+        # 1. Add temporary column
+        op.add_column(table, sa.Column(f"{column}_json", sa.JSON(), nullable=True))
+
+        # 2. Load old data
+        rows = conn.execute(sa.text(f'SELECT id, {column} FROM "{table}"')).fetchall()
+
+        for row in rows:
+            uid, raw = row
+            if raw is None:
+                parsed = None
+            else:
+                try:
+                    parsed = json.loads(raw)
+                except Exception:
+                    parsed = None  # fallback safe behavior
+
+            conn.execute(
+                sa.text(f'UPDATE "{table}" SET {column}_json = :val WHERE id = :id'),
+                {"val": json.dumps(parsed) if parsed else None, "id": uid},
+            )
+
+        # 3. Drop old TEXT column
+        op.drop_column(table, column)
+
+        # 4. Rename new JSON column → original name
+        op.alter_column(table, f"{column}_json", new_column_name=column)
+
+    else:
+        # PostgreSQL supports direct CAST
+        op.alter_column(
+            table,
+            column,
+            type_=sa.JSON(),
+            postgresql_using=f"{column}::json",
+        )
+
+
+def _convert_column_to_text(table: str, column: str):
+    conn = op.get_bind()
+    dialect = conn.dialect.name
+
+    if dialect == "sqlite":
+        op.add_column(table, sa.Column(f"{column}_text", sa.Text(), nullable=True))
+
+        rows = conn.execute(sa.text(f'SELECT id, {column} FROM "{table}"')).fetchall()
+
+        for uid, raw in rows:
+            conn.execute(
+                sa.text(f'UPDATE "{table}" SET {column}_text = :val WHERE id = :id'),
+                {"val": json.dumps(raw) if raw else None, "id": uid},
+            )
+
+        op.drop_column(table, column)
+        op.alter_column(table, f"{column}_text", new_column_name=column)
+
+    else:
+        op.alter_column(
+            table,
+            column,
+            type_=sa.Text(),
+            postgresql_using=f"to_json({column})::text",
+        )
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user", sa.Column("profile_banner_image_url", sa.Text(), nullable=True)
+    )
+    op.add_column("user", sa.Column("timezone", sa.String(), nullable=True))
+
+    op.add_column("user", sa.Column("presence_state", sa.String(), nullable=True))
+    op.add_column("user", sa.Column("status_emoji", sa.String(), nullable=True))
+    op.add_column("user", sa.Column("status_message", sa.Text(), nullable=True))
+    op.add_column(
+        "user", sa.Column("status_expires_at", sa.BigInteger(), nullable=True)
+    )
+
+    op.add_column("user", sa.Column("oauth", sa.JSON(), nullable=True))
+
+    # Convert info (TEXT/JSONField) → JSON
+    _convert_column_to_json("user", "info")
+    # Convert settings (TEXT/JSONField) → JSON
+    _convert_column_to_json("user", "settings")
+
+    op.create_table(
+        "api_key",
+        sa.Column("id", sa.Text(), primary_key=True, unique=True),
+        sa.Column("user_id", sa.Text(), sa.ForeignKey("user.id", ondelete="CASCADE")),
+        sa.Column("key", sa.Text(), unique=True, nullable=False),
+        sa.Column("data", sa.JSON(), nullable=True),
+        sa.Column("expires_at", sa.BigInteger(), nullable=True),
+        sa.Column("last_used_at", sa.BigInteger(), nullable=True),
+        sa.Column("created_at", sa.BigInteger(), nullable=False),
+        sa.Column("updated_at", sa.BigInteger(), nullable=False),
+    )
+
+    conn = op.get_bind()
+    users = conn.execute(
+        sa.text('SELECT id, oauth_sub FROM "user" WHERE oauth_sub IS NOT NULL')
+    ).fetchall()
+
+    for uid, oauth_sub in users:
+        if oauth_sub:
+            # Example formats supported:
+            #   provider@sub
+            #   plain sub (stored as {"oidc": {"sub": sub}})
+            if "@" in oauth_sub:
+                provider, sub = oauth_sub.split("@", 1)
+            else:
+                provider, sub = "oidc", oauth_sub
+
+            oauth_json = json.dumps({provider: {"sub": sub}})
+            conn.execute(
+                sa.text('UPDATE "user" SET oauth = :oauth WHERE id = :id'),
+                {"oauth": oauth_json, "id": uid},
+            )
+
+    users_with_keys = conn.execute(
+        sa.text('SELECT id, api_key FROM "user" WHERE api_key IS NOT NULL')
+    ).fetchall()
+    now = int(time.time())
+
+    for uid, api_key in users_with_keys:
+        if api_key:
+            conn.execute(
+                sa.text(
+                    """
+                    INSERT INTO api_key (id, user_id, key, created_at, updated_at)
+                    VALUES (:id, :user_id, :key, :created_at, :updated_at)
+                """
+                ),
+                {
+                    "id": f"key_{uid}",
+                    "user_id": uid,
+                    "key": api_key,
+                    "created_at": now,
+                    "updated_at": now,
+                },
+            )
+
+    if conn.dialect.name == "sqlite":
+        _drop_sqlite_indexes_for_column("user", "api_key", conn)
+        _drop_sqlite_indexes_for_column("user", "oauth_sub", conn)
+
+    with op.batch_alter_table("user") as batch_op:
+        batch_op.drop_column("api_key")
+        batch_op.drop_column("oauth_sub")
+
+
+def downgrade() -> None:
+    # --- 1. Restore old oauth_sub column ---
+    op.add_column("user", sa.Column("oauth_sub", sa.Text(), nullable=True))
+
+    conn = op.get_bind()
+    users = conn.execute(
+        sa.text('SELECT id, oauth FROM "user" WHERE oauth IS NOT NULL')
+    ).fetchall()
+
+    for uid, oauth in users:
+        try:
+            data = json.loads(oauth)
+            provider = list(data.keys())[0]
+            sub = data[provider].get("sub")
+            oauth_sub = f"{provider}@{sub}"
+        except Exception:
+            oauth_sub = None
+
+        conn.execute(
+            sa.text('UPDATE "user" SET oauth_sub = :oauth_sub WHERE id = :id'),
+            {"oauth_sub": oauth_sub, "id": uid},
+        )
+
+    op.drop_column("user", "oauth")
+
+    # --- 2. Restore api_key field ---
+    op.add_column("user", sa.Column("api_key", sa.String(), nullable=True))
+
+    # Restore values from api_key
+    keys = conn.execute(sa.text("SELECT user_id, key FROM api_key")).fetchall()
+    for uid, key in keys:
+        conn.execute(
+            sa.text('UPDATE "user" SET api_key = :key WHERE id = :id'),
+            {"key": key, "id": uid},
+        )
+
+    # Drop new table
+    op.drop_table("api_key")
+
+    with op.batch_alter_table("user") as batch_op:
+        batch_op.drop_column("profile_banner_image_url")
+        batch_op.drop_column("timezone")
+
+        batch_op.drop_column("presence_state")
+        batch_op.drop_column("status_emoji")
+        batch_op.drop_column("status_message")
+        batch_op.drop_column("status_expires_at")
+
+    # Convert info (JSON) → TEXT
+    _convert_column_to_text("user", "info")
+    # Convert settings (JSON) → TEXT
+    _convert_column_to_text("user", "settings")

backend/open_webui/migrations/versions/c440947495f3_add_chat_file_table.py

@@ -0,0 +1,57 @@
+"""Add chat_file table
+
+Revision ID: c440947495f3
+Revises: 81cc2ce44d79
+Create Date: 2025-12-21 20:27:41.694897
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "c440947495f3"
+down_revision: Union[str, None] = "81cc2ce44d79"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "chat_file",
+        sa.Column("id", sa.Text(), primary_key=True),
+        sa.Column("user_id", sa.Text(), nullable=False),
+        sa.Column(
+            "chat_id",
+            sa.Text(),
+            sa.ForeignKey("chat.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column(
+            "file_id",
+            sa.Text(),
+            sa.ForeignKey("file.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("message_id", sa.Text(), nullable=True),
+        sa.Column("created_at", sa.BigInteger(), nullable=False),
+        sa.Column("updated_at", sa.BigInteger(), nullable=False),
+        # indexes
+        sa.Index("ix_chat_file_chat_id", "chat_id"),
+        sa.Index("ix_chat_file_file_id", "file_id"),
+        sa.Index("ix_chat_file_message_id", "message_id"),
+        sa.Index("ix_chat_file_user_id", "user_id"),
+        # unique constraints
+        sa.UniqueConstraint(
+            "chat_id", "file_id", name="uq_chat_file_chat_file"
+        ),  # prevent duplicate entries
+    )
+    pass
+
+
+def downgrade() -> None:
+    op.drop_table("chat_file")
+    pass

backend/open_webui/models/auths.py

@@ -2,15 +2,13 @@ import logging
 import uuid
 from typing import Optional
 
-from open_webui.internal.db import Base, get_db
-from open_webui.models.users import UserModel, Users
-from open_webui.env import SRC_LOG_LEVELS
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
+from open_webui.models.users import UserModel, UserProfileImageResponse, Users
 from pydantic import BaseModel
 from sqlalchemy import Boolean, Column, String, Text
-from open_webui.utils.auth import verify_password
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 ####################
 # DB MODEL
@@ -20,7 +18,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class Auth(Base):
     __tablename__ = "auth"
 
-    id = Column(String, primary_key=True)
+    id = Column(String, primary_key=True, unique=True)
     email = Column(String)
     password = Column(Text)
     active = Column(Boolean)
@@ -47,15 +45,7 @@ class ApiKey(BaseModel):
     api_key: Optional[str] = None
 
 
-class UserResponse(BaseModel):
-    id: str
-    email: str
-    name: str
-    role: str
-    profile_image_url: str
-
-
-class SigninResponse(Token, UserResponse):
+class SigninResponse(Token, UserProfileImageResponse):
     pass
 
 
@@ -97,9 +87,10 @@ class AuthsTable:
         name: str,
         profile_image_url: str = "/user.png",
         role: str = "pending",
-        oauth_sub: Optional[str] = None,
+        oauth: Optional[dict] = None,
+        db: Optional[Session] = None,
     ) -> Optional[UserModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             log.info("insert_new_auth")
 
             id = str(uuid.uuid4())
@@ -111,7 +102,7 @@ class AuthsTable:
             db.add(result)
 
             user = Users.insert_new_user(
-                id, name, email, profile_image_url, role, oauth_sub
+                id, name, email, profile_image_url, role, oauth=oauth, db=db
             )
 
             db.commit()
@@ -122,18 +113,20 @@ class AuthsTable:
             else:
                 return None
 
-    def authenticate_user(self, email: str, password: str) -> Optional[UserModel]:
+    def authenticate_user(
+        self, email: str, verify_password: callable, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         log.info(f"authenticate_user: {email}")
 
-        user = Users.get_user_by_email(email)
+        user = Users.get_user_by_email(email, db=db)
         if not user:
             return None
 
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 auth = db.query(Auth).filter_by(id=user.id, active=True).first()
                 if auth:
-                    if verify_password(password, auth.password):
+                    if verify_password(auth.password):
                         return user
                     else:
                         return None
@@ -142,32 +135,38 @@ class AuthsTable:
         except Exception:
             return None
 
-    def authenticate_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
+    def authenticate_user_by_api_key(
+        self, api_key: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         log.info(f"authenticate_user_by_api_key: {api_key}")
         # if no api_key, return None
         if not api_key:
             return None
 
         try:
-            user = Users.get_user_by_api_key(api_key)
+            user = Users.get_user_by_api_key(api_key, db=db)
             return user if user else None
         except Exception:
             return False
 
-    def authenticate_user_by_email(self, email: str) -> Optional[UserModel]:
+    def authenticate_user_by_email(
+        self, email: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         log.info(f"authenticate_user_by_email: {email}")
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 auth = db.query(Auth).filter_by(email=email, active=True).first()
                 if auth:
-                    user = Users.get_user_by_id(auth.id)
+                    user = Users.get_user_by_id(auth.id, db=db)
                     return user
         except Exception:
             return None
 
-    def update_user_password_by_id(self, id: str, new_password: str) -> bool:
+    def update_user_password_by_id(
+        self, id: str, new_password: str, db: Optional[Session] = None
+    ) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 result = (
                     db.query(Auth).filter_by(id=id).update({"password": new_password})
                 )
@@ -176,20 +175,22 @@ class AuthsTable:
         except Exception:
             return False
 
-    def update_email_by_id(self, id: str, email: str) -> bool:
+    def update_email_by_id(
+        self, id: str, email: str, db: Optional[Session] = None
+    ) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 result = db.query(Auth).filter_by(id=id).update({"email": email})
                 db.commit()
                 return True if result == 1 else False
         except Exception:
             return False
 
-    def delete_auth_by_id(self, id: str) -> bool:
+    def delete_auth_by_id(self, id: str, db: Optional[Session] = None) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 # Delete User
-                result = Users.delete_user_by_id(id)
+                result = Users.delete_user_by_id(id, db=db)
 
                 if result:
                     db.query(Auth).filter_by(id=id).delete()

backend/open_webui/models/feedbacks.py

@@ -3,15 +3,14 @@ import time
 import uuid
 from typing import Optional
 
-from open_webui.internal.db import Base, get_db
-from open_webui.models.chats import Chats
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
+from open_webui.models.users import User
 
-from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, Text, JSON, Boolean
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 
 ####################
@@ -21,7 +20,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 class Feedback(Base):
     __tablename__ = "feedback"
-    id = Column(Text, primary_key=True)
+    id = Column(Text, primary_key=True, unique=True)
     user_id = Column(Text)
     version = Column(BigInteger, default=0)
     type = Column(Text)
@@ -62,6 +61,20 @@ class FeedbackResponse(BaseModel):
     updated_at: int
 
 
+class FeedbackIdResponse(BaseModel):
+    id: str
+    user_id: str
+    created_at: int
+    updated_at: int
+
+
+class LeaderboardFeedbackData(BaseModel):
+    """Minimal feedback data for leaderboard computation (excludes snapshot/meta)."""
+
+    id: str
+    data: Optional[dict] = None
+
+
 class RatingData(BaseModel):
     rating: Optional[str | int] = None
     model_id: Optional[str] = None
@@ -92,11 +105,44 @@ class FeedbackForm(BaseModel):
     model_config = ConfigDict(extra="allow")
 
 
+class UserResponse(BaseModel):
+    id: str
+    name: str
+    email: str
+    role: str = "pending"
+
+    last_active_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+    created_at: int  # timestamp in epoch
+
+    model_config = ConfigDict(from_attributes=True)
+
+
+class FeedbackUserResponse(FeedbackResponse):
+    user: Optional[UserResponse] = None
+
+
+class FeedbackListResponse(BaseModel):
+    items: list[FeedbackUserResponse]
+    total: int
+
+
+class ModelHistoryEntry(BaseModel):
+    date: str
+    won: int
+    lost: int
+
+
+class ModelHistoryResponse(BaseModel):
+    model_id: str
+    history: list[ModelHistoryEntry]
+
+
 class FeedbackTable:
     def insert_new_feedback(
-        self, user_id: str, form_data: FeedbackForm
+        self, user_id: str, form_data: FeedbackForm, db: Optional[Session] = None
     ) -> Optional[FeedbackModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             id = str(uuid.uuid4())
             feedback = FeedbackModel(
                 **{
@@ -121,9 +167,11 @@ class FeedbackTable:
                 log.exception(f"Error creating a new feedback: {e}")
                 return None
 
-    def get_feedback_by_id(self, id: str) -> Optional[FeedbackModel]:
+    def get_feedback_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[FeedbackModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 feedback = db.query(Feedback).filter_by(id=id).first()
                 if not feedback:
                     return None
@@ -132,10 +180,10 @@ class FeedbackTable:
             return None
 
     def get_feedback_by_id_and_user_id(
-        self, id: str, user_id: str
+        self, id: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[FeedbackModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 feedback = db.query(Feedback).filter_by(id=id, user_id=user_id).first()
                 if not feedback:
                     return None
@@ -143,8 +191,76 @@ class FeedbackTable:
         except Exception:
             return None
 
-    def get_all_feedbacks(self) -> list[FeedbackModel]:
-        with get_db() as db:
+    def get_feedback_items(
+        self,
+        filter: dict = {},
+        skip: int = 0,
+        limit: int = 30,
+        db: Optional[Session] = None,
+    ) -> FeedbackListResponse:
+        with get_db_context(db) as db:
+            query = db.query(Feedback, User).join(User, Feedback.user_id == User.id)
+
+            if filter:
+                order_by = filter.get("order_by")
+                direction = filter.get("direction")
+
+                if order_by == "username":
+                    if direction == "asc":
+                        query = query.order_by(User.name.asc())
+                    else:
+                        query = query.order_by(User.name.desc())
+                elif order_by == "model_id":
+                    # it's stored in feedback.data['model_id']
+                    if direction == "asc":
+                        query = query.order_by(
+                            Feedback.data["model_id"].as_string().asc()
+                        )
+                    else:
+                        query = query.order_by(
+                            Feedback.data["model_id"].as_string().desc()
+                        )
+                elif order_by == "rating":
+                    # it's stored in feedback.data['rating']
+                    if direction == "asc":
+                        query = query.order_by(
+                            Feedback.data["rating"].as_string().asc()
+                        )
+                    else:
+                        query = query.order_by(
+                            Feedback.data["rating"].as_string().desc()
+                        )
+                elif order_by == "updated_at":
+                    if direction == "asc":
+                        query = query.order_by(Feedback.updated_at.asc())
+                    else:
+                        query = query.order_by(Feedback.updated_at.desc())
+
+            else:
+                query = query.order_by(Feedback.created_at.desc())
+
+            # Count BEFORE pagination
+            total = query.count()
+
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
+            items = query.all()
+
+            feedbacks = []
+            for feedback, user in items:
+                feedback_model = FeedbackModel.model_validate(feedback)
+                user_model = UserResponse.model_validate(user)
+                feedbacks.append(
+                    FeedbackUserResponse(**feedback_model.model_dump(), user=user_model)
+                )
+
+            return FeedbackListResponse(items=feedbacks, total=total)
+
+    def get_all_feedbacks(self, db: Optional[Session] = None) -> list[FeedbackModel]:
+        with get_db_context(db) as db:
             return [
                 FeedbackModel.model_validate(feedback)
                 for feedback in db.query(Feedback)
@@ -152,8 +268,110 @@ class FeedbackTable:
                 .all()
             ]
 
-    def get_feedbacks_by_type(self, type: str) -> list[FeedbackModel]:
-        with get_db() as db:
+    def get_all_feedback_ids(
+        self, db: Optional[Session] = None
+    ) -> list[FeedbackIdResponse]:
+        with get_db_context(db) as db:
+            return [
+                FeedbackIdResponse(
+                    id=row.id,
+                    user_id=row.user_id,
+                    created_at=row.created_at,
+                    updated_at=row.updated_at,
+                )
+                for row in db.query(
+                    Feedback.id,
+                    Feedback.user_id,
+                    Feedback.created_at,
+                    Feedback.updated_at,
+                )
+                .order_by(Feedback.updated_at.desc())
+                .all()
+            ]
+
+    def get_feedbacks_for_leaderboard(
+        self, db: Optional[Session] = None
+    ) -> list[LeaderboardFeedbackData]:
+        """Fetch only id and data for leaderboard computation (excludes snapshot/meta)."""
+        with get_db_context(db) as db:
+            return [
+                LeaderboardFeedbackData(id=row.id, data=row.data)
+                for row in db.query(Feedback.id, Feedback.data).all()
+            ]
+
+    def get_model_evaluation_history(
+        self, model_id: str, days: int = 30, db: Optional[Session] = None
+    ) -> list[ModelHistoryEntry]:
+        """
+        Get daily wins/losses for a specific model over the past N days.
+        If days=0, returns all time data starting from first feedback.
+        Returns: [{"date": "2026-01-08", "won": 5, "lost": 2}, ...]
+        """
+        from datetime import datetime, timedelta
+        from collections import defaultdict
+
+        with get_db_context(db) as db:
+            if days == 0:
+                # All time - no cutoff
+                rows = db.query(Feedback.created_at, Feedback.data).all()
+            else:
+                cutoff = int(time.time()) - (days * 86400)
+                rows = (
+                    db.query(Feedback.created_at, Feedback.data)
+                    .filter(Feedback.created_at >= cutoff)
+                    .all()
+                )
+
+        daily_counts = defaultdict(lambda: {"won": 0, "lost": 0})
+        first_date = None
+
+        for created_at, data in rows:
+            if not data:
+                continue
+            if data.get("model_id") != model_id:
+                continue
+
+            rating_str = str(data.get("rating", ""))
+            if rating_str not in ("1", "-1"):
+                continue
+
+            date_str = datetime.fromtimestamp(created_at).strftime("%Y-%m-%d")
+            if rating_str == "1":
+                daily_counts[date_str]["won"] += 1
+            else:
+                daily_counts[date_str]["lost"] += 1
+
+            # Track first date for this model
+            if first_date is None or date_str < first_date:
+                first_date = date_str
+
+        # Generate date range
+        result = []
+        today = datetime.now().date()
+
+        if days == 0 and first_date:
+            # All time: start from first feedback date
+            start_date = datetime.strptime(first_date, "%Y-%m-%d").date()
+            num_days = (today - start_date).days + 1
+        else:
+            # Fixed range
+            num_days = days
+            start_date = today - timedelta(days=days - 1)
+
+        for i in range(num_days):
+            d = start_date + timedelta(days=i)
+            date_str = d.strftime("%Y-%m-%d")
+            counts = daily_counts.get(date_str, {"won": 0, "lost": 0})
+            result.append(
+                ModelHistoryEntry(date=date_str, won=counts["won"], lost=counts["lost"])
+            )
+
+        return result
+
+    def get_feedbacks_by_type(
+        self, type: str, db: Optional[Session] = None
+    ) -> list[FeedbackModel]:
+        with get_db_context(db) as db:
             return [
                 FeedbackModel.model_validate(feedback)
                 for feedback in db.query(Feedback)
@@ -162,8 +380,10 @@ class FeedbackTable:
                 .all()
             ]
 
-    def get_feedbacks_by_user_id(self, user_id: str) -> list[FeedbackModel]:
-        with get_db() as db:
+    def get_feedbacks_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> list[FeedbackModel]:
+        with get_db_context(db) as db:
             return [
                 FeedbackModel.model_validate(feedback)
                 for feedback in db.query(Feedback)
@@ -173,9 +393,9 @@ class FeedbackTable:
             ]
 
     def update_feedback_by_id(
-        self, id: str, form_data: FeedbackForm
+        self, id: str, form_data: FeedbackForm, db: Optional[Session] = None
     ) -> Optional[FeedbackModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             feedback = db.query(Feedback).filter_by(id=id).first()
             if not feedback:
                 return None
@@ -193,9 +413,13 @@ class FeedbackTable:
             return FeedbackModel.model_validate(feedback)
 
     def update_feedback_by_id_and_user_id(
-        self, id: str, user_id: str, form_data: FeedbackForm
+        self,
+        id: str,
+        user_id: str,
+        form_data: FeedbackForm,
+        db: Optional[Session] = None,
     ) -> Optional[FeedbackModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             feedback = db.query(Feedback).filter_by(id=id, user_id=user_id).first()
             if not feedback:
                 return None
@@ -212,8 +436,8 @@ class FeedbackTable:
             db.commit()
             return FeedbackModel.model_validate(feedback)
 
-    def delete_feedback_by_id(self, id: str) -> bool:
-        with get_db() as db:
+    def delete_feedback_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             feedback = db.query(Feedback).filter_by(id=id).first()
             if not feedback:
                 return False
@@ -221,8 +445,10 @@ class FeedbackTable:
             db.commit()
             return True
 
-    def delete_feedback_by_id_and_user_id(self, id: str, user_id: str) -> bool:
-        with get_db() as db:
+    def delete_feedback_by_id_and_user_id(
+        self, id: str, user_id: str, db: Optional[Session] = None
+    ) -> bool:
+        with get_db_context(db) as db:
             feedback = db.query(Feedback).filter_by(id=id, user_id=user_id).first()
             if not feedback:
                 return False
@@ -230,8 +456,10 @@ class FeedbackTable:
             db.commit()
             return True
 
-    def delete_feedbacks_by_user_id(self, user_id: str) -> bool:
-        with get_db() as db:
+    def delete_feedbacks_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> bool:
+        with get_db_context(db) as db:
             feedbacks = db.query(Feedback).filter_by(user_id=user_id).all()
             if not feedbacks:
                 return False
@@ -240,8 +468,8 @@ class FeedbackTable:
             db.commit()
             return True
 
-    def delete_all_feedbacks(self) -> bool:
-        with get_db() as db:
+    def delete_all_feedbacks(self, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             feedbacks = db.query(Feedback).all()
             if not feedbacks:
                 return False

backend/open_webui/models/files.py

@@ -2,13 +2,12 @@ import logging
 import time
 from typing import Optional
 
-from open_webui.internal.db import Base, JSONField, get_db
-from open_webui.env import SRC_LOG_LEVELS
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text, JSON
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 ####################
 # Files DB Schema
@@ -17,7 +16,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 class File(Base):
     __tablename__ = "file"
-    id = Column(String, primary_key=True)
+    id = Column(String, primary_key=True, unique=True)
     user_id = Column(String)
     hash = Column(Text, nullable=True)
 
@@ -83,7 +82,7 @@ class FileModelResponse(BaseModel):
 class FileMetadataResponse(BaseModel):
     id: str
     hash: Optional[str] = None
-    meta: dict
+    meta: Optional[dict] = None
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
@@ -98,9 +97,22 @@ class FileForm(BaseModel):
     access_control: Optional[dict] = None
 
 
+class FileUpdateForm(BaseModel):
+    hash: Optional[str] = None
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+
+class FileListResponse(BaseModel):
+    items: list[FileModel]
+    total: int
+
+
 class FilesTable:
-    def insert_new_file(self, user_id: str, form_data: FileForm) -> Optional[FileModel]:
-        with get_db() as db:
+    def insert_new_file(
+        self, user_id: str, form_data: FileForm, db: Optional[Session] = None
+    ) -> Optional[FileModel]:
+        with get_db_context(db) as db:
             file = FileModel(
                 **{
                     **form_data.model_dump(),
@@ -123,16 +135,23 @@ class FilesTable:
                 log.exception(f"Error inserting a new file: {e}")
                 return None
 
-    def get_file_by_id(self, id: str) -> Optional[FileModel]:
-        with get_db() as db:
-            try:
-                file = db.get(File, id)
-                return FileModel.model_validate(file)
-            except Exception:
-                return None
+    def get_file_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[FileModel]:
+        try:
+            with get_db_context(db) as db:
+                try:
+                    file = db.get(File, id)
+                    return FileModel.model_validate(file)
+                except Exception:
+                    return None
+        except Exception:
+            return None
 
-    def get_file_by_id_and_user_id(self, id: str, user_id: str) -> Optional[FileModel]:
-        with get_db() as db:
+    def get_file_by_id_and_user_id(
+        self, id: str, user_id: str, db: Optional[Session] = None
+    ) -> Optional[FileModel]:
+        with get_db_context(db) as db:
             try:
                 file = db.query(File).filter_by(id=id, user_id=user_id).first()
                 if file:
@@ -142,8 +161,10 @@ class FilesTable:
             except Exception:
                 return None
 
-    def get_file_metadata_by_id(self, id: str) -> Optional[FileMetadataResponse]:
-        with get_db() as db:
+    def get_file_metadata_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[FileMetadataResponse]:
+        with get_db_context(db) as db:
             try:
                 file = db.get(File, id)
                 return FileMetadataResponse(
@@ -156,12 +177,14 @@ class FilesTable:
             except Exception:
                 return None
 
-    def get_files(self) -> list[FileModel]:
-        with get_db() as db:
+    def get_files(self, db: Optional[Session] = None) -> list[FileModel]:
+        with get_db_context(db) as db:
             return [FileModel.model_validate(file) for file in db.query(File).all()]
 
-    def check_access_by_user_id(self, id, user_id, permission="write") -> bool:
-        file = self.get_file_by_id(id)
+    def check_access_by_user_id(
+        self, id, user_id, permission="write", db: Optional[Session] = None
+    ) -> bool:
+        file = self.get_file_by_id(id, db=db)
         if not file:
             return False
         if file.user_id == user_id:
@@ -169,8 +192,10 @@ class FilesTable:
         # Implement additional access control logic here as needed
         return False
 
-    def get_files_by_ids(self, ids: list[str]) -> list[FileModel]:
-        with get_db() as db:
+    def get_files_by_ids(
+        self, ids: list[str], db: Optional[Session] = None
+    ) -> list[FileModel]:
+        with get_db_context(db) as db:
             return [
                 FileModel.model_validate(file)
                 for file in db.query(File)
@@ -179,8 +204,10 @@ class FilesTable:
                 .all()
             ]
 
-    def get_file_metadatas_by_ids(self, ids: list[str]) -> list[FileMetadataResponse]:
-        with get_db() as db:
+    def get_file_metadatas_by_ids(
+        self, ids: list[str], db: Optional[Session] = None
+    ) -> list[FileMetadataResponse]:
+        with get_db_context(db) as db:
             return [
                 FileMetadataResponse(
                     id=file.id,
@@ -197,47 +224,145 @@ class FilesTable:
                 .all()
             ]
 
-    def get_files_by_user_id(self, user_id: str) -> list[FileModel]:
-        with get_db() as db:
+    def get_files_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> list[FileModel]:
+        with get_db_context(db) as db:
             return [
                 FileModel.model_validate(file)
                 for file in db.query(File).filter_by(user_id=user_id).all()
             ]
 
-    def update_file_hash_by_id(self, id: str, hash: str) -> Optional[FileModel]:
-        with get_db() as db:
+    @staticmethod
+    def _glob_to_like_pattern(glob: str) -> str:
+        """
+        Convert a glob/fnmatch pattern to a SQL LIKE pattern.
+
+        Escapes SQL special characters and converts glob wildcards:
+        - `*` becomes `%` (match any sequence of characters)
+        - `?` becomes `_` (match exactly one character)
+
+        Args:
+            glob: A glob pattern (e.g., "*.txt", "file?.doc")
+
+        Returns:
+            A SQL LIKE compatible pattern with proper escaping.
+        """
+        # Escape SQL special characters first, then convert glob wildcards
+        pattern = glob.replace("\\", "\\\\")
+        pattern = pattern.replace("%", "\\%")
+        pattern = pattern.replace("_", "\\_")
+        pattern = pattern.replace("*", "%")
+        pattern = pattern.replace("?", "_")
+        return pattern
+
+    def search_files(
+        self,
+        user_id: Optional[str] = None,
+        filename: str = "*",
+        skip: int = 0,
+        limit: int = 100,
+        db: Optional[Session] = None,
+    ) -> list[FileModel]:
+        """
+        Search files with glob pattern matching, optional user filter, and pagination.
+
+        Args:
+            user_id: Filter by user ID. If None, returns files for all users.
+            filename: Glob pattern to match filenames (e.g., "*.txt"). Default "*" matches all.
+            skip: Number of results to skip for pagination.
+            limit: Maximum number of results to return.
+            db: Optional database session.
+
+        Returns:
+            List of matching FileModel objects, ordered by updated_at descending.
+        """
+        with get_db_context(db) as db:
+            query = db.query(File)
+
+            if user_id:
+                query = query.filter_by(user_id=user_id)
+
+            pattern = self._glob_to_like_pattern(filename)
+            if pattern != "%":
+                query = query.filter(File.filename.ilike(pattern, escape="\\"))
+
+            return [
+                FileModel.model_validate(file)
+                for file in query.order_by(File.updated_at.desc())
+                .offset(skip)
+                .limit(limit)
+                .all()
+            ]
+
+    def update_file_by_id(
+        self, id: str, form_data: FileUpdateForm, db: Optional[Session] = None
+    ) -> Optional[FileModel]:
+        with get_db_context(db) as db:
+            try:
+                file = db.query(File).filter_by(id=id).first()
+
+                if form_data.hash is not None:
+                    file.hash = form_data.hash
+
+                if form_data.data is not None:
+                    file.data = {**(file.data if file.data else {}), **form_data.data}
+
+                if form_data.meta is not None:
+                    file.meta = {**(file.meta if file.meta else {}), **form_data.meta}
+
+                file.updated_at = int(time.time())
+                db.commit()
+                return FileModel.model_validate(file)
+            except Exception as e:
+                log.exception(f"Error updating file completely by id: {e}")
+                return None
+
+    def update_file_hash_by_id(
+        self, id: str, hash: Optional[str], db: Optional[Session] = None
+    ) -> Optional[FileModel]:
+        with get_db_context(db) as db:
             try:
                 file = db.query(File).filter_by(id=id).first()
                 file.hash = hash
+                file.updated_at = int(time.time())
                 db.commit()
 
                 return FileModel.model_validate(file)
             except Exception:
                 return None
 
-    def update_file_data_by_id(self, id: str, data: dict) -> Optional[FileModel]:
-        with get_db() as db:
+    def update_file_data_by_id(
+        self, id: str, data: dict, db: Optional[Session] = None
+    ) -> Optional[FileModel]:
+        with get_db_context(db) as db:
             try:
                 file = db.query(File).filter_by(id=id).first()
                 file.data = {**(file.data if file.data else {}), **data}
+                file.updated_at = int(time.time())
                 db.commit()
                 return FileModel.model_validate(file)
             except Exception as e:
 
                 return None
 
-    def update_file_metadata_by_id(self, id: str, meta: dict) -> Optional[FileModel]:
-        with get_db() as db:
+    def update_file_metadata_by_id(
+        self, id: str, meta: dict, db: Optional[Session] = None
+    ) -> Optional[FileModel]:
+        with get_db_context(db) as db:
             try:
                 file = db.query(File).filter_by(id=id).first()
                 file.meta = {**(file.meta if file.meta else {}), **meta}
+                file.updated_at = int(time.time())
                 db.commit()
                 return FileModel.model_validate(file)
             except Exception:
                 return None
 
-    def delete_file_by_id(self, id: str) -> bool:
-        with get_db() as db:
+                return False
+
+    def delete_file_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             try:
                 db.query(File).filter_by(id=id).delete()
                 db.commit()
@@ -246,8 +371,8 @@ class FilesTable:
             except Exception:
                 return False
 
-    def delete_all_files(self) -> bool:
-        with get_db() as db:
+    def delete_all_files(self, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             try:
                 db.query(File).delete()
                 db.commit()

backend/open_webui/models/folders.py

@@ -7,13 +7,12 @@ import re
 
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, Text, JSON, Boolean, func
+from sqlalchemy.orm import Session
 
-from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 
 ####################
@@ -23,7 +22,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 class Folder(Base):
     __tablename__ = "folder"
-    id = Column(Text, primary_key=True)
+    id = Column(Text, primary_key=True, unique=True)
     parent_id = Column(Text, nullable=True)
     user_id = Column(Text)
     name = Column(Text)
@@ -85,9 +84,13 @@ class FolderUpdateForm(BaseModel):
 
 class FolderTable:
     def insert_new_folder(
-        self, user_id: str, form_data: FolderForm, parent_id: Optional[str] = None
+        self,
+        user_id: str,
+        form_data: FolderForm,
+        parent_id: Optional[str] = None,
+        db: Optional[Session] = None,
     ) -> Optional[FolderModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             id = str(uuid.uuid4())
             folder = FolderModel(
                 **{
@@ -113,10 +116,10 @@ class FolderTable:
                 return None
 
     def get_folder_by_id_and_user_id(
-        self, id: str, user_id: str
+        self, id: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[FolderModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
 
                 if not folder:
@@ -127,15 +130,15 @@ class FolderTable:
             return None
 
     def get_children_folders_by_id_and_user_id(
-        self, id: str, user_id: str
+        self, id: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[list[FolderModel]]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 folders = []
 
                 def get_children(folder):
                     children = self.get_folders_by_parent_id_and_user_id(
-                        folder.id, user_id
+                        folder.id, user_id, db=db
                     )
                     for child in children:
                         get_children(child)
@@ -150,18 +153,24 @@ class FolderTable:
         except Exception:
             return None
 
-    def get_folders_by_user_id(self, user_id: str) -> list[FolderModel]:
-        with get_db() as db:
+    def get_folders_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> list[FolderModel]:
+        with get_db_context(db) as db:
             return [
                 FolderModel.model_validate(folder)
                 for folder in db.query(Folder).filter_by(user_id=user_id).all()
             ]
 
     def get_folder_by_parent_id_and_user_id_and_name(
-        self, parent_id: Optional[str], user_id: str, name: str
+        self,
+        parent_id: Optional[str],
+        user_id: str,
+        name: str,
+        db: Optional[Session] = None,
     ) -> Optional[FolderModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 # Check if folder exists
                 folder = (
                     db.query(Folder)
@@ -179,9 +188,9 @@ class FolderTable:
             return None
 
     def get_folders_by_parent_id_and_user_id(
-        self, parent_id: Optional[str], user_id: str
+        self, parent_id: Optional[str], user_id: str, db: Optional[Session] = None
     ) -> list[FolderModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             return [
                 FolderModel.model_validate(folder)
                 for folder in db.query(Folder)
@@ -194,9 +203,10 @@ class FolderTable:
         id: str,
         user_id: str,
         parent_id: str,
+        db: Optional[Session] = None,
     ) -> Optional[FolderModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
 
                 if not folder:
@@ -213,10 +223,14 @@ class FolderTable:
             return
 
     def update_folder_by_id_and_user_id(
-        self, id: str, user_id: str, form_data: FolderUpdateForm
+        self,
+        id: str,
+        user_id: str,
+        form_data: FolderUpdateForm,
+        db: Optional[Session] = None,
     ) -> Optional[FolderModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
 
                 if not folder:
@@ -259,10 +273,10 @@ class FolderTable:
             return
 
     def update_folder_is_expanded_by_id_and_user_id(
-        self, id: str, user_id: str, is_expanded: bool
+        self, id: str, user_id: str, is_expanded: bool, db: Optional[Session] = None
     ) -> Optional[FolderModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
 
                 if not folder:
@@ -278,10 +292,12 @@ class FolderTable:
             log.error(f"update_folder: {e}")
             return
 
-    def delete_folder_by_id_and_user_id(self, id: str, user_id: str) -> list[str]:
+    def delete_folder_by_id_and_user_id(
+        self, id: str, user_id: str, db: Optional[Session] = None
+    ) -> list[str]:
         try:
             folder_ids = []
-            with get_db() as db:
+            with get_db_context(db) as db:
                 folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
                 if not folder:
                     return folder_ids
@@ -291,7 +307,7 @@ class FolderTable:
                 # Delete all children folders
                 def delete_children(folder):
                     folder_children = self.get_folders_by_parent_id_and_user_id(
-                        folder.id, user_id
+                        folder.id, user_id, db=db
                     )
                     for folder_child in folder_children:
 
@@ -316,7 +332,7 @@ class FolderTable:
         return name.strip().lower()
 
     def search_folders_by_names(
-        self, user_id: str, queries: list[str]
+        self, user_id: str, queries: list[str], db: Optional[Session] = None
     ) -> list[FolderModel]:
         """
         Search for folders for a user where the name matches any of the queries, treating _ and space as equivalent, case-insensitive.
@@ -326,7 +342,7 @@ class FolderTable:
             return []
 
         results = {}
-        with get_db() as db:
+        with get_db_context(db) as db:
             folders = db.query(Folder).filter_by(user_id=user_id).all()
             for folder in folders:
                 if self.normalize_folder_name(folder.name) in normalized_queries:
@@ -334,7 +350,7 @@ class FolderTable:
 
                     # get children folders
                     children = self.get_children_folders_by_id_and_user_id(
-                        folder.id, user_id
+                        folder.id, user_id, db=db
                     )
                     for child in children:
                         results[child.id] = child
@@ -347,14 +363,14 @@ class FolderTable:
             return results
 
     def search_folders_by_name_contains(
-        self, user_id: str, query: str
+        self, user_id: str, query: str, db: Optional[Session] = None
     ) -> list[FolderModel]:
         """
         Partial match: normalized name contains (as substring) the normalized query.
         """
         normalized_query = self.normalize_folder_name(query)
         results = []
-        with get_db() as db:
+        with get_db_context(db) as db:
             folders = db.query(Folder).filter_by(user_id=user_id).all()
             for folder in folders:
                 norm_name = self.normalize_folder_name(folder.name)

backend/open_webui/models/functions.py

@@ -2,14 +2,13 @@ import logging
 import time
 from typing import Optional
 
-from open_webui.internal.db import Base, JSONField, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 from open_webui.models.users import Users, UserModel
-from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Boolean, Column, String, Text, Index
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 ####################
 # Functions DB Schema
@@ -19,7 +18,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class Function(Base):
     __tablename__ = "function"
 
-    id = Column(String, primary_key=True)
+    id = Column(String, primary_key=True, unique=True)
     user_id = Column(String)
     name = Column(Text)
     type = Column(Text)
@@ -105,7 +104,11 @@ class FunctionValves(BaseModel):
 
 class FunctionsTable:
     def insert_new_function(
-        self, user_id: str, type: str, form_data: FunctionForm
+        self,
+        user_id: str,
+        type: str,
+        form_data: FunctionForm,
+        db: Optional[Session] = None,
     ) -> Optional[FunctionModel]:
         function = FunctionModel(
             **{
@@ -118,7 +121,7 @@ class FunctionsTable:
         )
 
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 result = Function(**function.model_dump())
                 db.add(result)
                 db.commit()
@@ -132,11 +135,14 @@ class FunctionsTable:
             return None
 
     def sync_functions(
-        self, user_id: str, functions: list[FunctionWithValvesModel]
+        self,
+        user_id: str,
+        functions: list[FunctionWithValvesModel],
+        db: Optional[Session] = None,
     ) -> list[FunctionWithValvesModel]:
         # Synchronize functions for a user by updating existing ones, inserting new ones, and removing those that are no longer present.
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 # Get existing functions
                 existing_functions = db.query(Function).all()
                 existing_ids = {func.id for func in existing_functions}
@@ -179,18 +185,20 @@ class FunctionsTable:
             log.exception(f"Error syncing functions for user {user_id}: {e}")
             return []
 
-    def get_function_by_id(self, id: str) -> Optional[FunctionModel]:
+    def get_function_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[FunctionModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 function = db.get(Function, id)
                 return FunctionModel.model_validate(function)
         except Exception:
             return None
 
     def get_functions(
-        self, active_only=False, include_valves=False
+        self, active_only=False, include_valves=False, db: Optional[Session] = None
     ) -> list[FunctionModel | FunctionWithValvesModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             if active_only:
                 functions = db.query(Function).filter_by(is_active=True).all()
 
@@ -207,12 +215,14 @@ class FunctionsTable:
                     FunctionModel.model_validate(function) for function in functions
                 ]
 
-    def get_function_list(self) -> list[FunctionUserResponse]:
-        with get_db() as db:
+    def get_function_list(
+        self, db: Optional[Session] = None
+    ) -> list[FunctionUserResponse]:
+        with get_db_context(db) as db:
             functions = db.query(Function).order_by(Function.updated_at.desc()).all()
             user_ids = list(set(func.user_id for func in functions))
 
-            users = Users.get_users_by_user_ids(user_ids) if user_ids else []
+            users = Users.get_users_by_user_ids(user_ids, db=db) if user_ids else []
             users_dict = {user.id: user for user in users}
 
             return [
@@ -230,9 +240,9 @@ class FunctionsTable:
             ]
 
     def get_functions_by_type(
-        self, type: str, active_only=False
+        self, type: str, active_only=False, db: Optional[Session] = None
     ) -> list[FunctionModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             if active_only:
                 return [
                     FunctionModel.model_validate(function)
@@ -246,8 +256,10 @@ class FunctionsTable:
                     for function in db.query(Function).filter_by(type=type).all()
                 ]
 
-    def get_global_filter_functions(self) -> list[FunctionModel]:
-        with get_db() as db:
+    def get_global_filter_functions(
+        self, db: Optional[Session] = None
+    ) -> list[FunctionModel]:
+        with get_db_context(db) as db:
             return [
                 FunctionModel.model_validate(function)
                 for function in db.query(Function)
@@ -255,8 +267,10 @@ class FunctionsTable:
                 .all()
             ]
 
-    def get_global_action_functions(self) -> list[FunctionModel]:
-        with get_db() as db:
+    def get_global_action_functions(
+        self, db: Optional[Session] = None
+    ) -> list[FunctionModel]:
+        with get_db_context(db) as db:
             return [
                 FunctionModel.model_validate(function)
                 for function in db.query(Function)
@@ -264,8 +278,10 @@ class FunctionsTable:
                 .all()
             ]
 
-    def get_function_valves_by_id(self, id: str) -> Optional[dict]:
-        with get_db() as db:
+    def get_function_valves_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[dict]:
+        with get_db_context(db) as db:
             try:
                 function = db.get(Function, id)
                 return function.valves if function.valves else {}
@@ -274,23 +290,23 @@ class FunctionsTable:
                 return None
 
     def update_function_valves_by_id(
-        self, id: str, valves: dict
+        self, id: str, valves: dict, db: Optional[Session] = None
     ) -> Optional[FunctionValves]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             try:
                 function = db.get(Function, id)
                 function.valves = valves
                 function.updated_at = int(time.time())
                 db.commit()
                 db.refresh(function)
-                return self.get_function_by_id(id)
+                return self.get_function_by_id(id, db=db)
             except Exception:
                 return None
 
     def update_function_metadata_by_id(
-        self, id: str, metadata: dict
+        self, id: str, metadata: dict, db: Optional[Session] = None
     ) -> Optional[FunctionModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             try:
                 function = db.get(Function, id)
 
@@ -303,7 +319,7 @@ class FunctionsTable:
                     function.updated_at = int(time.time())
                     db.commit()
                     db.refresh(function)
-                    return self.get_function_by_id(id)
+                    return self.get_function_by_id(id, db=db)
                 else:
                     return None
             except Exception as e:
@@ -311,10 +327,10 @@ class FunctionsTable:
                 return None
 
     def get_user_valves_by_id_and_user_id(
-        self, id: str, user_id: str
+        self, id: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[dict]:
         try:
-            user = Users.get_user_by_id(user_id)
+            user = Users.get_user_by_id(user_id, db=db)
             user_settings = user.settings.model_dump() if user.settings else {}
 
             # Check if user has "functions" and "valves" settings
@@ -329,10 +345,10 @@ class FunctionsTable:
             return None
 
     def update_user_valves_by_id_and_user_id(
-        self, id: str, user_id: str, valves: dict
+        self, id: str, user_id: str, valves: dict, db: Optional[Session] = None
     ) -> Optional[dict]:
         try:
-            user = Users.get_user_by_id(user_id)
+            user = Users.get_user_by_id(user_id, db=db)
             user_settings = user.settings.model_dump() if user.settings else {}
 
             # Check if user has "functions" and "valves" settings
@@ -344,7 +360,7 @@ class FunctionsTable:
             user_settings["functions"]["valves"][id] = valves
 
             # Update the user settings in the database
-            Users.update_user_by_id(user_id, {"settings": user_settings})
+            Users.update_user_by_id(user_id, {"settings": user_settings}, db=db)
 
             return user_settings["functions"]["valves"][id]
         except Exception as e:
@@ -353,8 +369,10 @@ class FunctionsTable:
             )
             return None
 
-    def update_function_by_id(self, id: str, updated: dict) -> Optional[FunctionModel]:
-        with get_db() as db:
+    def update_function_by_id(
+        self, id: str, updated: dict, db: Optional[Session] = None
+    ) -> Optional[FunctionModel]:
+        with get_db_context(db) as db:
             try:
                 db.query(Function).filter_by(id=id).update(
                     {
@@ -363,12 +381,12 @@ class FunctionsTable:
                     }
                 )
                 db.commit()
-                return self.get_function_by_id(id)
+                return self.get_function_by_id(id, db=db)
             except Exception:
                 return None
 
-    def deactivate_all_functions(self) -> Optional[bool]:
-        with get_db() as db:
+    def deactivate_all_functions(self, db: Optional[Session] = None) -> Optional[bool]:
+        with get_db_context(db) as db:
             try:
                 db.query(Function).update(
                     {
@@ -381,8 +399,8 @@ class FunctionsTable:
             except Exception:
                 return None
 
-    def delete_function_by_id(self, id: str) -> bool:
-        with get_db() as db:
+    def delete_function_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             try:
                 db.query(Function).filter_by(id=id).delete()
                 db.commit()

backend/open_webui/models/groups.py

@@ -4,18 +4,28 @@ import time
 from typing import Optional
 import uuid
 
-from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 
 from open_webui.models.files import FileMetadataResponse
 
 
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text, JSON, func
+from sqlalchemy import (
+    BigInteger,
+    Column,
+    String,
+    Text,
+    JSON,
+    and_,
+    func,
+    ForeignKey,
+    cast,
+    or_,
+)
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 ####################
 # UserGroup DB Schema
@@ -35,14 +45,12 @@ class Group(Base):
     meta = Column(JSON, nullable=True)
 
     permissions = Column(JSON, nullable=True)
-    user_ids = Column(JSON, nullable=True)
 
     created_at = Column(BigInteger)
     updated_at = Column(BigInteger)
 
 
 class GroupModel(BaseModel):
-    model_config = ConfigDict(from_attributes=True)
     id: str
     user_id: str
 
@@ -53,49 +61,69 @@ class GroupModel(BaseModel):
     meta: Optional[dict] = None
 
     permissions: Optional[dict] = None
-    user_ids: list[str] = []
 
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
+    model_config = ConfigDict(from_attributes=True)
+
+
+class GroupMember(Base):
+    __tablename__ = "group_member"
+
+    id = Column(Text, unique=True, primary_key=True)
+    group_id = Column(
+        Text,
+        ForeignKey("group.id", ondelete="CASCADE"),
+        nullable=False,
+    )
+    user_id = Column(Text, nullable=False)
+    created_at = Column(BigInteger, nullable=True)
+    updated_at = Column(BigInteger, nullable=True)
+
+
+class GroupMemberModel(BaseModel):
+    id: str
+    group_id: str
+    user_id: str
+    created_at: Optional[int] = None  # timestamp in epoch
+    updated_at: Optional[int] = None  # timestamp in epoch
+
 
 ####################
 # Forms
 ####################
 
 
-class GroupResponse(BaseModel):
-    id: str
-    user_id: str
-    name: str
-    description: str
-    permissions: Optional[dict] = None
-    data: Optional[dict] = None
-    meta: Optional[dict] = None
-    user_ids: list[str] = []
-    created_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
+class GroupResponse(GroupModel):
+    member_count: Optional[int] = None
 
 
 class GroupForm(BaseModel):
     name: str
     description: str
     permissions: Optional[dict] = None
+    data: Optional[dict] = None
 
 
 class UserIdsForm(BaseModel):
     user_ids: Optional[list[str]] = None
 
 
-class GroupUpdateForm(GroupForm, UserIdsForm):
+class GroupUpdateForm(GroupForm):
     pass
 
 
+class GroupListResponse(BaseModel):
+    items: list[GroupResponse] = []
+    total: int = 0
+
+
 class GroupTable:
     def insert_new_group(
-        self, user_id: str, form_data: GroupForm
+        self, user_id: str, form_data: GroupForm, db: Optional[Session] = None
     ) -> Optional[GroupModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             group = GroupModel(
                 **{
                     **form_data.model_dump(exclude_none=True),
@@ -119,48 +147,236 @@ class GroupTable:
             except Exception:
                 return None
 
-    def get_groups(self) -> list[GroupModel]:
-        with get_db() as db:
+    def get_all_groups(self, db: Optional[Session] = None) -> list[GroupModel]:
+        with get_db_context(db) as db:
+            groups = db.query(Group).order_by(Group.updated_at.desc()).all()
+            return [GroupModel.model_validate(group) for group in groups]
+
+    def get_groups(self, filter, db: Optional[Session] = None) -> list[GroupResponse]:
+        with get_db_context(db) as db:
+            query = db.query(Group)
+
+            if filter:
+                if "query" in filter:
+                    query = query.filter(Group.name.ilike(f"%{filter['query']}%"))
+
+                # When share filter is present, member check is handled in the share logic
+                if "share" in filter:
+                    share_value = filter["share"]
+                    member_id = filter.get("member_id")
+                    json_share = Group.data["config"]["share"]
+                    json_share_bool = json_share.as_boolean()
+                    json_share_str = json_share.as_string()
+
+                    if share_value:
+                        # Groups open to anyone: data is null, share is null, or share is true
+                        anyone_can_share = or_(
+                            Group.data.is_(None),
+                            json_share_bool.is_(None),
+                            json_share_bool == True,
+                        )
+
+                        if member_id:
+                            # Also include member-only groups where user is a member
+                            member_groups_subq = (
+                                db.query(GroupMember.group_id)
+                                .filter(GroupMember.user_id == member_id)
+                                .subquery()
+                            )
+                            members_only_and_is_member = and_(
+                                json_share_str == "members",
+                                Group.id.in_(member_groups_subq),
+                            )
+                            query = query.filter(
+                                or_(anyone_can_share, members_only_and_is_member)
+                            )
+                        else:
+                            query = query.filter(anyone_can_share)
+                    else:
+                        query = query.filter(
+                            and_(Group.data.isnot(None), json_share_bool == False)
+                        )
+
+                else:
+                    # Only apply member_id filter when share filter is NOT present
+                    if "member_id" in filter:
+                        query = query.join(
+                            GroupMember, GroupMember.group_id == Group.id
+                        ).filter(GroupMember.user_id == filter["member_id"])
+
+            groups = query.order_by(Group.updated_at.desc()).all()
             return [
-                GroupModel.model_validate(group)
-                for group in db.query(Group).order_by(Group.updated_at.desc()).all()
+                GroupResponse.model_validate(
+                    {
+                        **GroupModel.model_validate(group).model_dump(),
+                        "member_count": self.get_group_member_count_by_id(
+                            group.id, db=db
+                        ),
+                    }
+                )
+                for group in groups
             ]
 
-    def get_groups_by_member_id(self, user_id: str) -> list[GroupModel]:
-        with get_db() as db:
+    def search_groups(
+        self,
+        filter: Optional[dict] = None,
+        skip: int = 0,
+        limit: int = 30,
+        db: Optional[Session] = None,
+    ) -> GroupListResponse:
+        with get_db_context(db) as db:
+            query = db.query(Group)
+
+            if filter:
+                if "query" in filter:
+                    query = query.filter(Group.name.ilike(f"%{filter['query']}%"))
+                if "member_id" in filter:
+                    query = query.join(
+                        GroupMember, GroupMember.group_id == Group.id
+                    ).filter(GroupMember.user_id == filter["member_id"])
+
+                if "share" in filter:
+                    #  'share' is stored in data JSON, support both sqlite and postgres
+                    share_value = filter["share"]
+                    print("Filtering by share:", share_value)
+                    query = query.filter(
+                        Group.data.op("->>")("share") == str(share_value)
+                    )
+
+            total = query.count()
+            query = query.order_by(Group.updated_at.desc())
+            groups = query.offset(skip).limit(limit).all()
+
+            return {
+                "items": [
+                    GroupResponse.model_validate(
+                        **GroupModel.model_validate(group).model_dump(),
+                        member_count=self.get_group_member_count_by_id(group.id, db=db),
+                    )
+                    for group in groups
+                ],
+                "total": total,
+            }
+
+    def get_groups_by_member_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> list[GroupModel]:
+        with get_db_context(db) as db:
             return [
                 GroupModel.model_validate(group)
                 for group in db.query(Group)
-                .filter(
-                    func.json_array_length(Group.user_ids) > 0
-                )  # Ensure array exists
-                .filter(
-                    Group.user_ids.cast(String).like(f'%"{user_id}"%')
-                )  # String-based check
+                .join(GroupMember, GroupMember.group_id == Group.id)
+                .filter(GroupMember.user_id == user_id)
                 .order_by(Group.updated_at.desc())
                 .all()
             ]
 
-    def get_group_by_id(self, id: str) -> Optional[GroupModel]:
+    def get_groups_by_member_ids(
+        self, user_ids: list[str], db: Optional[Session] = None
+    ) -> dict[str, list[GroupModel]]:
+        """Fetch groups for multiple users in a single query to avoid N+1."""
+        with get_db_context(db) as db:
+            # Query GroupMember joined with Group, filtering by user_ids
+            results = (
+                db.query(GroupMember.user_id, Group)
+                .join(Group, Group.id == GroupMember.group_id)
+                .filter(GroupMember.user_id.in_(user_ids))
+                .order_by(Group.updated_at.desc())
+                .all()
+            )
+
+            # Group groups by user_id
+            user_groups: dict[str, list[GroupModel]] = {uid: [] for uid in user_ids}
+            for user_id, group in results:
+                user_groups[user_id].append(GroupModel.model_validate(group))
+
+            return user_groups
+
+    def get_group_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[GroupModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 group = db.query(Group).filter_by(id=id).first()
                 return GroupModel.model_validate(group) if group else None
         except Exception:
             return None
 
-    def get_group_user_ids_by_id(self, id: str) -> Optional[str]:
-        group = self.get_group_by_id(id)
-        if group:
-            return group.user_ids
-        else:
-            return None
+    def get_group_user_ids_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[list[str]]:
+        with get_db_context(db) as db:
+            members = (
+                db.query(GroupMember.user_id).filter(GroupMember.group_id == id).all()
+            )
+
+            if not members:
+                return None
+
+            return [m[0] for m in members]
+
+    def get_group_user_ids_by_ids(
+        self, group_ids: list[str], db: Optional[Session] = None
+    ) -> dict[str, list[str]]:
+        with get_db_context(db) as db:
+            members = (
+                db.query(GroupMember.group_id, GroupMember.user_id)
+                .filter(GroupMember.group_id.in_(group_ids))
+                .all()
+            )
+
+            group_user_ids: dict[str, list[str]] = {
+                group_id: [] for group_id in group_ids
+            }
+
+            for group_id, user_id in members:
+                group_user_ids[group_id].append(user_id)
+
+            return group_user_ids
+
+    def set_group_user_ids_by_id(
+        self, group_id: str, user_ids: list[str], db: Optional[Session] = None
+    ) -> None:
+        with get_db_context(db) as db:
+            # Delete existing members
+            db.query(GroupMember).filter(GroupMember.group_id == group_id).delete()
+
+            # Insert new members
+            now = int(time.time())
+            new_members = [
+                GroupMember(
+                    id=str(uuid.uuid4()),
+                    group_id=group_id,
+                    user_id=user_id,
+                    created_at=now,
+                    updated_at=now,
+                )
+                for user_id in user_ids
+            ]
+
+            db.add_all(new_members)
+            db.commit()
+
+    def get_group_member_count_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> int:
+        with get_db_context(db) as db:
+            count = (
+                db.query(func.count(GroupMember.user_id))
+                .filter(GroupMember.group_id == id)
+                .scalar()
+            )
+            return count if count else 0
 
     def update_group_by_id(
-        self, id: str, form_data: GroupUpdateForm, overwrite: bool = False
+        self,
+        id: str,
+        form_data: GroupUpdateForm,
+        overwrite: bool = False,
+        db: Optional[Session] = None,
     ) -> Optional[GroupModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Group).filter_by(id=id).update(
                     {
                         **form_data.model_dump(exclude_none=True),
@@ -168,22 +384,22 @@ class GroupTable:
                     }
                 )
                 db.commit()
-                return self.get_group_by_id(id=id)
+                return self.get_group_by_id(id=id, db=db)
         except Exception as e:
             log.exception(e)
             return None
 
-    def delete_group_by_id(self, id: str) -> bool:
+    def delete_group_by_id(self, id: str, db: Optional[Session] = None) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Group).filter_by(id=id).delete()
                 db.commit()
                 return True
         except Exception:
             return False
 
-    def delete_all_groups(self) -> bool:
-        with get_db() as db:
+    def delete_all_groups(self, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             try:
                 db.query(Group).delete()
                 db.commit()
@@ -192,36 +408,47 @@ class GroupTable:
             except Exception:
                 return False
 
-    def remove_user_from_all_groups(self, user_id: str) -> bool:
-        with get_db() as db:
+    def remove_user_from_all_groups(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> bool:
+        with get_db_context(db) as db:
             try:
-                groups = self.get_groups_by_member_id(user_id)
+                # Find all groups the user belongs to
+                groups = (
+                    db.query(Group)
+                    .join(GroupMember, GroupMember.group_id == Group.id)
+                    .filter(GroupMember.user_id == user_id)
+                    .all()
+                )
 
+                # Remove the user from each group
                 for group in groups:
-                    group.user_ids.remove(user_id)
-                    db.query(Group).filter_by(id=group.id).update(
-                        {
-                            "user_ids": group.user_ids,
-                            "updated_at": int(time.time()),
-                        }
-                    )
-                    db.commit()
+                    db.query(GroupMember).filter(
+                        GroupMember.group_id == group.id, GroupMember.user_id == user_id
+                    ).delete()
 
+                    db.query(Group).filter_by(id=group.id).update(
+                        {"updated_at": int(time.time())}
+                    )
+
+                db.commit()
                 return True
+
             except Exception:
+                db.rollback()
                 return False
 
     def create_groups_by_group_names(
-        self, user_id: str, group_names: list[str]
+        self, user_id: str, group_names: list[str], db: Optional[Session] = None
     ) -> list[GroupModel]:
 
         # check for existing groups
-        existing_groups = self.get_groups()
+        existing_groups = self.get_all_groups(db=db)
         existing_group_names = {group.name for group in existing_groups}
 
         new_groups = []
 
-        with get_db() as db:
+        with get_db_context(db) as db:
             for group_name in group_names:
                 if group_name not in existing_group_names:
                     new_group = GroupModel(
@@ -243,96 +470,137 @@ class GroupTable:
                         continue
             return new_groups
 
-    def sync_groups_by_group_names(self, user_id: str, group_names: list[str]) -> bool:
-        with get_db() as db:
+    def sync_groups_by_group_names(
+        self, user_id: str, group_names: list[str], db: Optional[Session] = None
+    ) -> bool:
+        with get_db_context(db) as db:
             try:
-                groups = db.query(Group).filter(Group.name.in_(group_names)).all()
-                group_ids = [group.id for group in groups]
+                now = int(time.time())
 
-                # Remove user from groups not in the new list
-                existing_groups = self.get_groups_by_member_id(user_id)
+                # 1. Groups that SHOULD contain the user
+                target_groups = (
+                    db.query(Group).filter(Group.name.in_(group_names)).all()
+                )
+                target_group_ids = {g.id for g in target_groups}
 
-                for group in existing_groups:
-                    if group.id not in group_ids:
-                        group.user_ids.remove(user_id)
-                        db.query(Group).filter_by(id=group.id).update(
-                            {
-                                "user_ids": group.user_ids,
-                                "updated_at": int(time.time()),
-                            }
+                # 2. Groups the user is CURRENTLY in
+                existing_group_ids = {
+                    g.id
+                    for g in db.query(Group)
+                    .join(GroupMember, GroupMember.group_id == Group.id)
+                    .filter(GroupMember.user_id == user_id)
+                    .all()
+                }
+
+                # 3. Determine adds + removals
+                groups_to_add = target_group_ids - existing_group_ids
+                groups_to_remove = existing_group_ids - target_group_ids
+
+                # 4. Remove in one bulk delete
+                if groups_to_remove:
+                    db.query(GroupMember).filter(
+                        GroupMember.user_id == user_id,
+                        GroupMember.group_id.in_(groups_to_remove),
+                    ).delete(synchronize_session=False)
+
+                    db.query(Group).filter(Group.id.in_(groups_to_remove)).update(
+                        {"updated_at": now}, synchronize_session=False
+                    )
+
+                # 5. Bulk insert missing memberships
+                for group_id in groups_to_add:
+                    db.add(
+                        GroupMember(
+                            id=str(uuid.uuid4()),
+                            group_id=group_id,
+                            user_id=user_id,
+                            created_at=now,
+                            updated_at=now,
                         )
+                    )
 
-                # Add user to new groups
-                for group in groups:
-                    if user_id not in group.user_ids:
-                        group.user_ids.append(user_id)
-                        db.query(Group).filter_by(id=group.id).update(
-                            {
-                                "user_ids": group.user_ids,
-                                "updated_at": int(time.time()),
-                            }
-                        )
+                if groups_to_add:
+                    db.query(Group).filter(Group.id.in_(groups_to_add)).update(
+                        {"updated_at": now}, synchronize_session=False
+                    )
 
                 db.commit()
                 return True
+
             except Exception as e:
                 log.exception(e)
+                db.rollback()
                 return False
 
     def add_users_to_group(
-        self, id: str, user_ids: Optional[list[str]] = None
+        self,
+        id: str,
+        user_ids: Optional[list[str]] = None,
+        db: Optional[Session] = None,
     ) -> Optional[GroupModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 group = db.query(Group).filter_by(id=id).first()
                 if not group:
                     return None
 
-                group_user_ids = group.user_ids
-                if not group_user_ids or not isinstance(group_user_ids, list):
-                    group_user_ids = []
+                now = int(time.time())
 
-                group_user_ids = list(set(group_user_ids))  # Deduplicate
+                for user_id in user_ids or []:
+                    try:
+                        db.add(
+                            GroupMember(
+                                id=str(uuid.uuid4()),
+                                group_id=id,
+                                user_id=user_id,
+                                created_at=now,
+                                updated_at=now,
+                            )
+                        )
+                        db.flush()  # Detect unique constraint violation early
+                    except Exception:
+                        db.rollback()  # Clear failed INSERT
+                        db.begin()  # Start a new transaction
+                        continue  # Duplicate → ignore
 
-                for user_id in user_ids:
-                    if user_id not in group_user_ids:
-                        group_user_ids.append(user_id)
-
-                group.user_ids = group_user_ids
-                group.updated_at = int(time.time())
+                group.updated_at = now
                 db.commit()
                 db.refresh(group)
+
                 return GroupModel.model_validate(group)
+
         except Exception as e:
             log.exception(e)
             return None
 
     def remove_users_from_group(
-        self, id: str, user_ids: Optional[list[str]] = None
+        self,
+        id: str,
+        user_ids: Optional[list[str]] = None,
+        db: Optional[Session] = None,
     ) -> Optional[GroupModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 group = db.query(Group).filter_by(id=id).first()
                 if not group:
                     return None
 
-                group_user_ids = group.user_ids
-
-                if not group_user_ids or not isinstance(group_user_ids, list):
+                if not user_ids:
                     return GroupModel.model_validate(group)
 
-                group_user_ids = list(set(group_user_ids))  # Deduplicate
-
+                # Remove each user from group_member
                 for user_id in user_ids:
-                    if user_id in group_user_ids:
-                        group_user_ids.remove(user_id)
+                    db.query(GroupMember).filter(
+                        GroupMember.group_id == id, GroupMember.user_id == user_id
+                    ).delete()
 
-                group.user_ids = group_user_ids
+                # Update group timestamp
                 group.updated_at = int(time.time())
 
                 db.commit()
                 db.refresh(group)
                 return GroupModel.model_validate(group)
+
         except Exception as e:
             log.exception(e)
             return None

backend/open_webui/models/knowledge.py

@@ -4,21 +4,36 @@ import time
 from typing import Optional
 import uuid
 
-from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 
-from open_webui.models.files import FileMetadataResponse
+from open_webui.models.files import (
+    File,
+    FileModel,
+    FileMetadataResponse,
+    FileModelResponse,
+)
 from open_webui.models.groups import Groups
-from open_webui.models.users import Users, UserResponse
+from open_webui.models.users import User, UserModel, Users, UserResponse
 
 
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text, JSON
+from sqlalchemy import (
+    BigInteger,
+    Column,
+    ForeignKey,
+    String,
+    Text,
+    JSON,
+    UniqueConstraint,
+    or_,
+)
 
 from open_webui.utils.access_control import has_access
+from open_webui.utils.db.access_control import has_permission
+
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 ####################
 # Knowledge DB Schema
@@ -34,9 +49,7 @@ class Knowledge(Base):
     name = Column(Text)
     description = Column(Text)
 
-    data = Column(JSON, nullable=True)
     meta = Column(JSON, nullable=True)
-
     access_control = Column(JSON, nullable=True)  # Controls data access levels.
     # Defines access control rules for this entry.
     # - `None`: Public access, available to all users with the "user" role.
@@ -67,7 +80,6 @@ class KnowledgeModel(BaseModel):
     name: str
     description: str
 
-    data: Optional[dict] = None
     meta: Optional[dict] = None
 
     access_control: Optional[dict] = None
@@ -76,11 +88,42 @@ class KnowledgeModel(BaseModel):
     updated_at: int  # timestamp in epoch
 
 
+class KnowledgeFile(Base):
+    __tablename__ = "knowledge_file"
+
+    id = Column(Text, unique=True, primary_key=True)
+
+    knowledge_id = Column(
+        Text, ForeignKey("knowledge.id", ondelete="CASCADE"), nullable=False
+    )
+    file_id = Column(Text, ForeignKey("file.id", ondelete="CASCADE"), nullable=False)
+    user_id = Column(Text, nullable=False)
+
+    created_at = Column(BigInteger, nullable=False)
+    updated_at = Column(BigInteger, nullable=False)
+
+    __table_args__ = (
+        UniqueConstraint(
+            "knowledge_id", "file_id", name="uq_knowledge_file_knowledge_file"
+        ),
+    )
+
+
+class KnowledgeFileModel(BaseModel):
+    id: str
+    knowledge_id: str
+    file_id: str
+    user_id: str
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+    model_config = ConfigDict(from_attributes=True)
+
+
 ####################
 # Forms
 ####################
-
-
 class KnowledgeUserModel(KnowledgeModel):
     user: Optional[UserResponse] = None
 
@@ -90,21 +133,34 @@ class KnowledgeResponse(KnowledgeModel):
 
 
 class KnowledgeUserResponse(KnowledgeUserModel):
-    files: Optional[list[FileMetadataResponse | dict]] = None
+    pass
 
 
 class KnowledgeForm(BaseModel):
     name: str
     description: str
-    data: Optional[dict] = None
     access_control: Optional[dict] = None
 
 
+class FileUserResponse(FileModelResponse):
+    user: Optional[UserResponse] = None
+
+
+class KnowledgeListResponse(BaseModel):
+    items: list[KnowledgeUserModel]
+    total: int
+
+
+class KnowledgeFileListResponse(BaseModel):
+    items: list[FileUserResponse]
+    total: int
+
+
 class KnowledgeTable:
     def insert_new_knowledge(
-        self, user_id: str, form_data: KnowledgeForm
+        self, user_id: str, form_data: KnowledgeForm, db: Optional[Session] = None
     ) -> Optional[KnowledgeModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             knowledge = KnowledgeModel(
                 **{
                     **form_data.model_dump(),
@@ -127,15 +183,16 @@ class KnowledgeTable:
             except Exception:
                 return None
 
-    def get_knowledge_bases(self) -> list[KnowledgeUserModel]:
-        with get_db() as db:
+    def get_knowledge_bases(
+        self, skip: int = 0, limit: int = 30, db: Optional[Session] = None
+    ) -> list[KnowledgeUserModel]:
+        with get_db_context(db) as db:
             all_knowledge = (
                 db.query(Knowledge).order_by(Knowledge.updated_at.desc()).all()
             )
-
             user_ids = list(set(knowledge.user_id for knowledge in all_knowledge))
 
-            users = Users.get_users_by_user_ids(user_ids) if user_ids else []
+            users = Users.get_users_by_user_ids(user_ids, db=db) if user_ids else []
             users_dict = {user.id: user for user in users}
 
             knowledge_bases = []
@@ -151,20 +208,154 @@ class KnowledgeTable:
                 )
             return knowledge_bases
 
-    def check_access_by_user_id(self, id, user_id, permission="write") -> bool:
-        knowledge = self.get_knowledge_by_id(id)
+    def search_knowledge_bases(
+        self,
+        user_id: str,
+        filter: dict,
+        skip: int = 0,
+        limit: int = 30,
+        db: Optional[Session] = None,
+    ) -> KnowledgeListResponse:
+        try:
+            with get_db_context(db) as db:
+                query = db.query(Knowledge, User).outerjoin(
+                    User, User.id == Knowledge.user_id
+                )
+
+                if filter:
+                    query_key = filter.get("query")
+                    if query_key:
+                        query = query.filter(
+                            or_(
+                                Knowledge.name.ilike(f"%{query_key}%"),
+                                Knowledge.description.ilike(f"%{query_key}%"),
+                            )
+                        )
+
+                    view_option = filter.get("view_option")
+                    if view_option == "created":
+                        query = query.filter(Knowledge.user_id == user_id)
+                    elif view_option == "shared":
+                        query = query.filter(Knowledge.user_id != user_id)
+
+                    query = has_permission(db, Knowledge, query, filter)
+
+                query = query.order_by(Knowledge.updated_at.desc())
+
+                total = query.count()
+                if skip:
+                    query = query.offset(skip)
+                if limit:
+                    query = query.limit(limit)
+
+                items = query.all()
+
+                knowledge_bases = []
+                for knowledge_base, user in items:
+                    knowledge_bases.append(
+                        KnowledgeUserModel.model_validate(
+                            {
+                                **KnowledgeModel.model_validate(
+                                    knowledge_base
+                                ).model_dump(),
+                                "user": (
+                                    UserModel.model_validate(user).model_dump()
+                                    if user
+                                    else None
+                                ),
+                            }
+                        )
+                    )
+
+                return KnowledgeListResponse(items=knowledge_bases, total=total)
+        except Exception as e:
+            print(e)
+            return KnowledgeListResponse(items=[], total=0)
+
+    def search_knowledge_files(
+        self, filter: dict, skip: int = 0, limit: int = 30, db: Optional[Session] = None
+    ) -> KnowledgeFileListResponse:
+        """
+        Scalable version: search files across all knowledge bases the user has
+        READ access to, without loading all KBs or using large IN() lists.
+        """
+        try:
+            with get_db_context(db) as db:
+                # Base query: join Knowledge → KnowledgeFile → File
+                query = (
+                    db.query(File, User, Knowledge)
+                    .join(KnowledgeFile, File.id == KnowledgeFile.file_id)
+                    .join(Knowledge, KnowledgeFile.knowledge_id == Knowledge.id)
+                    .outerjoin(User, User.id == KnowledgeFile.user_id)
+                )
+
+                # Apply access-control directly to the joined query
+                # This makes the database handle filtering, even with 10k+ KBs
+                query = has_permission(db, Knowledge, query, filter)
+
+                # Apply filename search
+                if filter:
+                    q = filter.get("query")
+                    if q:
+                        query = query.filter(File.filename.ilike(f"%{q}%"))
+
+                # Order by file changes
+                query = query.order_by(File.updated_at.desc())
+
+                # Count before pagination
+                total = query.count()
+
+                if skip:
+                    query = query.offset(skip)
+                if limit:
+                    query = query.limit(limit)
+
+                rows = query.all()
+
+                items = []
+                for file, user, knowledge in rows:
+                    items.append(
+                        FileUserResponse(
+                            **FileModel.model_validate(file).model_dump(),
+                            user=(
+                                UserResponse(
+                                    **UserModel.model_validate(user).model_dump()
+                                )
+                                if user
+                                else None
+                            ),
+                            collection=KnowledgeModel.model_validate(
+                                knowledge
+                            ).model_dump(),
+                        )
+                    )
+
+                return KnowledgeFileListResponse(items=items, total=total)
+
+        except Exception as e:
+            print("search_knowledge_files error:", e)
+            return KnowledgeFileListResponse(items=[], total=0)
+
+    def check_access_by_user_id(
+        self, id, user_id, permission="write", db: Optional[Session] = None
+    ) -> bool:
+        knowledge = self.get_knowledge_by_id(id, db=db)
         if not knowledge:
             return False
         if knowledge.user_id == user_id:
             return True
-        user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user_id)}
+        user_group_ids = {
+            group.id for group in Groups.get_groups_by_member_id(user_id, db=db)
+        }
         return has_access(user_id, permission, knowledge.access_control, user_group_ids)
 
     def get_knowledge_bases_by_user_id(
-        self, user_id: str, permission: str = "write"
+        self, user_id: str, permission: str = "write", db: Optional[Session] = None
     ) -> list[KnowledgeUserModel]:
-        knowledge_bases = self.get_knowledge_bases()
-        user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user_id)}
+        knowledge_bases = self.get_knowledge_bases(db=db)
+        user_group_ids = {
+            group.id for group in Groups.get_groups_by_member_id(user_id, db=db)
+        }
         return [
             knowledge_base
             for knowledge_base in knowledge_bases
@@ -174,20 +365,234 @@ class KnowledgeTable:
             )
         ]
 
-    def get_knowledge_by_id(self, id: str) -> Optional[KnowledgeModel]:
+    def get_knowledge_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[KnowledgeModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 knowledge = db.query(Knowledge).filter_by(id=id).first()
                 return KnowledgeModel.model_validate(knowledge) if knowledge else None
         except Exception:
             return None
 
-    def update_knowledge_by_id(
-        self, id: str, form_data: KnowledgeForm, overwrite: bool = False
+    def get_knowledge_by_id_and_user_id(
+        self, id: str, user_id: str, db: Optional[Session] = None
+    ) -> Optional[KnowledgeModel]:
+        knowledge = self.get_knowledge_by_id(id, db=db)
+        if not knowledge:
+            return None
+
+        if knowledge.user_id == user_id:
+            return knowledge
+
+        user_group_ids = {
+            group.id for group in Groups.get_groups_by_member_id(user_id, db=db)
+        }
+        if has_access(user_id, "write", knowledge.access_control, user_group_ids):
+            return knowledge
+        return None
+
+    def get_knowledges_by_file_id(
+        self, file_id: str, db: Optional[Session] = None
+    ) -> list[KnowledgeModel]:
+        try:
+            with get_db_context(db) as db:
+                knowledges = (
+                    db.query(Knowledge)
+                    .join(KnowledgeFile, Knowledge.id == KnowledgeFile.knowledge_id)
+                    .filter(KnowledgeFile.file_id == file_id)
+                    .all()
+                )
+                return [
+                    KnowledgeModel.model_validate(knowledge) for knowledge in knowledges
+                ]
+        except Exception:
+            return []
+
+    def search_files_by_id(
+        self,
+        knowledge_id: str,
+        user_id: str,
+        filter: dict,
+        skip: int = 0,
+        limit: int = 30,
+        db: Optional[Session] = None,
+    ) -> KnowledgeFileListResponse:
+        try:
+            with get_db_context(db) as db:
+                query = (
+                    db.query(File, User)
+                    .join(KnowledgeFile, File.id == KnowledgeFile.file_id)
+                    .outerjoin(User, User.id == KnowledgeFile.user_id)
+                    .filter(KnowledgeFile.knowledge_id == knowledge_id)
+                )
+
+                if filter:
+                    query_key = filter.get("query")
+                    if query_key:
+                        query = query.filter(or_(File.filename.ilike(f"%{query_key}%")))
+
+                    view_option = filter.get("view_option")
+                    if view_option == "created":
+                        query = query.filter(KnowledgeFile.user_id == user_id)
+                    elif view_option == "shared":
+                        query = query.filter(KnowledgeFile.user_id != user_id)
+
+                    order_by = filter.get("order_by")
+                    direction = filter.get("direction")
+
+                    if order_by == "name":
+                        if direction == "asc":
+                            query = query.order_by(File.filename.asc())
+                        else:
+                            query = query.order_by(File.filename.desc())
+                    elif order_by == "created_at":
+                        if direction == "asc":
+                            query = query.order_by(File.created_at.asc())
+                        else:
+                            query = query.order_by(File.created_at.desc())
+                    elif order_by == "updated_at":
+                        if direction == "asc":
+                            query = query.order_by(File.updated_at.asc())
+                        else:
+                            query = query.order_by(File.updated_at.desc())
+                    else:
+                        query = query.order_by(File.updated_at.desc())
+
+                else:
+                    query = query.order_by(File.updated_at.desc())
+
+                # Count BEFORE pagination
+                total = query.count()
+
+                if skip:
+                    query = query.offset(skip)
+                if limit:
+                    query = query.limit(limit)
+
+                items = query.all()
+
+                files = []
+                for file, user in items:
+                    files.append(
+                        FileUserResponse(
+                            **FileModel.model_validate(file).model_dump(),
+                            user=(
+                                UserResponse(
+                                    **UserModel.model_validate(user).model_dump()
+                                )
+                                if user
+                                else None
+                            ),
+                        )
+                    )
+
+                return KnowledgeFileListResponse(items=files, total=total)
+        except Exception as e:
+            print(e)
+            return KnowledgeFileListResponse(items=[], total=0)
+
+    def get_files_by_id(
+        self, knowledge_id: str, db: Optional[Session] = None
+    ) -> list[FileModel]:
+        try:
+            with get_db_context(db) as db:
+                files = (
+                    db.query(File)
+                    .join(KnowledgeFile, File.id == KnowledgeFile.file_id)
+                    .filter(KnowledgeFile.knowledge_id == knowledge_id)
+                    .all()
+                )
+                return [FileModel.model_validate(file) for file in files]
+        except Exception:
+            return []
+
+    def get_file_metadatas_by_id(
+        self, knowledge_id: str, db: Optional[Session] = None
+    ) -> list[FileMetadataResponse]:
+        try:
+            with get_db_context(db) as db:
+                files = self.get_files_by_id(knowledge_id, db=db)
+                return [FileMetadataResponse(**file.model_dump()) for file in files]
+        except Exception:
+            return []
+
+    def add_file_to_knowledge_by_id(
+        self,
+        knowledge_id: str,
+        file_id: str,
+        user_id: str,
+        db: Optional[Session] = None,
+    ) -> Optional[KnowledgeFileModel]:
+        with get_db_context(db) as db:
+            knowledge_file = KnowledgeFileModel(
+                **{
+                    "id": str(uuid.uuid4()),
+                    "knowledge_id": knowledge_id,
+                    "file_id": file_id,
+                    "user_id": user_id,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            try:
+                result = KnowledgeFile(**knowledge_file.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return KnowledgeFileModel.model_validate(result)
+                else:
+                    return None
+            except Exception:
+                return None
+
+    def remove_file_from_knowledge_by_id(
+        self, knowledge_id: str, file_id: str, db: Optional[Session] = None
+    ) -> bool:
+        try:
+            with get_db_context(db) as db:
+                db.query(KnowledgeFile).filter_by(
+                    knowledge_id=knowledge_id, file_id=file_id
+                ).delete()
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def reset_knowledge_by_id(
+        self, id: str, db: Optional[Session] = None
     ) -> Optional[KnowledgeModel]:
         try:
-            with get_db() as db:
-                knowledge = self.get_knowledge_by_id(id=id)
+            with get_db_context(db) as db:
+                # Delete all knowledge_file entries for this knowledge_id
+                db.query(KnowledgeFile).filter_by(knowledge_id=id).delete()
+                db.commit()
+
+                # Update the knowledge entry's updated_at timestamp
+                db.query(Knowledge).filter_by(id=id).update(
+                    {
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+
+                return self.get_knowledge_by_id(id=id, db=db)
+        except Exception as e:
+            log.exception(e)
+            return None
+
+    def update_knowledge_by_id(
+        self,
+        id: str,
+        form_data: KnowledgeForm,
+        overwrite: bool = False,
+        db: Optional[Session] = None,
+    ) -> Optional[KnowledgeModel]:
+        try:
+            with get_db_context(db) as db:
+                knowledge = self.get_knowledge_by_id(id=id, db=db)
                 db.query(Knowledge).filter_by(id=id).update(
                     {
                         **form_data.model_dump(),
@@ -195,17 +600,17 @@ class KnowledgeTable:
                     }
                 )
                 db.commit()
-                return self.get_knowledge_by_id(id=id)
+                return self.get_knowledge_by_id(id=id, db=db)
         except Exception as e:
             log.exception(e)
             return None
 
     def update_knowledge_data_by_id(
-        self, id: str, data: dict
+        self, id: str, data: dict, db: Optional[Session] = None
     ) -> Optional[KnowledgeModel]:
         try:
-            with get_db() as db:
-                knowledge = self.get_knowledge_by_id(id=id)
+            with get_db_context(db) as db:
+                knowledge = self.get_knowledge_by_id(id=id, db=db)
                 db.query(Knowledge).filter_by(id=id).update(
                     {
                         "data": data,
@@ -213,22 +618,22 @@ class KnowledgeTable:
                     }
                 )
                 db.commit()
-                return self.get_knowledge_by_id(id=id)
+                return self.get_knowledge_by_id(id=id, db=db)
         except Exception as e:
             log.exception(e)
             return None
 
-    def delete_knowledge_by_id(self, id: str) -> bool:
+    def delete_knowledge_by_id(self, id: str, db: Optional[Session] = None) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Knowledge).filter_by(id=id).delete()
                 db.commit()
                 return True
         except Exception:
             return False
 
-    def delete_all_knowledge(self) -> bool:
-        with get_db() as db:
+    def delete_all_knowledge(self, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             try:
                 db.query(Knowledge).delete()
                 db.commit()

backend/open_webui/models/memories.py

@@ -2,7 +2,8 @@ import time
 import uuid
 from typing import Optional
 
-from open_webui.internal.db import Base, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, get_db, get_db_context
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text
 
@@ -14,7 +15,7 @@ from sqlalchemy import BigInteger, Column, String, Text
 class Memory(Base):
     __tablename__ = "memory"
 
-    id = Column(String, primary_key=True)
+    id = Column(String, primary_key=True, unique=True)
     user_id = Column(String)
     content = Column(Text)
     updated_at = Column(BigInteger)
@@ -41,8 +42,9 @@ class MemoriesTable:
         self,
         user_id: str,
         content: str,
+        db: Optional[Session] = None,
     ) -> Optional[MemoryModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             id = str(uuid.uuid4())
 
             memory = MemoryModel(
@@ -68,8 +70,9 @@ class MemoriesTable:
         id: str,
         user_id: str,
         content: str,
+        db: Optional[Session] = None,
     ) -> Optional[MemoryModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             try:
                 memory = db.get(Memory, id)
                 if not memory or memory.user_id != user_id:
@@ -83,32 +86,36 @@ class MemoriesTable:
             except Exception:
                 return None
 
-    def get_memories(self) -> list[MemoryModel]:
-        with get_db() as db:
+    def get_memories(self, db: Optional[Session] = None) -> list[MemoryModel]:
+        with get_db_context(db) as db:
             try:
                 memories = db.query(Memory).all()
                 return [MemoryModel.model_validate(memory) for memory in memories]
             except Exception:
                 return None
 
-    def get_memories_by_user_id(self, user_id: str) -> list[MemoryModel]:
-        with get_db() as db:
+    def get_memories_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> list[MemoryModel]:
+        with get_db_context(db) as db:
             try:
                 memories = db.query(Memory).filter_by(user_id=user_id).all()
                 return [MemoryModel.model_validate(memory) for memory in memories]
             except Exception:
                 return None
 
-    def get_memory_by_id(self, id: str) -> Optional[MemoryModel]:
-        with get_db() as db:
+    def get_memory_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[MemoryModel]:
+        with get_db_context(db) as db:
             try:
                 memory = db.get(Memory, id)
                 return MemoryModel.model_validate(memory)
             except Exception:
                 return None
 
-    def delete_memory_by_id(self, id: str) -> bool:
-        with get_db() as db:
+    def delete_memory_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             try:
                 db.query(Memory).filter_by(id=id).delete()
                 db.commit()
@@ -118,8 +125,10 @@ class MemoriesTable:
             except Exception:
                 return False
 
-    def delete_memories_by_user_id(self, user_id: str) -> bool:
-        with get_db() as db:
+    def delete_memories_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> bool:
+        with get_db_context(db) as db:
             try:
                 db.query(Memory).filter_by(user_id=user_id).delete()
                 db.commit()
@@ -128,8 +137,10 @@ class MemoriesTable:
             except Exception:
                 return False
 
-    def delete_memory_by_id_and_user_id(self, id: str, user_id: str) -> bool:
-        with get_db() as db:
+    def delete_memory_by_id_and_user_id(
+        self, id: str, user_id: str, db: Optional[Session] = None
+    ) -> bool:
+        with get_db_context(db) as db:
             try:
                 memory = db.get(Memory, id)
                 if not memory or memory.user_id != user_id:

backend/open_webui/models/messages.py

@@ -3,12 +3,14 @@ import time
 import uuid
 from typing import Optional
 
-from open_webui.internal.db import Base, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 from open_webui.models.tags import TagModel, Tag, Tags
-from open_webui.models.users import Users, UserNameResponse
+from open_webui.models.users import Users, User, UserNameResponse
+from open_webui.models.channels import Channels, ChannelMember
 
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, field_validator
 from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
 from sqlalchemy import or_, func, select, and_, text
 from sqlalchemy.sql import exists
@@ -20,7 +22,7 @@ from sqlalchemy.sql import exists
 
 class MessageReaction(Base):
     __tablename__ = "message_reaction"
-    id = Column(Text, primary_key=True)
+    id = Column(Text, primary_key=True, unique=True)
     user_id = Column(Text)
     message_id = Column(Text)
     name = Column(Text)
@@ -39,7 +41,7 @@ class MessageReactionModel(BaseModel):
 
 class Message(Base):
     __tablename__ = "message"
-    id = Column(Text, primary_key=True)
+    id = Column(Text, primary_key=True, unique=True)
 
     user_id = Column(Text)
     channel_id = Column(Text, nullable=True)
@@ -47,6 +49,11 @@ class Message(Base):
     reply_to_id = Column(Text, nullable=True)
     parent_id = Column(Text, nullable=True)
 
+    # Pins
+    is_pinned = Column(Boolean, nullable=False, default=False)
+    pinned_at = Column(BigInteger, nullable=True)
+    pinned_by = Column(Text, nullable=True)
+
     content = Column(Text)
     data = Column(JSON, nullable=True)
     meta = Column(JSON, nullable=True)
@@ -65,12 +72,17 @@ class MessageModel(BaseModel):
     reply_to_id: Optional[str] = None
     parent_id: Optional[str] = None
 
+    # Pins
+    is_pinned: bool = False
+    pinned_by: Optional[str] = None
+    pinned_at: Optional[int] = None  # timestamp in epoch (time_ns)
+
     content: str
     data: Optional[dict] = None
     meta: Optional[dict] = None
 
-    created_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
+    created_at: int  # timestamp in epoch (time_ns)
+    updated_at: int  # timestamp in epoch (time_ns)
 
 
 ####################
@@ -79,6 +91,7 @@ class MessageModel(BaseModel):
 
 
 class MessageForm(BaseModel):
+    temp_id: Optional[str] = None
     content: str
     reply_to_id: Optional[str] = None
     parent_id: Optional[str] = None
@@ -88,7 +101,7 @@ class MessageForm(BaseModel):
 
 class Reactions(BaseModel):
     name: str
-    user_ids: list[str]
+    users: list[dict]
     count: int
 
 
@@ -96,8 +109,25 @@ class MessageUserResponse(MessageModel):
     user: Optional[UserNameResponse] = None
 
 
+class MessageUserSlimResponse(MessageUserResponse):
+    data: bool | None = None
+
+    @field_validator("data", mode="before")
+    def convert_data_to_bool(cls, v):
+        # No data or not a dict → False
+        if not isinstance(v, dict):
+            return False
+
+        # True if ANY value in the dict is non-empty
+        return any(bool(val) for val in v.values())
+
+
 class MessageReplyToResponse(MessageUserResponse):
-    reply_to_message: Optional[MessageUserResponse] = None
+    reply_to_message: Optional[MessageUserSlimResponse] = None
+
+
+class MessageWithReactionsResponse(MessageUserSlimResponse):
+    reactions: list[Reactions]
 
 
 class MessageResponse(MessageReplyToResponse):
@@ -108,12 +138,18 @@ class MessageResponse(MessageReplyToResponse):
 
 class MessageTable:
     def insert_new_message(
-        self, form_data: MessageForm, channel_id: str, user_id: str
+        self,
+        form_data: MessageForm,
+        channel_id: str,
+        user_id: str,
+        db: Optional[Session] = None,
     ) -> Optional[MessageModel]:
-        with get_db() as db:
-            id = str(uuid.uuid4())
+        with get_db_context(db) as db:
+            channel_member = Channels.join_channel(channel_id, user_id)
 
+            id = str(uuid.uuid4())
             ts = int(time.time_ns())
+
             message = MessageModel(
                 **{
                     "id": id,
@@ -121,6 +157,9 @@ class MessageTable:
                     "channel_id": channel_id,
                     "reply_to_id": form_data.reply_to_id,
                     "parent_id": form_data.parent_id,
+                    "is_pinned": False,
+                    "pinned_at": None,
+                    "pinned_by": None,
                     "content": form_data.content,
                     "data": form_data.data,
                     "meta": form_data.meta,
@@ -128,33 +167,64 @@ class MessageTable:
                     "updated_at": ts,
                 }
             )
-
             result = Message(**message.model_dump())
+
             db.add(result)
             db.commit()
             db.refresh(result)
             return MessageModel.model_validate(result) if result else None
 
-    def get_message_by_id(self, id: str) -> Optional[MessageResponse]:
-        with get_db() as db:
+    def get_message_by_id(
+        self,
+        id: str,
+        include_thread_replies: Optional[bool] = True,
+        db: Optional[Session] = None,
+    ) -> Optional[MessageResponse]:
+        with get_db_context(db) as db:
             message = db.get(Message, id)
             if not message:
                 return None
 
             reply_to_message = (
-                self.get_message_by_id(message.reply_to_id)
+                self.get_message_by_id(
+                    message.reply_to_id, include_thread_replies=False, db=db
+                )
                 if message.reply_to_id
                 else None
             )
 
-            reactions = self.get_reactions_by_message_id(id)
-            thread_replies = self.get_thread_replies_by_message_id(id)
+            reactions = self.get_reactions_by_message_id(id, db=db)
+
+            thread_replies = []
+            if include_thread_replies:
+                thread_replies = self.get_thread_replies_by_message_id(id, db=db)
+
+            # Check if message was sent by webhook (webhook info in meta takes precedence)
+            webhook_info = message.meta.get("webhook") if message.meta else None
+            if webhook_info and webhook_info.get("id"):
+                # Look up webhook by ID to get current name
+                webhook = Channels.get_webhook_by_id(webhook_info.get("id"), db=db)
+                if webhook:
+                    user_info = {
+                        "id": webhook.id,
+                        "name": webhook.name,
+                        "role": "webhook",
+                    }
+                else:
+                    # Webhook was deleted, use placeholder
+                    user_info = {
+                        "id": webhook_info.get("id"),
+                        "name": "Deleted Webhook",
+                        "role": "webhook",
+                    }
+            else:
+                user = Users.get_user_by_id(message.user_id, db=db)
+                user_info = user.model_dump() if user else None
 
-            user = Users.get_user_by_id(message.user_id)
             return MessageResponse.model_validate(
                 {
                     **MessageModel.model_validate(message).model_dump(),
-                    "user": user.model_dump() if user else None,
+                    "user": user_info,
                     "reply_to_message": (
                         reply_to_message.model_dump() if reply_to_message else None
                     ),
@@ -166,8 +236,10 @@ class MessageTable:
                 }
             )
 
-    def get_thread_replies_by_message_id(self, id: str) -> list[MessageReplyToResponse]:
-        with get_db() as db:
+    def get_thread_replies_by_message_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> list[MessageReplyToResponse]:
+        with get_db_context(db) as db:
             all_messages = (
                 db.query(Message)
                 .filter_by(parent_id=id)
@@ -178,14 +250,35 @@ class MessageTable:
             messages = []
             for message in all_messages:
                 reply_to_message = (
-                    self.get_message_by_id(message.reply_to_id)
+                    self.get_message_by_id(
+                        message.reply_to_id, include_thread_replies=False, db=db
+                    )
                     if message.reply_to_id
                     else None
                 )
+
+                webhook_info = message.meta.get("webhook") if message.meta else None
+                user_info = None
+                if webhook_info and webhook_info.get("id"):
+                    webhook = Channels.get_webhook_by_id(webhook_info.get("id"), db=db)
+                    if webhook:
+                        user_info = {
+                            "id": webhook.id,
+                            "name": webhook.name,
+                            "role": "webhook",
+                        }
+                    else:
+                        user_info = {
+                            "id": webhook_info.get("id"),
+                            "name": "Deleted Webhook",
+                            "role": "webhook",
+                        }
+
                 messages.append(
                     MessageReplyToResponse.model_validate(
                         {
                             **MessageModel.model_validate(message).model_dump(),
+                            "user": user_info,
                             "reply_to_message": (
                                 reply_to_message.model_dump()
                                 if reply_to_message
@@ -196,17 +289,23 @@ class MessageTable:
                 )
             return messages
 
-    def get_reply_user_ids_by_message_id(self, id: str) -> list[str]:
-        with get_db() as db:
+    def get_reply_user_ids_by_message_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> list[str]:
+        with get_db_context(db) as db:
             return [
                 message.user_id
                 for message in db.query(Message).filter_by(parent_id=id).all()
             ]
 
     def get_messages_by_channel_id(
-        self, channel_id: str, skip: int = 0, limit: int = 50
+        self,
+        channel_id: str,
+        skip: int = 0,
+        limit: int = 50,
+        db: Optional[Session] = None,
     ) -> list[MessageReplyToResponse]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             all_messages = (
                 db.query(Message)
                 .filter_by(channel_id=channel_id, parent_id=None)
@@ -219,14 +318,35 @@ class MessageTable:
             messages = []
             for message in all_messages:
                 reply_to_message = (
-                    self.get_message_by_id(message.reply_to_id)
+                    self.get_message_by_id(
+                        message.reply_to_id, include_thread_replies=False, db=db
+                    )
                     if message.reply_to_id
                     else None
                 )
+
+                webhook_info = message.meta.get("webhook") if message.meta else None
+                user_info = None
+                if webhook_info and webhook_info.get("id"):
+                    webhook = Channels.get_webhook_by_id(webhook_info.get("id"), db=db)
+                    if webhook:
+                        user_info = {
+                            "id": webhook.id,
+                            "name": webhook.name,
+                            "role": "webhook",
+                        }
+                    else:
+                        user_info = {
+                            "id": webhook_info.get("id"),
+                            "name": "Deleted Webhook",
+                            "role": "webhook",
+                        }
+
                 messages.append(
                     MessageReplyToResponse.model_validate(
                         {
                             **MessageModel.model_validate(message).model_dump(),
+                            "user": user_info,
                             "reply_to_message": (
                                 reply_to_message.model_dump()
                                 if reply_to_message
@@ -238,9 +358,14 @@ class MessageTable:
             return messages
 
     def get_messages_by_parent_id(
-        self, channel_id: str, parent_id: str, skip: int = 0, limit: int = 50
+        self,
+        channel_id: str,
+        parent_id: str,
+        skip: int = 0,
+        limit: int = 50,
+        db: Optional[Session] = None,
     ) -> list[MessageReplyToResponse]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             message = db.get(Message, parent_id)
 
             if not message:
@@ -262,14 +387,35 @@ class MessageTable:
             messages = []
             for message in all_messages:
                 reply_to_message = (
-                    self.get_message_by_id(message.reply_to_id)
+                    self.get_message_by_id(
+                        message.reply_to_id, include_thread_replies=False, db=db
+                    )
                     if message.reply_to_id
                     else None
                 )
+
+                webhook_info = message.meta.get("webhook") if message.meta else None
+                user_info = None
+                if webhook_info and webhook_info.get("id"):
+                    webhook = Channels.get_webhook_by_id(webhook_info.get("id"), db=db)
+                    if webhook:
+                        user_info = {
+                            "id": webhook.id,
+                            "name": webhook.name,
+                            "role": "webhook",
+                        }
+                    else:
+                        user_info = {
+                            "id": webhook_info.get("id"),
+                            "name": "Deleted Webhook",
+                            "role": "webhook",
+                        }
+
                 messages.append(
                     MessageReplyToResponse.model_validate(
                         {
                             **MessageModel.model_validate(message).model_dump(),
+                            "user": user_info,
                             "reply_to_message": (
                                 reply_to_message.model_dump()
                                 if reply_to_message
@@ -280,10 +426,40 @@ class MessageTable:
                 )
             return messages
 
-    def update_message_by_id(
-        self, id: str, form_data: MessageForm
+    def get_last_message_by_channel_id(
+        self, channel_id: str, db: Optional[Session] = None
     ) -> Optional[MessageModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
+            message = (
+                db.query(Message)
+                .filter_by(channel_id=channel_id)
+                .order_by(Message.created_at.desc())
+                .first()
+            )
+            return MessageModel.model_validate(message) if message else None
+
+    def get_pinned_messages_by_channel_id(
+        self,
+        channel_id: str,
+        skip: int = 0,
+        limit: int = 50,
+        db: Optional[Session] = None,
+    ) -> list[MessageModel]:
+        with get_db_context(db) as db:
+            all_messages = (
+                db.query(Message)
+                .filter_by(channel_id=channel_id, is_pinned=True)
+                .order_by(Message.pinned_at.desc())
+                .offset(skip)
+                .limit(limit)
+                .all()
+            )
+            return [MessageModel.model_validate(message) for message in all_messages]
+
+    def update_message_by_id(
+        self, id: str, form_data: MessageForm, db: Optional[Session] = None
+    ) -> Optional[MessageModel]:
+        with get_db_context(db) as db:
             message = db.get(Message, id)
             message.content = form_data.content
             message.data = {
@@ -299,10 +475,52 @@ class MessageTable:
             db.refresh(message)
             return MessageModel.model_validate(message) if message else None
 
+    def update_is_pinned_by_id(
+        self,
+        id: str,
+        is_pinned: bool,
+        pinned_by: Optional[str] = None,
+        db: Optional[Session] = None,
+    ) -> Optional[MessageModel]:
+        with get_db_context(db) as db:
+            message = db.get(Message, id)
+            message.is_pinned = is_pinned
+            message.pinned_at = int(time.time_ns()) if is_pinned else None
+            message.pinned_by = pinned_by if is_pinned else None
+            db.commit()
+            db.refresh(message)
+            return MessageModel.model_validate(message) if message else None
+
+    def get_unread_message_count(
+        self,
+        channel_id: str,
+        user_id: str,
+        last_read_at: Optional[int] = None,
+        db: Optional[Session] = None,
+    ) -> int:
+        with get_db_context(db) as db:
+            query = db.query(Message).filter(
+                Message.channel_id == channel_id,
+                Message.parent_id == None,  # only count top-level messages
+                Message.created_at > (last_read_at if last_read_at else 0),
+            )
+            if user_id:
+                query = query.filter(Message.user_id != user_id)
+            return query.count()
+
     def add_reaction_to_message(
-        self, id: str, user_id: str, name: str
+        self, id: str, user_id: str, name: str, db: Optional[Session] = None
     ) -> Optional[MessageReactionModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
+            # check for existing reaction
+            existing_reaction = (
+                db.query(MessageReaction)
+                .filter_by(message_id=id, user_id=user_id, name=name)
+                .first()
+            )
+            if existing_reaction:
+                return MessageReactionModel.model_validate(existing_reaction)
+
             reaction_id = str(uuid.uuid4())
             reaction = MessageReactionModel(
                 id=reaction_id,
@@ -317,47 +535,62 @@ class MessageTable:
             db.refresh(result)
             return MessageReactionModel.model_validate(result) if result else None
 
-    def get_reactions_by_message_id(self, id: str) -> list[Reactions]:
-        with get_db() as db:
-            all_reactions = db.query(MessageReaction).filter_by(message_id=id).all()
+    def get_reactions_by_message_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> list[Reactions]:
+        with get_db_context(db) as db:
+            # JOIN User so all user info is fetched in one query
+            results = (
+                db.query(MessageReaction, User)
+                .join(User, MessageReaction.user_id == User.id)
+                .filter(MessageReaction.message_id == id)
+                .all()
+            )
 
             reactions = {}
-            for reaction in all_reactions:
+
+            for reaction, user in results:
                 if reaction.name not in reactions:
                     reactions[reaction.name] = {
                         "name": reaction.name,
-                        "user_ids": [],
+                        "users": [],
                         "count": 0,
                     }
-                reactions[reaction.name]["user_ids"].append(reaction.user_id)
+
+                reactions[reaction.name]["users"].append(
+                    {
+                        "id": user.id,
+                        "name": user.name,
+                    }
+                )
                 reactions[reaction.name]["count"] += 1
 
             return [Reactions(**reaction) for reaction in reactions.values()]
 
     def remove_reaction_by_id_and_user_id_and_name(
-        self, id: str, user_id: str, name: str
+        self, id: str, user_id: str, name: str, db: Optional[Session] = None
     ) -> bool:
-        with get_db() as db:
+        with get_db_context(db) as db:
             db.query(MessageReaction).filter_by(
                 message_id=id, user_id=user_id, name=name
             ).delete()
             db.commit()
             return True
 
-    def delete_reactions_by_id(self, id: str) -> bool:
-        with get_db() as db:
+    def delete_reactions_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             db.query(MessageReaction).filter_by(message_id=id).delete()
             db.commit()
             return True
 
-    def delete_replies_by_id(self, id: str) -> bool:
-        with get_db() as db:
+    def delete_replies_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             db.query(Message).filter_by(parent_id=id).delete()
             db.commit()
             return True
 
-    def delete_message_by_id(self, id: str) -> bool:
-        with get_db() as db:
+    def delete_message_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             db.query(Message).filter_by(id=id).delete()
 
             # Delete all reactions to this message
@@ -366,5 +599,35 @@ class MessageTable:
             db.commit()
             return True
 
+    def search_messages_by_channel_ids(
+        self,
+        channel_ids: list[str],
+        query: str,
+        start_timestamp: Optional[int] = None,
+        end_timestamp: Optional[int] = None,
+        limit: int = 10,
+        db: Optional[Session] = None,
+    ) -> list[MessageModel]:
+        """Search messages in specified channels by content."""
+        with get_db_context(db) as db:
+            query_builder = db.query(Message).filter(
+                Message.channel_id.in_(channel_ids),
+                Message.content.ilike(f"%{query}%"),
+            )
+
+            if start_timestamp:
+                query_builder = query_builder.filter(
+                    Message.created_at >= start_timestamp
+                )
+            if end_timestamp:
+                query_builder = query_builder.filter(
+                    Message.created_at <= end_timestamp
+                )
+
+            messages = (
+                query_builder.order_by(Message.created_at.desc()).limit(limit).all()
+            )
+            return [MessageModel.model_validate(msg) for msg in messages]
+
 
 Messages = MessageTable()

backend/open_webui/models/models.py

@@ -2,17 +2,19 @@ import logging
 import time
 from typing import Optional
 
-from open_webui.internal.db import Base, JSONField, get_db
-from open_webui.env import SRC_LOG_LEVELS
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 
 from open_webui.models.groups import Groups
-from open_webui.models.users import Users, UserResponse
+from open_webui.models.users import User, UserModel, Users, UserResponse
 
 
 from pydantic import BaseModel, ConfigDict
 
-from sqlalchemy import or_, and_, func
+from sqlalchemy import String, cast, or_, and_, func
 from sqlalchemy.dialects import postgresql, sqlite
+
+from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy import BigInteger, Column, Text, JSON, Boolean
 
 
@@ -20,7 +22,6 @@ from open_webui.utils.access_control import has_access
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 
 ####################
@@ -53,7 +54,7 @@ class ModelMeta(BaseModel):
 class Model(Base):
     __tablename__ = "model"
 
-    id = Column(Text, primary_key=True)
+    id = Column(Text, primary_key=True, unique=True)
     """
         The model's id as used in the API. If set to an existing model, it will override the model.
     """
@@ -129,10 +130,24 @@ class ModelUserResponse(ModelModel):
     user: Optional[UserResponse] = None
 
 
+class ModelAccessResponse(ModelUserResponse):
+    write_access: Optional[bool] = False
+
+
 class ModelResponse(ModelModel):
     pass
 
 
+class ModelListResponse(BaseModel):
+    items: list[ModelUserResponse]
+    total: int
+
+
+class ModelAccessListResponse(BaseModel):
+    items: list[ModelAccessResponse]
+    total: int
+
+
 class ModelForm(BaseModel):
     id: str
     base_model_id: Optional[str] = None
@@ -145,7 +160,7 @@ class ModelForm(BaseModel):
 
 class ModelsTable:
     def insert_new_model(
-        self, form_data: ModelForm, user_id: str
+        self, form_data: ModelForm, user_id: str, db: Optional[Session] = None
     ) -> Optional[ModelModel]:
         model = ModelModel(
             **{
@@ -156,7 +171,7 @@ class ModelsTable:
             }
         )
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 result = Model(**model.model_dump())
                 db.add(result)
                 db.commit()
@@ -170,17 +185,17 @@ class ModelsTable:
             log.exception(f"Failed to insert a new model: {e}")
             return None
 
-    def get_all_models(self) -> list[ModelModel]:
-        with get_db() as db:
+    def get_all_models(self, db: Optional[Session] = None) -> list[ModelModel]:
+        with get_db_context(db) as db:
             return [ModelModel.model_validate(model) for model in db.query(Model).all()]
 
-    def get_models(self) -> list[ModelUserResponse]:
-        with get_db() as db:
+    def get_models(self, db: Optional[Session] = None) -> list[ModelUserResponse]:
+        with get_db_context(db) as db:
             all_models = db.query(Model).filter(Model.base_model_id != None).all()
 
             user_ids = list(set(model.user_id for model in all_models))
 
-            users = Users.get_users_by_user_ids(user_ids) if user_ids else []
+            users = Users.get_users_by_user_ids(user_ids, db=db) if user_ids else []
             users_dict = {user.id: user for user in users}
 
             models = []
@@ -196,18 +211,20 @@ class ModelsTable:
                 )
             return models
 
-    def get_base_models(self) -> list[ModelModel]:
-        with get_db() as db:
+    def get_base_models(self, db: Optional[Session] = None) -> list[ModelModel]:
+        with get_db_context(db) as db:
             return [
                 ModelModel.model_validate(model)
                 for model in db.query(Model).filter(Model.base_model_id == None).all()
             ]
 
     def get_models_by_user_id(
-        self, user_id: str, permission: str = "write"
+        self, user_id: str, permission: str = "write", db: Optional[Session] = None
     ) -> list[ModelUserResponse]:
-        models = self.get_models()
-        user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user_id)}
+        models = self.get_models(db=db)
+        user_group_ids = {
+            group.id for group in Groups.get_groups_by_member_id(user_id, db=db)
+        }
         return [
             model
             for model in models
@@ -215,16 +232,164 @@ class ModelsTable:
             or has_access(user_id, permission, model.access_control, user_group_ids)
         ]
 
-    def get_model_by_id(self, id: str) -> Optional[ModelModel]:
+    def _has_permission(self, db, query, filter: dict, permission: str = "read"):
+        group_ids = filter.get("group_ids", [])
+        user_id = filter.get("user_id")
+
+        dialect_name = db.bind.dialect.name
+
+        # Public access
+        conditions = []
+        if group_ids or user_id:
+            conditions.extend(
+                [
+                    Model.access_control.is_(None),
+                    cast(Model.access_control, String) == "null",
+                ]
+            )
+
+        # User-level permission
+        if user_id:
+            conditions.append(Model.user_id == user_id)
+
+        # Group-level permission
+        if group_ids:
+            group_conditions = []
+            for gid in group_ids:
+                if dialect_name == "sqlite":
+                    group_conditions.append(
+                        Model.access_control[permission]["group_ids"].contains([gid])
+                    )
+                elif dialect_name == "postgresql":
+                    group_conditions.append(
+                        cast(
+                            Model.access_control[permission]["group_ids"],
+                            JSONB,
+                        ).contains([gid])
+                    )
+            conditions.append(or_(*group_conditions))
+
+        if conditions:
+            query = query.filter(or_(*conditions))
+
+        return query
+
+    def search_models(
+        self,
+        user_id: str,
+        filter: dict = {},
+        skip: int = 0,
+        limit: int = 30,
+        db: Optional[Session] = None,
+    ) -> ModelListResponse:
+        with get_db_context(db) as db:
+            # Join GroupMember so we can order by group_id when requested
+            query = db.query(Model, User).outerjoin(User, User.id == Model.user_id)
+            query = query.filter(Model.base_model_id != None)
+
+            if filter:
+                query_key = filter.get("query")
+                if query_key:
+                    query = query.filter(
+                        or_(
+                            Model.name.ilike(f"%{query_key}%"),
+                            Model.base_model_id.ilike(f"%{query_key}%"),
+                        )
+                    )
+
+                view_option = filter.get("view_option")
+                if view_option == "created":
+                    query = query.filter(Model.user_id == user_id)
+                elif view_option == "shared":
+                    query = query.filter(Model.user_id != user_id)
+
+                # Apply access control filtering
+                query = self._has_permission(
+                    db,
+                    query,
+                    filter,
+                    permission="read",
+                )
+
+                tag = filter.get("tag")
+                if tag:
+                    # TODO: This is a simple implementation and should be improved for performance
+                    like_pattern = f'%"{tag.lower()}"%'  # `"tag"` inside JSON array
+                    meta_text = func.lower(cast(Model.meta, String))
+
+                    query = query.filter(meta_text.like(like_pattern))
+
+                order_by = filter.get("order_by")
+                direction = filter.get("direction")
+
+                if order_by == "name":
+                    if direction == "asc":
+                        query = query.order_by(Model.name.asc())
+                    else:
+                        query = query.order_by(Model.name.desc())
+                elif order_by == "created_at":
+                    if direction == "asc":
+                        query = query.order_by(Model.created_at.asc())
+                    else:
+                        query = query.order_by(Model.created_at.desc())
+                elif order_by == "updated_at":
+                    if direction == "asc":
+                        query = query.order_by(Model.updated_at.asc())
+                    else:
+                        query = query.order_by(Model.updated_at.desc())
+
+            else:
+                query = query.order_by(Model.created_at.desc())
+
+            # Count BEFORE pagination
+            total = query.count()
+
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
+            items = query.all()
+
+            models = []
+            for model, user in items:
+                models.append(
+                    ModelUserResponse(
+                        **ModelModel.model_validate(model).model_dump(),
+                        user=(
+                            UserResponse(**UserModel.model_validate(user).model_dump())
+                            if user
+                            else None
+                        ),
+                    )
+                )
+
+            return ModelListResponse(items=models, total=total)
+
+    def get_model_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[ModelModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 model = db.get(Model, id)
                 return ModelModel.model_validate(model)
         except Exception:
             return None
 
-    def toggle_model_by_id(self, id: str) -> Optional[ModelModel]:
-        with get_db() as db:
+    def get_models_by_ids(
+        self, ids: list[str], db: Optional[Session] = None
+    ) -> list[ModelModel]:
+        try:
+            with get_db_context(db) as db:
+                models = db.query(Model).filter(Model.id.in_(ids)).all()
+                return [ModelModel.model_validate(model) for model in models]
+        except Exception:
+            return []
+
+    def toggle_model_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[ModelModel]:
+        with get_db_context(db) as db:
             try:
                 is_active = db.query(Model).filter_by(id=id).first().is_active
 
@@ -236,19 +401,19 @@ class ModelsTable:
                 )
                 db.commit()
 
-                return self.get_model_by_id(id)
+                return self.get_model_by_id(id, db=db)
             except Exception:
                 return None
 
-    def update_model_by_id(self, id: str, model: ModelForm) -> Optional[ModelModel]:
+    def update_model_by_id(
+        self, id: str, model: ModelForm, db: Optional[Session] = None
+    ) -> Optional[ModelModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 # update only the fields that are present in the model
-                result = (
-                    db.query(Model)
-                    .filter_by(id=id)
-                    .update(model.model_dump(exclude={"id"}))
-                )
+                data = model.model_dump(exclude={"id"})
+                result = db.query(Model).filter_by(id=id).update(data)
+
                 db.commit()
 
                 model = db.get(Model, id)
@@ -258,9 +423,9 @@ class ModelsTable:
             log.exception(f"Failed to update the model by id {id}: {e}")
             return None
 
-    def delete_model_by_id(self, id: str) -> bool:
+    def delete_model_by_id(self, id: str, db: Optional[Session] = None) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Model).filter_by(id=id).delete()
                 db.commit()
 
@@ -268,9 +433,9 @@ class ModelsTable:
         except Exception:
             return False
 
-    def delete_all_models(self) -> bool:
+    def delete_all_models(self, db: Optional[Session] = None) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Model).delete()
                 db.commit()
 
@@ -278,9 +443,11 @@ class ModelsTable:
         except Exception:
             return False
 
-    def sync_models(self, user_id: str, models: list[ModelModel]) -> list[ModelModel]:
+    def sync_models(
+        self, user_id: str, models: list[ModelModel], db: Optional[Session] = None
+    ) -> list[ModelModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 # Get existing models
                 existing_models = db.query(Model).all()
                 existing_ids = {model.id for model in existing_models}

backend/open_webui/models/notes.py

@@ -4,15 +4,19 @@ import uuid
 from typing import Optional
 from functools import lru_cache
 
-from open_webui.internal.db import Base, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, get_db, get_db_context
 from open_webui.models.groups import Groups
 from open_webui.utils.access_control import has_access
-from open_webui.models.users import Users, UserResponse
+from open_webui.models.users import User, UserModel, Users, UserResponse
 
 
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
-from sqlalchemy import or_, func, select, and_, text
+from sqlalchemy.dialects.postgresql import JSONB
+
+
+from sqlalchemy import or_, func, select, and_, text, cast, or_, and_, func
 from sqlalchemy.sql import exists
 
 ####################
@@ -23,7 +27,7 @@ from sqlalchemy.sql import exists
 class Note(Base):
     __tablename__ = "note"
 
-    id = Column(Text, primary_key=True)
+    id = Column(Text, primary_key=True, unique=True)
     user_id = Column(Text)
 
     title = Column(Text)
@@ -75,13 +79,142 @@ class NoteUserResponse(NoteModel):
     user: Optional[UserResponse] = None
 
 
+class NoteItemResponse(BaseModel):
+    id: str
+    title: str
+    data: Optional[dict]
+    updated_at: int
+    created_at: int
+    user: Optional[UserResponse] = None
+
+
+class NoteListResponse(BaseModel):
+    items: list[NoteUserResponse]
+    total: int
+
+
 class NoteTable:
+    def _has_permission(self, db, query, filter: dict, permission: str = "read"):
+        group_ids = filter.get("group_ids", [])
+        user_id = filter.get("user_id")
+        dialect_name = db.bind.dialect.name
+
+        conditions = []
+
+        # Handle read_only permission separately
+        if permission == "read_only":
+            # For read_only, we want items where:
+            # 1. User has explicit read permission (via groups or user-level)
+            # 2. BUT does NOT have write permission
+            # 3. Public items are NOT considered read_only
+
+            read_conditions = []
+
+            # Group-level read permission
+            if group_ids:
+                group_read_conditions = []
+                for gid in group_ids:
+                    if dialect_name == "sqlite":
+                        group_read_conditions.append(
+                            Note.access_control["read"]["group_ids"].contains([gid])
+                        )
+                    elif dialect_name == "postgresql":
+                        group_read_conditions.append(
+                            cast(
+                                Note.access_control["read"]["group_ids"],
+                                JSONB,
+                            ).contains([gid])
+                        )
+
+                if group_read_conditions:
+                    read_conditions.append(or_(*group_read_conditions))
+
+            # Combine read conditions
+            if read_conditions:
+                has_read = or_(*read_conditions)
+            else:
+                # If no read conditions, return empty result
+                return query.filter(False)
+
+            # Now exclude items where user has write permission
+            write_exclusions = []
+
+            # Exclude items owned by user (they have implicit write)
+            if user_id:
+                write_exclusions.append(Note.user_id != user_id)
+
+            # Exclude items where user has explicit write permission via groups
+            if group_ids:
+                group_write_conditions = []
+                for gid in group_ids:
+                    if dialect_name == "sqlite":
+                        group_write_conditions.append(
+                            Note.access_control["write"]["group_ids"].contains([gid])
+                        )
+                    elif dialect_name == "postgresql":
+                        group_write_conditions.append(
+                            cast(
+                                Note.access_control["write"]["group_ids"],
+                                JSONB,
+                            ).contains([gid])
+                        )
+
+                if group_write_conditions:
+                    # User should NOT have write permission
+                    write_exclusions.append(~or_(*group_write_conditions))
+
+            # Exclude public items (items without access_control)
+            write_exclusions.append(Note.access_control.isnot(None))
+            write_exclusions.append(cast(Note.access_control, String) != "null")
+
+            # Combine: has read AND does not have write AND not public
+            if write_exclusions:
+                query = query.filter(and_(has_read, *write_exclusions))
+            else:
+                query = query.filter(has_read)
+
+            return query
+
+        # Original logic for other permissions (read, write, etc.)
+        # Public access conditions
+        if group_ids or user_id:
+            conditions.extend(
+                [
+                    Note.access_control.is_(None),
+                    cast(Note.access_control, String) == "null",
+                ]
+            )
+
+        # User-level permission (owner has all permissions)
+        if user_id:
+            conditions.append(Note.user_id == user_id)
+
+        # Group-level permission
+        if group_ids:
+            group_conditions = []
+            for gid in group_ids:
+                if dialect_name == "sqlite":
+                    group_conditions.append(
+                        Note.access_control[permission]["group_ids"].contains([gid])
+                    )
+                elif dialect_name == "postgresql":
+                    group_conditions.append(
+                        cast(
+                            Note.access_control[permission]["group_ids"],
+                            JSONB,
+                        ).contains([gid])
+                    )
+            conditions.append(or_(*group_conditions))
+
+        if conditions:
+            query = query.filter(or_(*conditions))
+
+        return query
+
     def insert_new_note(
-        self,
-        form_data: NoteForm,
-        user_id: str,
+        self, user_id: str, form_data: NoteForm, db: Optional[Session] = None
     ) -> Optional[NoteModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             note = NoteModel(
                 **{
                     "id": str(uuid.uuid4()),
@@ -99,9 +232,9 @@ class NoteTable:
             return note
 
     def get_notes(
-        self, skip: Optional[int] = None, limit: Optional[int] = None
+        self, skip: int = 0, limit: int = 50, db: Optional[Session] = None
     ) -> list[NoteModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             query = db.query(Note).order_by(Note.updated_at.desc())
             if skip is not None:
                 query = query.offset(skip)
@@ -110,15 +243,121 @@ class NoteTable:
             notes = query.all()
             return [NoteModel.model_validate(note) for note in notes]
 
+    def search_notes(
+        self,
+        user_id: str,
+        filter: dict = {},
+        skip: int = 0,
+        limit: int = 30,
+        db: Optional[Session] = None,
+    ) -> NoteListResponse:
+        with get_db_context(db) as db:
+            query = db.query(Note, User).outerjoin(User, User.id == Note.user_id)
+            if filter:
+                query_key = filter.get("query")
+                if query_key:
+                    # Normalize search by removing hyphens and spaces (e.g., "todo" matches "to-do" and "to do")
+                    normalized_query = query_key.replace("-", "").replace(" ", "")
+                    query = query.filter(
+                        or_(
+                            func.replace(
+                                func.replace(Note.title, "-", ""), " ", ""
+                            ).ilike(f"%{normalized_query}%"),
+                            func.replace(
+                                func.replace(
+                                    cast(Note.data["content"]["md"], Text), "-", ""
+                                ),
+                                " ",
+                                "",
+                            ).ilike(f"%{normalized_query}%"),
+                        )
+                    )
+
+                view_option = filter.get("view_option")
+                if view_option == "created":
+                    query = query.filter(Note.user_id == user_id)
+                elif view_option == "shared":
+                    query = query.filter(Note.user_id != user_id)
+
+                # Apply access control filtering
+                if "permission" in filter:
+                    permission = filter["permission"]
+                else:
+                    permission = "write"
+
+                query = self._has_permission(
+                    db,
+                    query,
+                    filter,
+                    permission=permission,
+                )
+
+                order_by = filter.get("order_by")
+                direction = filter.get("direction")
+
+                if order_by == "name":
+                    if direction == "asc":
+                        query = query.order_by(Note.title.asc())
+                    else:
+                        query = query.order_by(Note.title.desc())
+                elif order_by == "created_at":
+                    if direction == "asc":
+                        query = query.order_by(Note.created_at.asc())
+                    else:
+                        query = query.order_by(Note.created_at.desc())
+                elif order_by == "updated_at":
+                    if direction == "asc":
+                        query = query.order_by(Note.updated_at.asc())
+                    else:
+                        query = query.order_by(Note.updated_at.desc())
+                else:
+                    query = query.order_by(Note.updated_at.desc())
+
+            else:
+                query = query.order_by(Note.updated_at.desc())
+
+            # Count BEFORE pagination
+            total = query.count()
+
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
+            items = query.all()
+
+            notes = []
+            for note, user in items:
+                notes.append(
+                    NoteUserResponse(
+                        **NoteModel.model_validate(note).model_dump(),
+                        user=(
+                            UserResponse(**UserModel.model_validate(user).model_dump())
+                            if user
+                            else None
+                        ),
+                    )
+                )
+
+            return NoteListResponse(items=notes, total=total)
+
     def get_notes_by_user_id(
         self,
         user_id: str,
-        skip: Optional[int] = None,
-        limit: Optional[int] = None,
+        permission: str = "read",
+        skip: int = 0,
+        limit: int = 50,
+        db: Optional[Session] = None,
     ) -> list[NoteModel]:
-        with get_db() as db:
-            query = db.query(Note).filter(Note.user_id == user_id)
-            query = query.order_by(Note.updated_at.desc())
+        with get_db_context(db) as db:
+            user_group_ids = [
+                group.id for group in Groups.get_groups_by_member_id(user_id, db=db)
+            ]
+
+            query = db.query(Note).order_by(Note.updated_at.desc())
+            query = self._has_permission(
+                db, query, {"user_id": user_id, "group_ids": user_group_ids}, permission
+            )
 
             if skip is not None:
                 query = query.offset(skip)
@@ -128,65 +367,17 @@ class NoteTable:
             notes = query.all()
             return [NoteModel.model_validate(note) for note in notes]
 
-    def get_notes_by_permission(
-        self,
-        user_id: str,
-        permission: str = "write",
-        skip: Optional[int] = None,
-        limit: Optional[int] = None,
-    ) -> list[NoteModel]:
-        with get_db() as db:
-            user_groups = Groups.get_groups_by_member_id(user_id)
-            user_group_ids = {group.id for group in user_groups}
-
-            # Order newest-first. We stream to keep memory usage low.
-            query = (
-                db.query(Note)
-                .order_by(Note.updated_at.desc())
-                .execution_options(stream_results=True)
-                .yield_per(256)
-            )
-
-            results: list[NoteModel] = []
-            n_skipped = 0
-
-            for note in query:
-                # Fast-pass #1: owner
-                if note.user_id == user_id:
-                    permitted = True
-                # Fast-pass #2: public/open
-                elif note.access_control is None:
-                    # Technically this should mean public access for both read and write, but we'll only do read for now
-                    # We might want to change this behavior later
-                    permitted = permission == "read"
-                else:
-                    permitted = has_access(
-                        user_id, permission, note.access_control, user_group_ids
-                    )
-
-                if not permitted:
-                    continue
-
-                # Apply skip AFTER permission filtering so it counts only accessible notes
-                if skip and n_skipped < skip:
-                    n_skipped += 1
-                    continue
-
-                results.append(NoteModel.model_validate(note))
-                if limit is not None and len(results) >= limit:
-                    break
-
-            return results
-
-    def get_note_by_id(self, id: str) -> Optional[NoteModel]:
-        with get_db() as db:
+    def get_note_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[NoteModel]:
+        with get_db_context(db) as db:
             note = db.query(Note).filter(Note.id == id).first()
             return NoteModel.model_validate(note) if note else None
 
     def update_note_by_id(
-        self, id: str, form_data: NoteUpdateForm
+        self, id: str, form_data: NoteUpdateForm, db: Optional[Session] = None
     ) -> Optional[NoteModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             note = db.query(Note).filter(Note.id == id).first()
             if not note:
                 return None
@@ -208,11 +399,14 @@ class NoteTable:
             db.commit()
             return NoteModel.model_validate(note) if note else None
 
-    def delete_note_by_id(self, id: str):
-        with get_db() as db:
-            db.query(Note).filter(Note.id == id).delete()
-            db.commit()
-            return True
+    def delete_note_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        try:
+            with get_db_context(db) as db:
+                db.query(Note).filter(Note.id == id).delete()
+                db.commit()
+                return True
+        except Exception:
+            return False
 
 
 Notes = NoteTable()

backend/open_webui/models/oauth_sessions.py

@@ -8,14 +8,14 @@ import json
 
 from cryptography.fernet import Fernet
 
-from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS, OAUTH_SESSION_TOKEN_ENCRYPTION_KEY
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, get_db, get_db_context
+from open_webui.env import OAUTH_SESSION_TOKEN_ENCRYPTION_KEY
 
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text, Index
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 ####################
 # DB MODEL
@@ -25,7 +25,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class OAuthSession(Base):
     __tablename__ = "oauth_session"
 
-    id = Column(Text, primary_key=True)
+    id = Column(Text, primary_key=True, unique=True)
     user_id = Column(Text, nullable=False)
     provider = Column(Text, nullable=False)
     token = Column(
@@ -110,10 +110,11 @@ class OAuthSessionTable:
         user_id: str,
         provider: str,
         token: dict,
+        db: Optional[Session] = None,
     ) -> Optional[OAuthSessionModel]:
         """Create a new OAuth session"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 current_time = int(time.time())
                 id = str(uuid.uuid4())
 
@@ -142,10 +143,12 @@ class OAuthSessionTable:
             log.error(f"Error creating OAuth session: {e}")
             return None
 
-    def get_session_by_id(self, session_id: str) -> Optional[OAuthSessionModel]:
+    def get_session_by_id(
+        self, session_id: str, db: Optional[Session] = None
+    ) -> Optional[OAuthSessionModel]:
         """Get OAuth session by ID"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 session = db.query(OAuthSession).filter_by(id=session_id).first()
                 if session:
                     session.token = self._decrypt_token(session.token)
@@ -157,11 +160,11 @@ class OAuthSessionTable:
             return None
 
     def get_session_by_id_and_user_id(
-        self, session_id: str, user_id: str
+        self, session_id: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[OAuthSessionModel]:
         """Get OAuth session by ID and user ID"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 session = (
                     db.query(OAuthSession)
                     .filter_by(id=session_id, user_id=user_id)
@@ -177,11 +180,11 @@ class OAuthSessionTable:
             return None
 
     def get_session_by_provider_and_user_id(
-        self, provider: str, user_id: str
+        self, provider: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[OAuthSessionModel]:
         """Get OAuth session by provider and user ID"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 session = (
                     db.query(OAuthSession)
                     .filter_by(provider=provider, user_id=user_id)
@@ -196,10 +199,12 @@ class OAuthSessionTable:
             log.error(f"Error getting OAuth session by provider and user ID: {e}")
             return None
 
-    def get_sessions_by_user_id(self, user_id: str) -> List[OAuthSessionModel]:
+    def get_sessions_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> List[OAuthSessionModel]:
         """Get all OAuth sessions for a user"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 sessions = db.query(OAuthSession).filter_by(user_id=user_id).all()
 
                 results = []
@@ -214,11 +219,11 @@ class OAuthSessionTable:
             return []
 
     def update_session_by_id(
-        self, session_id: str, token: dict
+        self, session_id: str, token: dict, db: Optional[Session] = None
     ) -> Optional[OAuthSessionModel]:
         """Update OAuth session tokens"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 current_time = int(time.time())
 
                 db.query(OAuthSession).filter_by(id=session_id).update(
@@ -240,10 +245,12 @@ class OAuthSessionTable:
             log.error(f"Error updating OAuth session tokens: {e}")
             return None
 
-    def delete_session_by_id(self, session_id: str) -> bool:
+    def delete_session_by_id(
+        self, session_id: str, db: Optional[Session] = None
+    ) -> bool:
         """Delete an OAuth session"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 result = db.query(OAuthSession).filter_by(id=session_id).delete()
                 db.commit()
                 return result > 0
@@ -251,10 +258,12 @@ class OAuthSessionTable:
             log.error(f"Error deleting OAuth session: {e}")
             return False
 
-    def delete_sessions_by_user_id(self, user_id: str) -> bool:
+    def delete_sessions_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> bool:
         """Delete all OAuth sessions for a user"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 result = db.query(OAuthSession).filter_by(user_id=user_id).delete()
                 db.commit()
                 return True
@@ -262,10 +271,12 @@ class OAuthSessionTable:
             log.error(f"Error deleting OAuth sessions by user ID: {e}")
             return False
 
-    def delete_sessions_by_provider(self, provider: str) -> bool:
+    def delete_sessions_by_provider(
+        self, provider: str, db: Optional[Session] = None
+    ) -> bool:
         """Delete all OAuth sessions for a provider"""
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(OAuthSession).filter_by(provider=provider).delete()
                 db.commit()
                 return True

backend/open_webui/models/prompts.py

@@ -1,7 +1,8 @@
 import time
 from typing import Optional
 
-from open_webui.internal.db import Base, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 from open_webui.models.groups import Groups
 from open_webui.models.users import Users, UserResponse
 
@@ -62,6 +63,10 @@ class PromptUserResponse(PromptModel):
     user: Optional[UserResponse] = None
 
 
+class PromptAccessResponse(PromptUserResponse):
+    write_access: Optional[bool] = False
+
+
 class PromptForm(BaseModel):
     command: str
     title: str
@@ -71,7 +76,7 @@ class PromptForm(BaseModel):
 
 class PromptsTable:
     def insert_new_prompt(
-        self, user_id: str, form_data: PromptForm
+        self, user_id: str, form_data: PromptForm, db: Optional[Session] = None
     ) -> Optional[PromptModel]:
         prompt = PromptModel(
             **{
@@ -82,7 +87,7 @@ class PromptsTable:
         )
 
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 result = Prompt(**prompt.model_dump())
                 db.add(result)
                 db.commit()
@@ -94,21 +99,23 @@ class PromptsTable:
         except Exception:
             return None
 
-    def get_prompt_by_command(self, command: str) -> Optional[PromptModel]:
+    def get_prompt_by_command(
+        self, command: str, db: Optional[Session] = None
+    ) -> Optional[PromptModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 prompt = db.query(Prompt).filter_by(command=command).first()
                 return PromptModel.model_validate(prompt)
         except Exception:
             return None
 
-    def get_prompts(self) -> list[PromptUserResponse]:
-        with get_db() as db:
+    def get_prompts(self, db: Optional[Session] = None) -> list[PromptUserResponse]:
+        with get_db_context(db) as db:
             all_prompts = db.query(Prompt).order_by(Prompt.timestamp.desc()).all()
 
             user_ids = list(set(prompt.user_id for prompt in all_prompts))
 
-            users = Users.get_users_by_user_ids(user_ids) if user_ids else []
+            users = Users.get_users_by_user_ids(user_ids, db=db) if user_ids else []
             users_dict = {user.id: user for user in users}
 
             prompts = []
@@ -126,10 +133,12 @@ class PromptsTable:
             return prompts
 
     def get_prompts_by_user_id(
-        self, user_id: str, permission: str = "write"
+        self, user_id: str, permission: str = "write", db: Optional[Session] = None
     ) -> list[PromptUserResponse]:
-        prompts = self.get_prompts()
-        user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user_id)}
+        prompts = self.get_prompts(db=db)
+        user_group_ids = {
+            group.id for group in Groups.get_groups_by_member_id(user_id, db=db)
+        }
 
         return [
             prompt
@@ -139,10 +148,10 @@ class PromptsTable:
         ]
 
     def update_prompt_by_command(
-        self, command: str, form_data: PromptForm
+        self, command: str, form_data: PromptForm, db: Optional[Session] = None
     ) -> Optional[PromptModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 prompt = db.query(Prompt).filter_by(command=command).first()
                 prompt.title = form_data.title
                 prompt.content = form_data.content
@@ -153,9 +162,11 @@ class PromptsTable:
         except Exception:
             return None
 
-    def delete_prompt_by_command(self, command: str) -> bool:
+    def delete_prompt_by_command(
+        self, command: str, db: Optional[Session] = None
+    ) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Prompt).filter_by(command=command).delete()
                 db.commit()
 

backend/open_webui/models/tags.py

@@ -3,15 +3,14 @@ import time
 import uuid
 from typing import Optional
 
-from open_webui.internal.db import Base, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 
 
-from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, JSON, PrimaryKeyConstraint, Index
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 
 ####################
@@ -52,8 +51,10 @@ class TagChatIdForm(BaseModel):
 
 
 class TagTable:
-    def insert_new_tag(self, name: str, user_id: str) -> Optional[TagModel]:
-        with get_db() as db:
+    def insert_new_tag(
+        self, name: str, user_id: str, db: Optional[Session] = None
+    ) -> Optional[TagModel]:
+        with get_db_context(db) as db:
             id = name.replace(" ", "_").lower()
             tag = TagModel(**{"id": id, "user_id": user_id, "name": name})
             try:
@@ -70,27 +71,29 @@ class TagTable:
                 return None
 
     def get_tag_by_name_and_user_id(
-        self, name: str, user_id: str
+        self, name: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[TagModel]:
         try:
             id = name.replace(" ", "_").lower()
-            with get_db() as db:
+            with get_db_context(db) as db:
                 tag = db.query(Tag).filter_by(id=id, user_id=user_id).first()
                 return TagModel.model_validate(tag)
         except Exception:
             return None
 
-    def get_tags_by_user_id(self, user_id: str) -> list[TagModel]:
-        with get_db() as db:
+    def get_tags_by_user_id(
+        self, user_id: str, db: Optional[Session] = None
+    ) -> list[TagModel]:
+        with get_db_context(db) as db:
             return [
                 TagModel.model_validate(tag)
                 for tag in (db.query(Tag).filter_by(user_id=user_id).all())
             ]
 
     def get_tags_by_ids_and_user_id(
-        self, ids: list[str], user_id: str
+        self, ids: list[str], user_id: str, db: Optional[Session] = None
     ) -> list[TagModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             return [
                 TagModel.model_validate(tag)
                 for tag in (
@@ -98,9 +101,11 @@ class TagTable:
                 )
             ]
 
-    def delete_tag_by_name_and_user_id(self, name: str, user_id: str) -> bool:
+    def delete_tag_by_name_and_user_id(
+        self, name: str, user_id: str, db: Optional[Session] = None
+    ) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 id = name.replace(" ", "_").lower()
                 res = db.query(Tag).filter_by(id=id, user_id=user_id).delete()
                 log.debug(f"res: {res}")

backend/open_webui/models/tools.py

@@ -2,11 +2,11 @@ import logging
 import time
 from typing import Optional
 
-from open_webui.internal.db import Base, JSONField, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 from open_webui.models.users import Users, UserResponse
 from open_webui.models.groups import Groups
 
-from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text, JSON
 
@@ -14,7 +14,6 @@ from open_webui.utils.access_control import has_access
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 ####################
 # Tools DB Schema
@@ -24,7 +23,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class Tool(Base):
     __tablename__ = "tool"
 
-    id = Column(String, primary_key=True)
+    id = Column(String, primary_key=True, unique=True)
     user_id = Column(String)
     name = Column(Text)
     content = Column(Text)
@@ -98,6 +97,10 @@ class ToolUserResponse(ToolResponse):
     model_config = ConfigDict(extra="allow")
 
 
+class ToolAccessResponse(ToolUserResponse):
+    write_access: Optional[bool] = False
+
+
 class ToolForm(BaseModel):
     id: str
     name: str
@@ -112,9 +115,13 @@ class ToolValves(BaseModel):
 
 class ToolsTable:
     def insert_new_tool(
-        self, user_id: str, form_data: ToolForm, specs: list[dict]
+        self,
+        user_id: str,
+        form_data: ToolForm,
+        specs: list[dict],
+        db: Optional[Session] = None,
     ) -> Optional[ToolModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             tool = ToolModel(
                 **{
                     **form_data.model_dump(),
@@ -138,21 +145,23 @@ class ToolsTable:
                 log.exception(f"Error creating a new tool: {e}")
                 return None
 
-    def get_tool_by_id(self, id: str) -> Optional[ToolModel]:
+    def get_tool_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[ToolModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 tool = db.get(Tool, id)
                 return ToolModel.model_validate(tool)
         except Exception:
             return None
 
-    def get_tools(self) -> list[ToolUserModel]:
-        with get_db() as db:
+    def get_tools(self, db: Optional[Session] = None) -> list[ToolUserModel]:
+        with get_db_context(db) as db:
             all_tools = db.query(Tool).order_by(Tool.updated_at.desc()).all()
 
             user_ids = list(set(tool.user_id for tool in all_tools))
 
-            users = Users.get_users_by_user_ids(user_ids) if user_ids else []
+            users = Users.get_users_by_user_ids(user_ids, db=db) if user_ids else []
             users_dict = {user.id: user for user in users}
 
             tools = []
@@ -169,10 +178,12 @@ class ToolsTable:
             return tools
 
     def get_tools_by_user_id(
-        self, user_id: str, permission: str = "write"
+        self, user_id: str, permission: str = "write", db: Optional[Session] = None
     ) -> list[ToolUserModel]:
-        tools = self.get_tools()
-        user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user_id)}
+        tools = self.get_tools(db=db)
+        user_group_ids = {
+            group.id for group in Groups.get_groups_by_member_id(user_id, db=db)
+        }
 
         return [
             tool
@@ -181,31 +192,35 @@ class ToolsTable:
             or has_access(user_id, permission, tool.access_control, user_group_ids)
         ]
 
-    def get_tool_valves_by_id(self, id: str) -> Optional[dict]:
+    def get_tool_valves_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[dict]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 tool = db.get(Tool, id)
                 return tool.valves if tool.valves else {}
         except Exception as e:
             log.exception(f"Error getting tool valves by id {id}")
             return None
 
-    def update_tool_valves_by_id(self, id: str, valves: dict) -> Optional[ToolValves]:
+    def update_tool_valves_by_id(
+        self, id: str, valves: dict, db: Optional[Session] = None
+    ) -> Optional[ToolValves]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Tool).filter_by(id=id).update(
                     {"valves": valves, "updated_at": int(time.time())}
                 )
                 db.commit()
-                return self.get_tool_by_id(id)
+                return self.get_tool_by_id(id, db=db)
         except Exception:
             return None
 
     def get_user_valves_by_id_and_user_id(
-        self, id: str, user_id: str
+        self, id: str, user_id: str, db: Optional[Session] = None
     ) -> Optional[dict]:
         try:
-            user = Users.get_user_by_id(user_id)
+            user = Users.get_user_by_id(user_id, db=db)
             user_settings = user.settings.model_dump() if user.settings else {}
 
             # Check if user has "tools" and "valves" settings
@@ -222,10 +237,10 @@ class ToolsTable:
             return None
 
     def update_user_valves_by_id_and_user_id(
-        self, id: str, user_id: str, valves: dict
+        self, id: str, user_id: str, valves: dict, db: Optional[Session] = None
     ) -> Optional[dict]:
         try:
-            user = Users.get_user_by_id(user_id)
+            user = Users.get_user_by_id(user_id, db=db)
             user_settings = user.settings.model_dump() if user.settings else {}
 
             # Check if user has "tools" and "valves" settings
@@ -237,7 +252,7 @@ class ToolsTable:
             user_settings["tools"]["valves"][id] = valves
 
             # Update the user settings in the database
-            Users.update_user_by_id(user_id, {"settings": user_settings})
+            Users.update_user_by_id(user_id, {"settings": user_settings}, db=db)
 
             return user_settings["tools"]["valves"][id]
         except Exception as e:
@@ -246,9 +261,11 @@ class ToolsTable:
             )
             return None
 
-    def update_tool_by_id(self, id: str, updated: dict) -> Optional[ToolModel]:
+    def update_tool_by_id(
+        self, id: str, updated: dict, db: Optional[Session] = None
+    ) -> Optional[ToolModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Tool).filter_by(id=id).update(
                     {**updated, "updated_at": int(time.time())}
                 )
@@ -260,9 +277,9 @@ class ToolsTable:
         except Exception:
             return None
 
-    def delete_tool_by_id(self, id: str) -> bool:
+    def delete_tool_by_id(self, id: str, db: Optional[Session] = None) -> bool:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(Tool).filter_by(id=id).delete()
                 db.commit()
 

backend/open_webui/models/users.py

@@ -1,18 +1,34 @@
 import time
 from typing import Optional
 
-from open_webui.internal.db import Base, JSONField, get_db
+from sqlalchemy.orm import Session
+from open_webui.internal.db import Base, JSONField, get_db, get_db_context
 
 
 from open_webui.env import DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL
+
 from open_webui.models.chats import Chats
-from open_webui.models.groups import Groups
+from open_webui.models.groups import Groups, GroupMember
+from open_webui.models.channels import ChannelMember
+
 from open_webui.utils.misc import throttle
 
 
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text, Date
-from sqlalchemy import or_
+from sqlalchemy import (
+    BigInteger,
+    JSON,
+    Column,
+    String,
+    Boolean,
+    Text,
+    Date,
+    exists,
+    select,
+    cast,
+)
+from sqlalchemy import or_, case
+from sqlalchemy.dialects.postgresql import JSONB
 
 import datetime
 
@@ -21,59 +37,71 @@ import datetime
 ####################
 
 
-class User(Base):
-    __tablename__ = "user"
-
-    id = Column(String, primary_key=True)
-    name = Column(String)
-
-    email = Column(String)
-    username = Column(String(50), nullable=True)
-
-    role = Column(String)
-    profile_image_url = Column(Text)
-
-    bio = Column(Text, nullable=True)
-    gender = Column(Text, nullable=True)
-    date_of_birth = Column(Date, nullable=True)
-
-    info = Column(JSONField, nullable=True)
-    settings = Column(JSONField, nullable=True)
-
-    api_key = Column(String, nullable=True, unique=True)
-    oauth_sub = Column(Text, unique=True)
-
-    last_active_at = Column(BigInteger)
-
-    updated_at = Column(BigInteger)
-    created_at = Column(BigInteger)
-
-
 class UserSettings(BaseModel):
     ui: Optional[dict] = {}
     model_config = ConfigDict(extra="allow")
     pass
 
 
+class User(Base):
+    __tablename__ = "user"
+
+    id = Column(String, primary_key=True, unique=True)
+    email = Column(String)
+    username = Column(String(50), nullable=True)
+    role = Column(String)
+
+    name = Column(String)
+
+    profile_image_url = Column(Text)
+    profile_banner_image_url = Column(Text, nullable=True)
+
+    bio = Column(Text, nullable=True)
+    gender = Column(Text, nullable=True)
+    date_of_birth = Column(Date, nullable=True)
+    timezone = Column(String, nullable=True)
+
+    presence_state = Column(String, nullable=True)
+    status_emoji = Column(String, nullable=True)
+    status_message = Column(Text, nullable=True)
+    status_expires_at = Column(BigInteger, nullable=True)
+
+    info = Column(JSON, nullable=True)
+    settings = Column(JSON, nullable=True)
+
+    oauth = Column(JSON, nullable=True)
+
+    last_active_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+    created_at = Column(BigInteger)
+
+
 class UserModel(BaseModel):
     id: str
-    name: str
 
     email: str
     username: Optional[str] = None
-
     role: str = "pending"
+
+    name: str
+
     profile_image_url: str
+    profile_banner_image_url: Optional[str] = None
 
     bio: Optional[str] = None
     gender: Optional[str] = None
     date_of_birth: Optional[datetime.date] = None
+    timezone: Optional[str] = None
+
+    presence_state: Optional[str] = None
+    status_emoji: Optional[str] = None
+    status_message: Optional[str] = None
+    status_expires_at: Optional[int] = None
 
     info: Optional[dict] = None
     settings: Optional[UserSettings] = None
 
-    api_key: Optional[str] = None
-    oauth_sub: Optional[str] = None
+    oauth: Optional[dict] = None
 
     last_active_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
@@ -82,6 +110,38 @@ class UserModel(BaseModel):
     model_config = ConfigDict(from_attributes=True)
 
 
+class UserStatusModel(UserModel):
+    is_active: bool = False
+
+    model_config = ConfigDict(from_attributes=True)
+
+
+class ApiKey(Base):
+    __tablename__ = "api_key"
+
+    id = Column(Text, primary_key=True, unique=True)
+    user_id = Column(Text, nullable=False)
+    key = Column(Text, unique=True, nullable=False)
+    data = Column(JSON, nullable=True)
+    expires_at = Column(BigInteger, nullable=True)
+    last_used_at = Column(BigInteger, nullable=True)
+    created_at = Column(BigInteger, nullable=False)
+    updated_at = Column(BigInteger, nullable=False)
+
+
+class ApiKeyModel(BaseModel):
+    id: str
+    user_id: str
+    key: str
+    data: Optional[dict] = None
+    expires_at: Optional[int] = None
+    last_used_at: Optional[int] = None
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+    model_config = ConfigDict(from_attributes=True)
+
+
 ####################
 # Forms
 ####################
@@ -95,12 +155,31 @@ class UpdateProfileForm(BaseModel):
     date_of_birth: Optional[datetime.date] = None
 
 
+class UserGroupIdsModel(UserModel):
+    group_ids: list[str] = []
+
+
+class UserModelResponse(UserModel):
+    model_config = ConfigDict(extra="allow")
+
+
 class UserListResponse(BaseModel):
-    users: list[UserModel]
+    users: list[UserModelResponse]
     total: int
 
 
-class UserInfoResponse(BaseModel):
+class UserGroupIdsListResponse(BaseModel):
+    users: list[UserGroupIdsModel]
+    total: int
+
+
+class UserStatus(BaseModel):
+    status_emoji: Optional[str] = None
+    status_message: Optional[str] = None
+    status_expires_at: Optional[int] = None
+
+
+class UserInfoResponse(UserStatus):
     id: str
     name: str
     email: str
@@ -112,6 +191,12 @@ class UserIdNameResponse(BaseModel):
     name: str
 
 
+class UserIdNameStatusResponse(UserStatus):
+    id: str
+    name: str
+    is_active: Optional[bool] = None
+
+
 class UserInfoListResponse(BaseModel):
     users: list[UserInfoResponse]
     total: int
@@ -122,18 +207,18 @@ class UserIdNameListResponse(BaseModel):
     total: int
 
 
-class UserResponse(BaseModel):
-    id: str
-    name: str
-    email: str
-    role: str
-    profile_image_url: str
-
-
 class UserNameResponse(BaseModel):
     id: str
     name: str
     role: str
+
+
+class UserResponse(UserNameResponse):
+    email: str
+
+
+class UserProfileImageResponse(UserNameResponse):
+    email: str
     profile_image_url: str
 
 
@@ -158,20 +243,21 @@ class UsersTable:
         email: str,
         profile_image_url: str = "/user.png",
         role: str = "pending",
-        oauth_sub: Optional[str] = None,
+        oauth: Optional[dict] = None,
+        db: Optional[Session] = None,
     ) -> Optional[UserModel]:
-        with get_db() as db:
+        with get_db_context(db) as db:
             user = UserModel(
                 **{
                     "id": id,
-                    "name": name,
                     "email": email,
+                    "name": name,
                     "role": role,
                     "profile_image_url": profile_image_url,
                     "last_active_at": int(time.time()),
                     "created_at": int(time.time()),
                     "updated_at": int(time.time()),
-                    "oauth_sub": oauth_sub,
+                    "oauth": oauth,
                 }
             )
             result = User(**user.model_dump())
@@ -183,36 +269,60 @@ class UsersTable:
             else:
                 return None
 
-    def get_user_by_id(self, id: str) -> Optional[UserModel]:
+    def get_user_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 user = db.query(User).filter_by(id=id).first()
                 return UserModel.model_validate(user)
         except Exception:
             return None
 
-    def get_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
+    def get_user_by_api_key(
+        self, api_key: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
-                user = db.query(User).filter_by(api_key=api_key).first()
-                return UserModel.model_validate(user)
+            with get_db_context(db) as db:
+                user = (
+                    db.query(User)
+                    .join(ApiKey, User.id == ApiKey.user_id)
+                    .filter(ApiKey.key == api_key)
+                    .first()
+                )
+                return UserModel.model_validate(user) if user else None
         except Exception:
             return None
 
-    def get_user_by_email(self, email: str) -> Optional[UserModel]:
+    def get_user_by_email(
+        self, email: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 user = db.query(User).filter_by(email=email).first()
                 return UserModel.model_validate(user)
         except Exception:
             return None
 
-    def get_user_by_oauth_sub(self, sub: str) -> Optional[UserModel]:
+    def get_user_by_oauth_sub(
+        self, provider: str, sub: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
-                user = db.query(User).filter_by(oauth_sub=sub).first()
-                return UserModel.model_validate(user)
-        except Exception:
+            with get_db_context(db) as db:  # type: Session
+                dialect_name = db.bind.dialect.name
+
+                query = db.query(User)
+                if dialect_name == "sqlite":
+                    query = query.filter(User.oauth.contains({provider: {"sub": sub}}))
+                elif dialect_name == "postgresql":
+                    query = query.filter(
+                        User.oauth[provider].cast(JSONB)["sub"].astext == sub
+                    )
+
+                user = query.first()
+                return UserModel.model_validate(user) if user else None
+        except Exception as e:
+            # You may want to log the exception here
             return None
 
     def get_users(
@@ -220,8 +330,10 @@ class UsersTable:
         filter: Optional[dict] = None,
         skip: Optional[int] = None,
         limit: Optional[int] = None,
+        db: Optional[Session] = None,
     ) -> dict:
-        with get_db() as db:
+        with get_db_context(db) as db:
+            # Join GroupMember so we can order by group_id when requested
             query = db.query(User)
 
             if filter:
@@ -234,14 +346,76 @@ class UsersTable:
                         )
                     )
 
+                channel_id = filter.get("channel_id")
+                if channel_id:
+                    query = query.filter(
+                        exists(
+                            select(ChannelMember.id).where(
+                                ChannelMember.user_id == User.id,
+                                ChannelMember.channel_id == channel_id,
+                            )
+                        )
+                    )
+
+                user_ids = filter.get("user_ids")
+                group_ids = filter.get("group_ids")
+
+                if isinstance(user_ids, list) and isinstance(group_ids, list):
+                    # If both are empty lists, return no users
+                    if not user_ids and not group_ids:
+                        return {"users": [], "total": 0}
+
+                if user_ids:
+                    query = query.filter(User.id.in_(user_ids))
+
+                if group_ids:
+                    query = query.filter(
+                        exists(
+                            select(GroupMember.id).where(
+                                GroupMember.user_id == User.id,
+                                GroupMember.group_id.in_(group_ids),
+                            )
+                        )
+                    )
+
+                roles = filter.get("roles")
+                if roles:
+                    include_roles = [role for role in roles if not role.startswith("!")]
+                    exclude_roles = [role[1:] for role in roles if role.startswith("!")]
+
+                    if include_roles:
+                        query = query.filter(User.role.in_(include_roles))
+                    if exclude_roles:
+                        query = query.filter(~User.role.in_(exclude_roles))
+
                 order_by = filter.get("order_by")
                 direction = filter.get("direction")
 
-                if order_by == "name":
+                if order_by and order_by.startswith("group_id:"):
+                    group_id = order_by.split(":", 1)[1]
+
+                    # Subquery that checks if the user belongs to the group
+                    membership_exists = exists(
+                        select(GroupMember.id).where(
+                            GroupMember.user_id == User.id,
+                            GroupMember.group_id == group_id,
+                        )
+                    )
+
+                    # CASE: user in group → 1, user not in group → 0
+                    group_sort = case((membership_exists, 1), else_=0)
+
+                    if direction == "asc":
+                        query = query.order_by(group_sort.asc(), User.name.asc())
+                    else:
+                        query = query.order_by(group_sort.desc(), User.name.asc())
+
+                elif order_by == "name":
                     if direction == "asc":
                         query = query.order_by(User.name.asc())
                     else:
                         query = query.order_by(User.name.desc())
+
                 elif order_by == "email":
                     if direction == "asc":
                         query = query.order_by(User.email.asc())
@@ -274,41 +448,61 @@ class UsersTable:
             else:
                 query = query.order_by(User.created_at.desc())
 
-            if skip:
+            # Count BEFORE pagination
+            total = query.count()
+
+            # correct pagination logic
+            if skip is not None:
                 query = query.offset(skip)
-            if limit:
+            if limit is not None:
                 query = query.limit(limit)
 
             users = query.all()
             return {
                 "users": [UserModel.model_validate(user) for user in users],
-                "total": db.query(User).count(),
+                "total": total,
             }
 
-    def get_users_by_user_ids(self, user_ids: list[str]) -> list[UserModel]:
-        with get_db() as db:
+    def get_users_by_group_id(
+        self, group_id: str, db: Optional[Session] = None
+    ) -> list[UserModel]:
+        with get_db_context(db) as db:
+            users = (
+                db.query(User)
+                .join(GroupMember, User.id == GroupMember.user_id)
+                .filter(GroupMember.group_id == group_id)
+                .all()
+            )
+            return [UserModel.model_validate(user) for user in users]
+
+    def get_users_by_user_ids(
+        self, user_ids: list[str], db: Optional[Session] = None
+    ) -> list[UserStatusModel]:
+        with get_db_context(db) as db:
             users = db.query(User).filter(User.id.in_(user_ids)).all()
             return [UserModel.model_validate(user) for user in users]
 
-    def get_num_users(self) -> Optional[int]:
-        with get_db() as db:
+    def get_num_users(self, db: Optional[Session] = None) -> Optional[int]:
+        with get_db_context(db) as db:
             return db.query(User).count()
 
-    def has_users(self) -> bool:
-        with get_db() as db:
+    def has_users(self, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
             return db.query(db.query(User).exists()).scalar()
 
-    def get_first_user(self) -> UserModel:
+    def get_first_user(self, db: Optional[Session] = None) -> UserModel:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 user = db.query(User).order_by(User.created_at).first()
                 return UserModel.model_validate(user)
         except Exception:
             return None
 
-    def get_user_webhook_url_by_id(self, id: str) -> Optional[str]:
+    def get_user_webhook_url_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[str]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 user = db.query(User).filter_by(id=id).first()
 
                 if user.settings is None:
@@ -322,9 +516,20 @@ class UsersTable:
         except Exception:
             return None
 
-    def update_user_role_by_id(self, id: str, role: str) -> Optional[UserModel]:
+    def get_num_users_active_today(self, db: Optional[Session] = None) -> Optional[int]:
+        with get_db_context(db) as db:
+            current_timestamp = int(datetime.datetime.now().timestamp())
+            today_midnight_timestamp = current_timestamp - (current_timestamp % 86400)
+            query = db.query(User).filter(
+                User.last_active_at > today_midnight_timestamp
+            )
+            return query.count()
+
+    def update_user_role_by_id(
+        self, id: str, role: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(User).filter_by(id=id).update({"role": role})
                 db.commit()
                 user = db.query(User).filter_by(id=id).first()
@@ -332,11 +537,26 @@ class UsersTable:
         except Exception:
             return None
 
-    def update_user_profile_image_url_by_id(
-        self, id: str, profile_image_url: str
+    def update_user_status_by_id(
+        self, id: str, form_data: UserStatus, db: Optional[Session] = None
     ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
+                db.query(User).filter_by(id=id).update(
+                    {**form_data.model_dump(exclude_none=True)}
+                )
+                db.commit()
+
+                user = db.query(User).filter_by(id=id).first()
+                return UserModel.model_validate(user)
+        except Exception:
+            return None
+
+    def update_user_profile_image_url_by_id(
+        self, id: str, profile_image_url: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
+        try:
+            with get_db_context(db) as db:
                 db.query(User).filter_by(id=id).update(
                     {"profile_image_url": profile_image_url}
                 )
@@ -348,9 +568,11 @@ class UsersTable:
             return None
 
     @throttle(DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL)
-    def update_user_last_active_by_id(self, id: str) -> Optional[UserModel]:
+    def update_last_active_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(User).filter_by(id=id).update(
                     {"last_active_at": int(time.time())}
                 )
@@ -361,22 +583,43 @@ class UsersTable:
         except Exception:
             return None
 
-    def update_user_oauth_sub_by_id(
-        self, id: str, oauth_sub: str
+    def update_user_oauth_by_id(
+        self, id: str, provider: str, sub: str, db: Optional[Session] = None
     ) -> Optional[UserModel]:
+        """
+        Update or insert an OAuth provider/sub pair into the user's oauth JSON field.
+        Example resulting structure:
+            {
+                "google": { "sub": "123" },
+                "github": { "sub": "abc" }
+            }
+        """
         try:
-            with get_db() as db:
-                db.query(User).filter_by(id=id).update({"oauth_sub": oauth_sub})
+            with get_db_context(db) as db:
+                user = db.query(User).filter_by(id=id).first()
+                if not user:
+                    return None
+
+                # Load existing oauth JSON or create empty
+                oauth = user.oauth or {}
+
+                # Update or insert provider entry
+                oauth[provider] = {"sub": sub}
+
+                # Persist updated JSON
+                db.query(User).filter_by(id=id).update({"oauth": oauth})
                 db.commit()
 
-                user = db.query(User).filter_by(id=id).first()
                 return UserModel.model_validate(user)
+
         except Exception:
             return None
 
-    def update_user_by_id(self, id: str, updated: dict) -> Optional[UserModel]:
+    def update_user_by_id(
+        self, id: str, updated: dict, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
+            with get_db_context(db) as db:
                 db.query(User).filter_by(id=id).update(updated)
                 db.commit()
 
@@ -387,10 +630,16 @@ class UsersTable:
             print(e)
             return None
 
-    def update_user_settings_by_id(self, id: str, updated: dict) -> Optional[UserModel]:
+    def update_user_settings_by_id(
+        self, id: str, updated: dict, db: Optional[Session] = None
+    ) -> Optional[UserModel]:
         try:
-            with get_db() as db:
-                user_settings = db.query(User).filter_by(id=id).first().settings
+            with get_db_context(db) as db:
+                user = db.query(User).filter_by(id=id).first()
+                if not user:
+                    return None
+
+                user_settings = user.settings
 
                 if user_settings is None:
                     user_settings = {}
@@ -405,15 +654,15 @@ class UsersTable:
         except Exception:
             return None
 
-    def delete_user_by_id(self, id: str) -> bool:
+    def delete_user_by_id(self, id: str, db: Optional[Session] = None) -> bool:
         try:
             # Remove User from Groups
             Groups.remove_user_from_all_groups(id)
 
             # Delete User Chats
-            result = Chats.delete_chats_by_user_id(id)
+            result = Chats.delete_chats_by_user_id(id, db=db)
             if result:
-                with get_db() as db:
+                with get_db_context(db) as db:
                     # Delete User
                     db.query(User).filter_by(id=id).delete()
                     db.commit()
@@ -424,35 +673,81 @@ class UsersTable:
         except Exception:
             return False
 
-    def update_user_api_key_by_id(self, id: str, api_key: str) -> bool:
+    def get_user_api_key_by_id(
+        self, id: str, db: Optional[Session] = None
+    ) -> Optional[str]:
         try:
-            with get_db() as db:
-                result = db.query(User).filter_by(id=id).update({"api_key": api_key})
-                db.commit()
-                return True if result == 1 else False
-        except Exception:
-            return False
-
-    def get_user_api_key_by_id(self, id: str) -> Optional[str]:
-        try:
-            with get_db() as db:
-                user = db.query(User).filter_by(id=id).first()
-                return user.api_key
+            with get_db_context(db) as db:
+                api_key = db.query(ApiKey).filter_by(user_id=id).first()
+                return api_key.key if api_key else None
         except Exception:
             return None
 
-    def get_valid_user_ids(self, user_ids: list[str]) -> list[str]:
-        with get_db() as db:
+    def update_user_api_key_by_id(
+        self, id: str, api_key: str, db: Optional[Session] = None
+    ) -> bool:
+        try:
+            with get_db_context(db) as db:
+                db.query(ApiKey).filter_by(user_id=id).delete()
+                db.commit()
+
+                now = int(time.time())
+                new_api_key = ApiKey(
+                    id=f"key_{id}",
+                    user_id=id,
+                    key=api_key,
+                    created_at=now,
+                    updated_at=now,
+                )
+                db.add(new_api_key)
+                db.commit()
+
+                return True
+
+        except Exception:
+            return False
+
+    def delete_user_api_key_by_id(self, id: str, db: Optional[Session] = None) -> bool:
+        try:
+            with get_db_context(db) as db:
+                db.query(ApiKey).filter_by(user_id=id).delete()
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def get_valid_user_ids(
+        self, user_ids: list[str], db: Optional[Session] = None
+    ) -> list[str]:
+        with get_db_context(db) as db:
             users = db.query(User).filter(User.id.in_(user_ids)).all()
             return [user.id for user in users]
 
-    def get_super_admin_user(self) -> Optional[UserModel]:
-        with get_db() as db:
+    def get_super_admin_user(self, db: Optional[Session] = None) -> Optional[UserModel]:
+        with get_db_context(db) as db:
             user = db.query(User).filter_by(role="admin").first()
             if user:
                 return UserModel.model_validate(user)
             else:
                 return None
 
+    def get_active_user_count(self, db: Optional[Session] = None) -> int:
+        with get_db_context(db) as db:
+            # Consider user active if last_active_at within the last 3 minutes
+            three_minutes_ago = int(time.time()) - 180
+            count = (
+                db.query(User).filter(User.last_active_at >= three_minutes_ago).count()
+            )
+            return count
+
+    def is_user_active(self, user_id: str, db: Optional[Session] = None) -> bool:
+        with get_db_context(db) as db:
+            user = db.query(User).filter_by(id=user_id).first()
+            if user and user.last_active_at:
+                # Consider user active if last_active_at within the last 3 minutes
+                three_minutes_ago = int(time.time()) - 180
+                return user.last_active_at >= three_minutes_ago
+            return False
+
 
 Users = UsersTable()

backend/open_webui/retrieval/loaders/external_document.py

@@ -6,10 +6,8 @@ from urllib.parse import quote
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
 from open_webui.utils.headers import include_user_info_headers
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class ExternalDocumentLoader(BaseLoader):

backend/open_webui/retrieval/loaders/external_web.py

@@ -4,10 +4,8 @@ from typing import Iterator, List, Union
 
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class ExternalWebLoader(BaseLoader):

backend/open_webui/retrieval/loaders/main.py

@@ -30,11 +30,10 @@ from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
 from open_webui.retrieval.loaders.mineru import MinerULoader
 
 
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.env import GLOBAL_LOG_LEVEL, REQUESTS_VERIFY
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 known_source_ext = [
     "go",
@@ -115,7 +114,7 @@ class TikaLoader:
             endpoint += "/"
         endpoint += "tika/text"
 
-        r = requests.put(endpoint, data=data, headers=headers)
+        r = requests.put(endpoint, data=data, headers=headers, verify=REQUESTS_VERIFY)
 
         if r.ok:
             raw_metadata = r.json()
@@ -132,8 +131,9 @@ class TikaLoader:
 
 
 class DoclingLoader:
-    def __init__(self, url, file_path=None, mime_type=None, params=None):
+    def __init__(self, url, api_key=None, file_path=None, mime_type=None, params=None):
         self.url = url.rstrip("/")
+        self.api_key = api_key
         self.file_path = file_path
         self.mime_type = mime_type
 
@@ -141,68 +141,25 @@ class DoclingLoader:
 
     def load(self) -> list[Document]:
         with open(self.file_path, "rb") as f:
-            files = {
-                "files": (
-                    self.file_path,
-                    f,
-                    self.mime_type or "application/octet-stream",
-                )
-            }
+            headers = {}
+            if self.api_key:
+                headers["X-Api-Key"] = f"Bearer {self.api_key}"
 
-            params = {"image_export_mode": "placeholder"}
-
-            if self.params:
-                if self.params.get("do_picture_description"):
-                    params["do_picture_description"] = self.params.get(
-                        "do_picture_description"
+            r = requests.post(
+                f"{self.url}/v1/convert/file",
+                files={
+                    "files": (
+                        self.file_path,
+                        f,
+                        self.mime_type or "application/octet-stream",
                     )
-
-                    picture_description_mode = self.params.get(
-                        "picture_description_mode", ""
-                    ).lower()
-
-                    if picture_description_mode == "local" and self.params.get(
-                        "picture_description_local", {}
-                    ):
-                        params["picture_description_local"] = json.dumps(
-                            self.params.get("picture_description_local", {})
-                        )
-
-                    elif picture_description_mode == "api" and self.params.get(
-                        "picture_description_api", {}
-                    ):
-                        params["picture_description_api"] = json.dumps(
-                            self.params.get("picture_description_api", {})
-                        )
-
-                params["do_ocr"] = self.params.get("do_ocr")
-
-                params["force_ocr"] = self.params.get("force_ocr")
-
-                if (
-                    self.params.get("do_ocr")
-                    and self.params.get("ocr_engine")
-                    and self.params.get("ocr_lang")
-                ):
-                    params["ocr_engine"] = self.params.get("ocr_engine")
-                    params["ocr_lang"] = [
-                        lang.strip()
-                        for lang in self.params.get("ocr_lang").split(",")
-                        if lang.strip()
-                    ]
-
-                if self.params.get("pdf_backend"):
-                    params["pdf_backend"] = self.params.get("pdf_backend")
-
-                if self.params.get("table_mode"):
-                    params["table_mode"] = self.params.get("table_mode")
-
-                if self.params.get("pipeline"):
-                    params["pipeline"] = self.params.get("pipeline")
-
-            endpoint = f"{self.url}/v1/convert/file"
-            r = requests.post(endpoint, files=files, data=params)
-
+                },
+                data={
+                    "image_export_mode": "placeholder",
+                    **self.params,
+                },
+                headers=headers,
+            )
         if r.ok:
             result = r.json()
             document_data = result.get("document", {})
@@ -211,7 +168,6 @@ class DoclingLoader:
             metadata = {"Content-Type": self.mime_type} if self.mime_type else {}
 
             log.debug("Docling extracted text: %s", text)
-
             return [Document(page_content=text, metadata=metadata)]
         else:
             error_msg = f"Error calling Docling API: {r.reason}"
@@ -340,6 +296,7 @@ class Loader:
 
                 loader = DoclingLoader(
                     url=self.kwargs.get("DOCLING_SERVER_URL"),
+                    api_key=self.kwargs.get("DOCLING_API_KEY", None),
                     file_path=file_path,
                     mime_type=file_content_type,
                     params=params,
@@ -362,22 +319,33 @@ class Loader:
                     file_path=file_path,
                     api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
                     api_key=self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY"),
+                    api_model=self.kwargs.get("DOCUMENT_INTELLIGENCE_MODEL"),
                 )
             else:
                 loader = AzureAIDocumentIntelligenceLoader(
                     file_path=file_path,
                     api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
                     azure_credential=DefaultAzureCredential(),
+                    api_model=self.kwargs.get("DOCUMENT_INTELLIGENCE_MODEL"),
                 )
         elif self.engine == "mineru" and file_ext in [
             "pdf"
         ]:  # MinerU currently only supports PDF
+
+            mineru_timeout = self.kwargs.get("MINERU_API_TIMEOUT", 300)
+            if mineru_timeout:
+                try:
+                    mineru_timeout = int(mineru_timeout)
+                except ValueError:
+                    mineru_timeout = 300
+
             loader = MinerULoader(
                 file_path=file_path,
                 api_mode=self.kwargs.get("MINERU_API_MODE", "local"),
                 api_url=self.kwargs.get("MINERU_API_URL", "http://localhost:8000"),
                 api_key=self.kwargs.get("MINERU_API_KEY", ""),
                 params=self.kwargs.get("MINERU_PARAMS", {}),
+                timeout=mineru_timeout,
             )
         elif (
             self.engine == "mistral_ocr"

backend/open_webui/retrieval/loaders/mineru.py

@@ -26,20 +26,23 @@ class MinerULoader:
         api_url: str = "http://localhost:8000",
         api_key: str = "",
         params: dict = None,
+        timeout: Optional[int] = 300,
     ):
         self.file_path = file_path
         self.api_mode = api_mode.lower()
         self.api_url = api_url.rstrip("/")
         self.api_key = api_key
+        self.timeout = timeout
 
         # Parse params dict with defaults
-        params = params or {}
+        self.params = params or {}
         self.enable_ocr = params.get("enable_ocr", False)
         self.enable_formula = params.get("enable_formula", True)
         self.enable_table = params.get("enable_table", True)
         self.language = params.get("language", "en")
         self.model_version = params.get("model_version", "pipeline")
-        self.page_ranges = params.get("page_ranges", "")
+
+        self.page_ranges = self.params.pop("page_ranges", "")
 
         # Validate API mode
         if self.api_mode not in ["local", "cloud"]:
@@ -76,27 +79,10 @@ class MinerULoader:
 
         # Build form data for Local API
         form_data = {
+            **self.params,
             "return_md": "true",
-            "formula_enable": str(self.enable_formula).lower(),
-            "table_enable": str(self.enable_table).lower(),
         }
 
-        # Parse method based on OCR setting
-        if self.enable_ocr:
-            form_data["parse_method"] = "ocr"
-        else:
-            form_data["parse_method"] = "auto"
-
-        # Language configuration (Local API uses lang_list array)
-        if self.language:
-            form_data["lang_list"] = self.language
-
-        # Backend/model version (Local API uses "backend" parameter)
-        if self.model_version == "vlm":
-            form_data["backend"] = "vlm-vllm-engine"
-        else:
-            form_data["backend"] = "pipeline"
-
         # Page ranges (Local API uses start_page_id and end_page_id)
         if self.page_ranges:
             # For simplicity, if page_ranges is specified, log a warning
@@ -117,7 +103,7 @@ class MinerULoader:
                     f"{self.api_url}/file_parse",
                     data=form_data,
                     files=files,
-                    timeout=300,  # 5 minute timeout for large documents
+                    timeout=self.timeout,
                 )
                 response.raise_for_status()
 
@@ -236,10 +222,7 @@ class MinerULoader:
 
         # Build request body
         request_body = {
-            "enable_formula": self.enable_formula,
-            "enable_table": self.enable_table,
-            "language": self.language,
-            "model_version": self.model_version,
+            **self.params,
             "files": [
                 {
                     "name": filename,
@@ -319,7 +302,7 @@ class MinerULoader:
                 response = requests.put(
                     upload_url,
                     data=f,
-                    timeout=300,  # 5 minute timeout for large files
+                    timeout=self.timeout,
                 )
                 response.raise_for_status()
         except FileNotFoundError:

backend/open_webui/retrieval/loaders/mistral.py

@@ -9,11 +9,10 @@ from typing import List, Dict, Any
 from contextlib import asynccontextmanager
 
 from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.env import GLOBAL_LOG_LEVEL
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class MistralLoader:

backend/open_webui/retrieval/loaders/tavily.py

@@ -4,10 +4,8 @@ from typing import Iterator, List, Literal, Union
 
 from langchain_core.document_loaders import BaseLoader
 from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class TavilyLoader(BaseLoader):

backend/open_webui/retrieval/loaders/youtube.py

@@ -4,10 +4,8 @@ from xml.etree.ElementTree import ParseError
 from typing import Any, Dict, Generator, List, Optional, Sequence, Union
 from urllib.parse import parse_qs, urlparse
 from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 ALLOWED_SCHEMES = {"http", "https"}
 ALLOWED_NETLOCS = {

backend/open_webui/retrieval/models/colbert.py

@@ -5,12 +5,10 @@ import numpy as np
 from colbert.infra import ColBERTConfig
 from colbert.modeling.checkpoint import Checkpoint
 
-from open_webui.env import SRC_LOG_LEVELS
 
 from open_webui.retrieval.models.base_reranker import BaseReranker
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class ColBERT(BaseReranker):

backend/open_webui/retrieval/models/external.py

@@ -4,12 +4,12 @@ from typing import Optional, List, Tuple
 from urllib.parse import quote
 
 
-from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, SRC_LOG_LEVELS
+from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, REQUESTS_VERIFY
 from open_webui.retrieval.models.base_reranker import BaseReranker
+from open_webui.utils.headers import include_user_info_headers
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class ExternalReranker(BaseReranker):
@@ -18,10 +18,12 @@ class ExternalReranker(BaseReranker):
         api_key: str,
         url: str = "http://localhost:8080/v1/rerank",
         model: str = "reranker",
+        timeout: Optional[int] = None,
     ):
         self.api_key = api_key
         self.url = url
         self.model = model
+        self.timeout = timeout
 
     def predict(
         self, sentences: List[Tuple[str, str]], user=None
@@ -40,23 +42,20 @@ class ExternalReranker(BaseReranker):
             log.info(f"ExternalReranker:predict:model {self.model}")
             log.info(f"ExternalReranker:predict:query {query}")
 
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {self.api_key}",
+            }
+
+            if ENABLE_FORWARD_USER_INFO_HEADERS and user:
+                headers = include_user_info_headers(headers, user)
+
             r = requests.post(
                 f"{self.url}",
-                headers={
-                    "Content-Type": "application/json",
-                    "Authorization": f"Bearer {self.api_key}",
-                    **(
-                        {
-                            "X-OpenWebUI-User-Name": quote(user.name, safe=" "),
-                            "X-OpenWebUI-User-Id": user.id,
-                            "X-OpenWebUI-User-Email": user.email,
-                            "X-OpenWebUI-User-Role": user.role,
-                        }
-                        if ENABLE_FORWARD_USER_INFO_HEADERS and user
-                        else {}
-                    ),
-                },
+                headers=headers,
                 json=payload,
+                timeout=self.timeout,
+                verify=REQUESTS_VERIFY,
             )
 
             r.raise_for_status()

backend/open_webui/retrieval/utils.py

@@ -1,8 +1,10 @@
 import logging
 import os
-from typing import Optional, Union
+from typing import Awaitable, Optional, Union
 
 import requests
+import aiohttp
+import asyncio
 import hashlib
 from concurrent.futures import ThreadPoolExecutor
 import time
@@ -10,7 +12,10 @@ import re
 
 from urllib.parse import quote
 from huggingface_hub import snapshot_download
-from langchain.retrievers import ContextualCompressionRetriever, EnsembleRetriever
+from langchain_classic.retrievers import (
+    ContextualCompressionRetriever,
+    EnsembleRetriever,
+)
 from langchain_community.retrievers import BM25Retriever
 from langchain_core.documents import Document
 
@@ -27,6 +32,7 @@ from open_webui.models.notes import Notes
 
 from open_webui.retrieval.vector.main import GetResult
 from open_webui.utils.access_control import has_access
+from open_webui.utils.headers import include_user_info_headers
 from open_webui.utils.misc import get_message_list
 
 from open_webui.retrieval.web.utils import get_web_loader
@@ -34,9 +40,10 @@ from open_webui.retrieval.loaders.youtube import YoutubeLoader
 
 
 from open_webui.env import (
-    SRC_LOG_LEVELS,
+    AIOHTTP_CLIENT_TIMEOUT,
     OFFLINE_MODE,
     ENABLE_FORWARD_USER_INFO_HEADERS,
+    AIOHTTP_CLIENT_SESSION_SSL,
 )
 from open_webui.config import (
     RAG_EMBEDDING_QUERY_PREFIX,
@@ -45,7 +52,6 @@ from open_webui.config import (
 )
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 from typing import Any
@@ -88,14 +94,29 @@ class VectorSearchRetriever(BaseRetriever):
     top_k: int
 
     def _get_relevant_documents(
+        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
+    ) -> list[Document]:
+        """Get documents relevant to a query.
+
+        Args:
+            query: String to find relevant documents for.
+            run_manager: The callback handler to use.
+
+        Returns:
+            List of relevant documents.
+        """
+        return []
+
+    async def _aget_relevant_documents(
         self,
         query: str,
         *,
         run_manager: CallbackManagerForRetrieverRun,
     ) -> list[Document]:
+        embedding = await self.embedding_function(query, RAG_EMBEDDING_QUERY_PREFIX)
         result = VECTOR_DB_CLIENT.search(
             collection_name=self.collection_name,
-            vectors=[self.embedding_function(query, RAG_EMBEDDING_QUERY_PREFIX)],
+            vectors=[embedding],
             limit=self.top_k,
         )
 
@@ -148,7 +169,45 @@ def get_doc(collection_name: str, user: UserModel = None):
         raise e
 
 
-def query_doc_with_hybrid_search(
+def get_enriched_texts(collection_result: GetResult) -> list[str]:
+    enriched_texts = []
+    for idx, text in enumerate(collection_result.documents[0]):
+        metadata = collection_result.metadatas[0][idx]
+        metadata_parts = [text]
+
+        # Add filename (repeat twice for extra weight in BM25 scoring)
+        if metadata.get("name"):
+            filename = metadata["name"]
+            filename_tokens = (
+                filename.replace("_", " ").replace("-", " ").replace(".", " ")
+            )
+            metadata_parts.append(
+                f"Filename: {filename} {filename_tokens} {filename_tokens}"
+            )
+
+        # Add title if available
+        if metadata.get("title"):
+            metadata_parts.append(f"Title: {metadata['title']}")
+
+        # Add document section headings if available (from markdown splitter)
+        if metadata.get("headings") and isinstance(metadata["headings"], list):
+            headings = " > ".join(str(h) for h in metadata["headings"])
+            metadata_parts.append(f"Section: {headings}")
+
+        # Add source URL/path if available
+        if metadata.get("source"):
+            metadata_parts.append(f"Source: {metadata['source']}")
+
+        # Add snippet for web search results
+        if metadata.get("snippet"):
+            metadata_parts.append(f"Snippet: {metadata['snippet']}")
+
+        enriched_texts.append(" ".join(metadata_parts))
+
+    return enriched_texts
+
+
+async def query_doc_with_hybrid_search(
     collection_name: str,
     collection_result: GetResult,
     query: str,
@@ -158,12 +217,21 @@ def query_doc_with_hybrid_search(
     k_reranker: int,
     r: float,
     hybrid_bm25_weight: float,
+    enable_enriched_texts: bool = False,
 ) -> dict:
     try:
+        # First check if collection_result has the required attributes
         if (
             not collection_result
             or not hasattr(collection_result, "documents")
-            or not collection_result.documents
+            or not hasattr(collection_result, "metadatas")
+        ):
+            log.warning(f"query_doc_with_hybrid_search:no_docs {collection_name}")
+            return {"documents": [], "metadatas": [], "distances": []}
+
+        # Now safely check the documents content after confirming attributes exist
+        if (
+            not collection_result.documents
             or len(collection_result.documents) == 0
             or not collection_result.documents[0]
         ):
@@ -172,8 +240,14 @@ def query_doc_with_hybrid_search(
 
         log.debug(f"query_doc_with_hybrid_search:doc {collection_name}")
 
+        bm25_texts = (
+            get_enriched_texts(collection_result)
+            if enable_enriched_texts
+            else collection_result.documents[0]
+        )
+
         bm25_retriever = BM25Retriever.from_texts(
-            texts=collection_result.documents[0],
+            texts=bm25_texts,
             metadatas=collection_result.metadatas[0],
         )
         bm25_retriever.k = k
@@ -209,7 +283,7 @@ def query_doc_with_hybrid_search(
             base_compressor=compressor, base_retriever=ensemble_retriever
         )
 
-        result = compression_retriever.invoke(query)
+        result = await compression_retriever.ainvoke(query)
 
         distances = [d.metadata.get("score") for d in result]
         documents = [d.page_content for d in result]
@@ -328,7 +402,7 @@ def get_all_items_from_collections(collection_names: list[str]) -> dict:
     return merge_get_results(results)
 
 
-def query_collection(
+async def query_collection(
     collection_names: list[str],
     queries: list[str],
     embedding_function,
@@ -353,7 +427,9 @@ def query_collection(
             return None, e
 
     # Generate all query embeddings (in one call)
-    query_embeddings = embedding_function(queries, prefix=RAG_EMBEDDING_QUERY_PREFIX)
+    query_embeddings = await embedding_function(
+        queries, prefix=RAG_EMBEDDING_QUERY_PREFIX
+    )
     log.debug(
         f"query_collection: processing {len(queries)} queries across {len(collection_names)} collections"
     )
@@ -380,7 +456,7 @@ def query_collection(
     return merge_and_sort_query_results(results, k=k)
 
 
-def query_collection_with_hybrid_search(
+async def query_collection_with_hybrid_search(
     collection_names: list[str],
     queries: list[str],
     embedding_function,
@@ -389,6 +465,7 @@ def query_collection_with_hybrid_search(
     k_reranker: int,
     r: float,
     hybrid_bm25_weight: float,
+    enable_enriched_texts: bool = False,
 ) -> dict:
     results = []
     error = False
@@ -411,9 +488,9 @@ def query_collection_with_hybrid_search(
         f"Starting hybrid search for {len(queries)} queries in {len(collection_names)} collections..."
     )
 
-    def process_query(collection_name, query):
+    async def process_query(collection_name, query):
         try:
-            result = query_doc_with_hybrid_search(
+            result = await query_doc_with_hybrid_search(
                 collection_name=collection_name,
                 collection_result=collection_results[collection_name],
                 query=query,
@@ -423,6 +500,7 @@ def query_collection_with_hybrid_search(
                 k_reranker=k_reranker,
                 r=r,
                 hybrid_bm25_weight=hybrid_bm25_weight,
+                enable_enriched_texts=enable_enriched_texts,
             )
             return result, None
         except Exception as e:
@@ -432,15 +510,16 @@ def query_collection_with_hybrid_search(
     # Prepare tasks for all collections and queries
     # Avoid running any tasks for collections that failed to fetch data (have assigned None)
     tasks = [
-        (cn, q)
-        for cn in collection_names
-        if collection_results[cn] is not None
-        for q in queries
+        (collection_name, query)
+        for collection_name in collection_names
+        if collection_results[collection_name] is not None
+        for query in queries
     ]
 
-    with ThreadPoolExecutor() as executor:
-        future_results = [executor.submit(process_query, cn, q) for cn, q in tasks]
-        task_results = [future.result() for future in future_results]
+    # Run all queries in parallel using asyncio.gather
+    task_results = await asyncio.gather(
+        *[process_query(collection_name, query) for collection_name, query in tasks]
+    )
 
     for result, err in task_results:
         if err is not None:
@@ -456,6 +535,257 @@ def query_collection_with_hybrid_search(
     return merge_and_sort_query_results(results, k=k)
 
 
+def generate_openai_batch_embeddings(
+    model: str,
+    texts: list[str],
+    url: str = "https://api.openai.com/v1",
+    key: str = "",
+    prefix: str = None,
+    user: UserModel = None,
+) -> Optional[list[list[float]]]:
+    try:
+        log.debug(
+            f"generate_openai_batch_embeddings:model {model} batch size: {len(texts)}"
+        )
+        json_data = {"input": texts, "model": model}
+        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
+            json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
+
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {key}",
+        }
+        if ENABLE_FORWARD_USER_INFO_HEADERS and user:
+            headers = include_user_info_headers(headers, user)
+
+        r = requests.post(
+            f"{url}/embeddings",
+            headers=headers,
+            json=json_data,
+        )
+        r.raise_for_status()
+        data = r.json()
+        if "data" in data:
+            return [elem["embedding"] for elem in data["data"]]
+        else:
+            raise "Something went wrong :/"
+    except Exception as e:
+        log.exception(f"Error generating openai batch embeddings: {e}")
+        return None
+
+
+async def agenerate_openai_batch_embeddings(
+    model: str,
+    texts: list[str],
+    url: str = "https://api.openai.com/v1",
+    key: str = "",
+    prefix: str = None,
+    user: UserModel = None,
+) -> Optional[list[list[float]]]:
+    try:
+        log.debug(
+            f"agenerate_openai_batch_embeddings:model {model} batch size: {len(texts)}"
+        )
+        form_data = {"input": texts, "model": model}
+        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
+            form_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
+
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {key}",
+        }
+        if ENABLE_FORWARD_USER_INFO_HEADERS and user:
+            headers = include_user_info_headers(headers, user)
+
+        async with aiohttp.ClientSession(
+            trust_env=True, timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
+        ) as session:
+            async with session.post(
+                f"{url}/embeddings", headers=headers, json=form_data
+            ) as r:
+                r.raise_for_status()
+                data = await r.json()
+                if "data" in data:
+                    return [item["embedding"] for item in data["data"]]
+                else:
+                    raise Exception("Something went wrong :/")
+    except Exception as e:
+        log.exception(f"Error generating openai batch embeddings: {e}")
+        return None
+
+
+def generate_azure_openai_batch_embeddings(
+    model: str,
+    texts: list[str],
+    url: str,
+    key: str = "",
+    version: str = "",
+    prefix: str = None,
+    user: UserModel = None,
+) -> Optional[list[list[float]]]:
+    try:
+        log.debug(
+            f"generate_azure_openai_batch_embeddings:deployment {model} batch size: {len(texts)}"
+        )
+        json_data = {"input": texts}
+        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
+            json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
+
+        url = f"{url}/openai/deployments/{model}/embeddings?api-version={version}"
+
+        for _ in range(5):
+            headers = {
+                "Content-Type": "application/json",
+                "api-key": key,
+            }
+            if ENABLE_FORWARD_USER_INFO_HEADERS and user:
+                headers = include_user_info_headers(headers, user)
+
+            r = requests.post(
+                url,
+                headers=headers,
+                json=json_data,
+            )
+            if r.status_code == 429:
+                retry = float(r.headers.get("Retry-After", "1"))
+                time.sleep(retry)
+                continue
+            r.raise_for_status()
+            data = r.json()
+            if "data" in data:
+                return [elem["embedding"] for elem in data["data"]]
+            else:
+                raise Exception("Something went wrong :/")
+        return None
+    except Exception as e:
+        log.exception(f"Error generating azure openai batch embeddings: {e}")
+        return None
+
+
+async def agenerate_azure_openai_batch_embeddings(
+    model: str,
+    texts: list[str],
+    url: str,
+    key: str = "",
+    version: str = "",
+    prefix: str = None,
+    user: UserModel = None,
+) -> Optional[list[list[float]]]:
+    try:
+        log.debug(
+            f"agenerate_azure_openai_batch_embeddings:deployment {model} batch size: {len(texts)}"
+        )
+        form_data = {"input": texts}
+        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
+            form_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
+
+        full_url = f"{url}/openai/deployments/{model}/embeddings?api-version={version}"
+
+        headers = {
+            "Content-Type": "application/json",
+            "api-key": key,
+        }
+        if ENABLE_FORWARD_USER_INFO_HEADERS and user:
+            headers = include_user_info_headers(headers, user)
+
+        async with aiohttp.ClientSession(
+            trust_env=True, timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
+        ) as session:
+            async with session.post(full_url, headers=headers, json=form_data) as r:
+                r.raise_for_status()
+                data = await r.json()
+                if "data" in data:
+                    return [item["embedding"] for item in data["data"]]
+                else:
+                    raise Exception("Something went wrong :/")
+    except Exception as e:
+        log.exception(f"Error generating azure openai batch embeddings: {e}")
+        return None
+
+
+def generate_ollama_batch_embeddings(
+    model: str,
+    texts: list[str],
+    url: str,
+    key: str = "",
+    prefix: str = None,
+    user: UserModel = None,
+) -> Optional[list[list[float]]]:
+    try:
+        log.debug(
+            f"generate_ollama_batch_embeddings:model {model} batch size: {len(texts)}"
+        )
+        json_data = {"input": texts, "model": model}
+        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
+            json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
+
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {key}",
+        }
+        if ENABLE_FORWARD_USER_INFO_HEADERS and user:
+            headers = include_user_info_headers(headers, user)
+
+        r = requests.post(
+            f"{url}/api/embed",
+            headers=headers,
+            json=json_data,
+        )
+        r.raise_for_status()
+        data = r.json()
+
+        if "embeddings" in data:
+            return data["embeddings"]
+        else:
+            raise "Something went wrong :/"
+    except Exception as e:
+        log.exception(f"Error generating ollama batch embeddings: {e}")
+        return None
+
+
+async def agenerate_ollama_batch_embeddings(
+    model: str,
+    texts: list[str],
+    url: str,
+    key: str = "",
+    prefix: str = None,
+    user: UserModel = None,
+) -> Optional[list[list[float]]]:
+    try:
+        log.debug(
+            f"agenerate_ollama_batch_embeddings:model {model} batch size: {len(texts)}"
+        )
+        form_data = {"input": texts, "model": model}
+        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
+            form_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
+
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {key}",
+        }
+        if ENABLE_FORWARD_USER_INFO_HEADERS and user:
+            headers = include_user_info_headers(headers, user)
+
+        async with aiohttp.ClientSession(
+            trust_env=True, timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
+        ) as session:
+            async with session.post(
+                f"{url}/api/embed",
+                headers=headers,
+                json=form_data,
+                ssl=AIOHTTP_CLIENT_SESSION_SSL,
+            ) as r:
+                r.raise_for_status()
+                data = await r.json()
+                if "embeddings" in data:
+                    return data["embeddings"]
+                else:
+                    raise Exception("Something went wrong :/")
+    except Exception as e:
+        log.exception(f"Error generating ollama batch embeddings: {e}")
+        return None
+
+
 def get_embedding_function(
     embedding_engine,
     embedding_model,
@@ -464,13 +794,26 @@ def get_embedding_function(
     key,
     embedding_batch_size,
     azure_api_version=None,
-):
+    enable_async=True,
+) -> Awaitable:
     if embedding_engine == "":
-        return lambda query, prefix=None, user=None: embedding_function.encode(
-            query, **({"prompt": prefix} if prefix else {})
-        ).tolist()
+        # Sentence transformers: CPU-bound sync operation
+        async def async_embedding_function(query, prefix=None, user=None):
+            return await asyncio.to_thread(
+                (
+                    lambda query, prefix=None: embedding_function.encode(
+                        query,
+                        batch_size=int(embedding_batch_size),
+                        **({"prompt": prefix} if prefix else {}),
+                    ).tolist()
+                ),
+                query,
+                prefix,
+            )
+
+        return async_embedding_function
     elif embedding_engine in ["ollama", "openai", "azure_openai"]:
-        func = lambda query, prefix=None, user=None: generate_embeddings(
+        embedding_function = lambda query, prefix=None, user=None: generate_embeddings(
             engine=embedding_engine,
             model=embedding_model,
             text=query,
@@ -481,41 +824,114 @@ def get_embedding_function(
             azure_api_version=azure_api_version,
         )
 
-        def generate_multiple(query, prefix, user, func):
+        async def async_embedding_function(query, prefix=None, user=None):
             if isinstance(query, list):
-                embeddings = []
-                for i in range(0, len(query), embedding_batch_size):
-                    batch_embeddings = func(
-                        query[i : i + embedding_batch_size],
-                        prefix=prefix,
-                        user=user,
-                    )
+                # Create batches
+                batches = [
+                    query[i : i + embedding_batch_size]
+                    for i in range(0, len(query), embedding_batch_size)
+                ]
 
+                if enable_async:
+                    log.debug(
+                        f"generate_multiple_async: Processing {len(batches)} batches in parallel"
+                    )
+                    # Execute all batches in parallel
+                    tasks = [
+                        embedding_function(batch, prefix=prefix, user=user)
+                        for batch in batches
+                    ]
+                    batch_results = await asyncio.gather(*tasks)
+                else:
+                    log.debug(
+                        f"generate_multiple_async: Processing {len(batches)} batches sequentially"
+                    )
+                    batch_results = []
+                    for batch in batches:
+                        batch_results.append(
+                            await embedding_function(batch, prefix=prefix, user=user)
+                        )
+
+                # Flatten results
+                embeddings = []
+                for batch_embeddings in batch_results:
                     if isinstance(batch_embeddings, list):
                         embeddings.extend(batch_embeddings)
+
+                log.debug(
+                    f"generate_multiple_async: Generated {len(embeddings)} embeddings from {len(batches)} parallel batches"
+                )
                 return embeddings
             else:
-                return func(query, prefix, user)
+                return await embedding_function(query, prefix, user)
 
-        return lambda query, prefix=None, user=None: generate_multiple(
-            query, prefix, user, func
-        )
+        return async_embedding_function
     else:
         raise ValueError(f"Unknown embedding engine: {embedding_engine}")
 
 
+async def generate_embeddings(
+    engine: str,
+    model: str,
+    text: Union[str, list[str]],
+    prefix: Union[str, None] = None,
+    **kwargs,
+):
+    url = kwargs.get("url", "")
+    key = kwargs.get("key", "")
+    user = kwargs.get("user")
+
+    if prefix is not None and RAG_EMBEDDING_PREFIX_FIELD_NAME is None:
+        if isinstance(text, list):
+            text = [f"{prefix}{text_element}" for text_element in text]
+        else:
+            text = f"{prefix}{text}"
+
+    if engine == "ollama":
+        embeddings = await agenerate_ollama_batch_embeddings(
+            **{
+                "model": model,
+                "texts": text if isinstance(text, list) else [text],
+                "url": url,
+                "key": key,
+                "prefix": prefix,
+                "user": user,
+            }
+        )
+        return embeddings[0] if isinstance(text, str) else embeddings
+    elif engine == "openai":
+        embeddings = await agenerate_openai_batch_embeddings(
+            model, text if isinstance(text, list) else [text], url, key, prefix, user
+        )
+        return embeddings[0] if isinstance(text, str) else embeddings
+    elif engine == "azure_openai":
+        azure_api_version = kwargs.get("azure_api_version", "")
+        embeddings = await agenerate_azure_openai_batch_embeddings(
+            model,
+            text if isinstance(text, list) else [text],
+            url,
+            key,
+            azure_api_version,
+            prefix,
+            user,
+        )
+        return embeddings[0] if isinstance(text, str) else embeddings
+
+
 def get_reranking_function(reranking_engine, reranking_model, reranking_function):
     if reranking_function is None:
         return None
     if reranking_engine == "external":
-        return lambda sentences, user=None: reranking_function.predict(
-            sentences, user=user
+        return lambda query, documents, user=None: reranking_function.predict(
+            [(query, doc.page_content) for doc in documents], user=user
         )
     else:
-        return lambda sentences, user=None: reranking_function.predict(sentences)
+        return lambda query, documents, user=None: reranking_function.predict(
+            [(query, doc.page_content) for doc in documents]
+        )
 
 
-def get_sources_from_items(
+async def get_sources_from_items(
     request,
     items,
     queries,
@@ -686,23 +1102,19 @@ def get_sources_from_items(
                         or knowledge_base.user_id == user.id
                         or has_access(user.id, "read", knowledge_base.access_control)
                     ):
-
-                        file_ids = knowledge_base.data.get("file_ids", [])
+                        files = Knowledges.get_files_by_id(knowledge_base.id)
 
                         documents = []
                         metadatas = []
-                        for file_id in file_ids:
-                            file_object = Files.get_file_by_id(file_id)
-
-                            if file_object:
-                                documents.append(file_object.data.get("content", ""))
-                                metadatas.append(
-                                    {
-                                        "file_id": file_id,
-                                        "name": file_object.filename,
-                                        "source": file_object.filename,
-                                    }
-                                )
+                        for file in files:
+                            documents.append(file.data.get("content", ""))
+                            metadatas.append(
+                                {
+                                    "file_id": file.id,
+                                    "name": file.filename,
+                                    "source": file.filename,
+                                }
+                            )
 
                         query_result = {
                             "documents": [documents],
@@ -743,7 +1155,7 @@ def get_sources_from_items(
                     query_result = None  # Initialize to None
                     if hybrid_search:
                         try:
-                            query_result = query_collection_with_hybrid_search(
+                            query_result = await query_collection_with_hybrid_search(
                                 collection_names=collection_names,
                                 queries=queries,
                                 embedding_function=embedding_function,
@@ -752,6 +1164,7 @@ def get_sources_from_items(
                                 k_reranker=k_reranker,
                                 r=r,
                                 hybrid_bm25_weight=hybrid_bm25_weight,
+                                enable_enriched_texts=request.app.state.config.ENABLE_RAG_HYBRID_SEARCH_ENRICHED_TEXTS,
                             )
                         except Exception as e:
                             log.debug(
@@ -760,7 +1173,7 @@ def get_sources_from_items(
 
                     # fallback to non-hybrid search
                     if not hybrid_search and query_result is None:
-                        query_result = query_collection(
+                        query_result = await query_collection(
                             collection_names=collection_names,
                             queries=queries,
                             embedding_function=embedding_function,
@@ -836,199 +1249,6 @@ def get_model_path(model: str, update_model: bool = False):
         return model
 
 
-def generate_openai_batch_embeddings(
-    model: str,
-    texts: list[str],
-    url: str = "https://api.openai.com/v1",
-    key: str = "",
-    prefix: str = None,
-    user: UserModel = None,
-) -> Optional[list[list[float]]]:
-    try:
-        log.debug(
-            f"generate_openai_batch_embeddings:model {model} batch size: {len(texts)}"
-        )
-        json_data = {"input": texts, "model": model}
-        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
-            json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
-
-        r = requests.post(
-            f"{url}/embeddings",
-            headers={
-                "Content-Type": "application/json",
-                "Authorization": f"Bearer {key}",
-                **(
-                    {
-                        "X-OpenWebUI-User-Name": quote(user.name, safe=" "),
-                        "X-OpenWebUI-User-Id": user.id,
-                        "X-OpenWebUI-User-Email": user.email,
-                        "X-OpenWebUI-User-Role": user.role,
-                    }
-                    if ENABLE_FORWARD_USER_INFO_HEADERS and user
-                    else {}
-                ),
-            },
-            json=json_data,
-        )
-        r.raise_for_status()
-        data = r.json()
-        if "data" in data:
-            return [elem["embedding"] for elem in data["data"]]
-        else:
-            raise "Something went wrong :/"
-    except Exception as e:
-        log.exception(f"Error generating openai batch embeddings: {e}")
-        return None
-
-
-def generate_azure_openai_batch_embeddings(
-    model: str,
-    texts: list[str],
-    url: str,
-    key: str = "",
-    version: str = "",
-    prefix: str = None,
-    user: UserModel = None,
-) -> Optional[list[list[float]]]:
-    try:
-        log.debug(
-            f"generate_azure_openai_batch_embeddings:deployment {model} batch size: {len(texts)}"
-        )
-        json_data = {"input": texts}
-        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
-            json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
-
-        url = f"{url}/openai/deployments/{model}/embeddings?api-version={version}"
-
-        for _ in range(5):
-            r = requests.post(
-                url,
-                headers={
-                    "Content-Type": "application/json",
-                    "api-key": key,
-                    **(
-                        {
-                            "X-OpenWebUI-User-Name": quote(user.name, safe=" "),
-                            "X-OpenWebUI-User-Id": user.id,
-                            "X-OpenWebUI-User-Email": user.email,
-                            "X-OpenWebUI-User-Role": user.role,
-                        }
-                        if ENABLE_FORWARD_USER_INFO_HEADERS and user
-                        else {}
-                    ),
-                },
-                json=json_data,
-            )
-            if r.status_code == 429:
-                retry = float(r.headers.get("Retry-After", "1"))
-                time.sleep(retry)
-                continue
-            r.raise_for_status()
-            data = r.json()
-            if "data" in data:
-                return [elem["embedding"] for elem in data["data"]]
-            else:
-                raise Exception("Something went wrong :/")
-        return None
-    except Exception as e:
-        log.exception(f"Error generating azure openai batch embeddings: {e}")
-        return None
-
-
-def generate_ollama_batch_embeddings(
-    model: str,
-    texts: list[str],
-    url: str,
-    key: str = "",
-    prefix: str = None,
-    user: UserModel = None,
-) -> Optional[list[list[float]]]:
-    try:
-        log.debug(
-            f"generate_ollama_batch_embeddings:model {model} batch size: {len(texts)}"
-        )
-        json_data = {"input": texts, "model": model}
-        if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
-            json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
-
-        r = requests.post(
-            f"{url}/api/embed",
-            headers={
-                "Content-Type": "application/json",
-                "Authorization": f"Bearer {key}",
-                **(
-                    {
-                        "X-OpenWebUI-User-Name": quote(user.name, safe=" "),
-                        "X-OpenWebUI-User-Id": user.id,
-                        "X-OpenWebUI-User-Email": user.email,
-                        "X-OpenWebUI-User-Role": user.role,
-                    }
-                    if ENABLE_FORWARD_USER_INFO_HEADERS
-                    else {}
-                ),
-            },
-            json=json_data,
-        )
-        r.raise_for_status()
-        data = r.json()
-
-        if "embeddings" in data:
-            return data["embeddings"]
-        else:
-            raise "Something went wrong :/"
-    except Exception as e:
-        log.exception(f"Error generating ollama batch embeddings: {e}")
-        return None
-
-
-def generate_embeddings(
-    engine: str,
-    model: str,
-    text: Union[str, list[str]],
-    prefix: Union[str, None] = None,
-    **kwargs,
-):
-    url = kwargs.get("url", "")
-    key = kwargs.get("key", "")
-    user = kwargs.get("user")
-
-    if prefix is not None and RAG_EMBEDDING_PREFIX_FIELD_NAME is None:
-        if isinstance(text, list):
-            text = [f"{prefix}{text_element}" for text_element in text]
-        else:
-            text = f"{prefix}{text}"
-
-    if engine == "ollama":
-        embeddings = generate_ollama_batch_embeddings(
-            **{
-                "model": model,
-                "texts": text if isinstance(text, list) else [text],
-                "url": url,
-                "key": key,
-                "prefix": prefix,
-                "user": user,
-            }
-        )
-        return embeddings[0] if isinstance(text, str) else embeddings
-    elif engine == "openai":
-        embeddings = generate_openai_batch_embeddings(
-            model, text if isinstance(text, list) else [text], url, key, prefix, user
-        )
-        return embeddings[0] if isinstance(text, str) else embeddings
-    elif engine == "azure_openai":
-        azure_api_version = kwargs.get("azure_api_version", "")
-        embeddings = generate_azure_openai_batch_embeddings(
-            model,
-            text if isinstance(text, list) else [text],
-            url,
-            key,
-            azure_api_version,
-            prefix,
-            user,
-        )
-        return embeddings[0] if isinstance(text, str) else embeddings
-
-
 import operator
 from typing import Optional, Sequence
 
@@ -1051,19 +1271,38 @@ class RerankCompressor(BaseDocumentCompressor):
         documents: Sequence[Document],
         query: str,
         callbacks: Optional[Callbacks] = None,
+    ) -> Sequence[Document]:
+        """Compress retrieved documents given the query context.
+
+        Args:
+            documents: The retrieved documents.
+            query: The query context.
+            callbacks: Optional callbacks to run during compression.
+
+        Returns:
+            The compressed documents.
+
+        """
+        return []
+
+    async def acompress_documents(
+        self,
+        documents: Sequence[Document],
+        query: str,
+        callbacks: Optional[Callbacks] = None,
     ) -> Sequence[Document]:
         reranking = self.reranking_function is not None
 
         scores = None
         if reranking:
-            scores = self.reranking_function(
-                [(query, doc.page_content) for doc in documents]
-            )
+            scores = await asyncio.to_thread(self.reranking_function, query, documents)
         else:
             from sentence_transformers import util
 
-            query_embedding = self.embedding_function(query, RAG_EMBEDDING_QUERY_PREFIX)
-            document_embedding = self.embedding_function(
+            query_embedding = await self.embedding_function(
+                query, RAG_EMBEDDING_QUERY_PREFIX
+            )
+            document_embedding = await self.embedding_function(
                 [doc.page_content for doc in documents], RAG_EMBEDDING_CONTENT_PREFIX
             )
             scores = util.cos_sim(query_embedding, document_embedding)[0]

backend/open_webui/retrieval/vector/dbs/chroma.py

@@ -24,10 +24,8 @@ from open_webui.config import (
     CHROMA_CLIENT_AUTH_PROVIDER,
     CHROMA_CLIENT_AUTH_CREDENTIALS,
 )
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class ChromaClient(VectorDBBase):
@@ -71,7 +69,11 @@ class ChromaClient(VectorDBBase):
         return self.client.delete_collection(name=collection_name)
 
     def search(
-        self, collection_name: str, vectors: list[list[float | int]], limit: int
+        self,
+        collection_name: str,
+        vectors: list[list[float | int]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
         try:
@@ -80,6 +82,7 @@ class ChromaClient(VectorDBBase):
                 result = collection.query(
                     query_embeddings=vectors,
                     n_results=limit,
+                    where=filter,
                 )
 
                 # chromadb has cosine distance, 2 (worst) -> 0 (best). Re-odering to 0 -> 1

backend/open_webui/retrieval/vector/dbs/elasticsearch.py

@@ -153,7 +153,11 @@ class ElasticsearchClient(VectorDBBase):
 
     # Status: works
     def search(
-        self, collection_name: str, vectors: list[list[float]], limit: int
+        self,
+        collection_name: str,
+        vectors: list[list[float]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         query = {
             "size": limit,

backend/open_webui/retrieval/vector/dbs/milvus.py

@@ -25,10 +25,8 @@ from open_webui.config import (
     MILVUS_DISKANN_MAX_DEGREE,
     MILVUS_DISKANN_SEARCH_LIST_SIZE,
 )
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class MilvusClient(VectorDBBase):
@@ -181,7 +179,11 @@ class MilvusClient(VectorDBBase):
         )
 
     def search(
-        self, collection_name: str, vectors: list[list[float | int]], limit: int
+        self,
+        collection_name: str,
+        vectors: list[list[float | int]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
         collection_name = collection_name.replace("-", "_")
@@ -200,23 +202,24 @@ class MilvusClient(VectorDBBase):
     def query(self, collection_name: str, filter: dict, limit: int = -1):
         connections.connect(uri=MILVUS_URI, token=MILVUS_TOKEN, db_name=MILVUS_DB)
 
-        # Construct the filter string for querying
         collection_name = collection_name.replace("-", "_")
         if not self.has_collection(collection_name):
             log.warning(
                 f"Query attempted on non-existent collection: {self.collection_prefix}_{collection_name}"
             )
             return None
-        filter_string = " && ".join(
-            [
-                f'metadata["{key}"] == {json.dumps(value)}'
-                for key, value in filter.items()
-            ]
-        )
+
+        filter_expressions = []
+        for key, value in filter.items():
+            if isinstance(value, str):
+                filter_expressions.append(f'metadata["{key}"] == "{value}"')
+            else:
+                filter_expressions.append(f'metadata["{key}"] == {value}')
+
+        filter_string = " && ".join(filter_expressions)
 
         collection = Collection(f"{self.collection_prefix}_{collection_name}")
         collection.load()
-        all_results = []
 
         try:
             log.info(
@@ -224,24 +227,25 @@ class MilvusClient(VectorDBBase):
             )
 
             iterator = collection.query_iterator(
-                filter=filter_string,
+                expr=filter_string,
                 output_fields=[
                     "id",
                     "data",
                     "metadata",
                 ],
-                limit=limit,  # Pass the limit directly; -1 means no limit.
+                limit=limit if limit > 0 else -1,
             )
 
+            all_results = []
             while True:
-                result = iterator.next()
-                if not result:
+                batch = iterator.next()
+                if not batch:
                     iterator.close()
                     break
-                all_results += result
+                all_results.extend(batch)
 
-            log.info(f"Total results from query: {len(all_results)}")
-            return self._result_to_get_result([all_results])
+            log.debug(f"Total results from query: {len(all_results)}")
+            return self._result_to_get_result([all_results] if all_results else [[]])
 
         except Exception as e:
             log.exception(

backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py

@@ -12,7 +12,6 @@ from open_webui.config import (
     MILVUS_HNSW_EFCONSTRUCTION,
     MILVUS_IVF_FLAT_NLIST,
 )
-from open_webui.env import SRC_LOG_LEVELS
 from open_webui.retrieval.vector.main import (
     GetResult,
     SearchResult,
@@ -29,7 +28,6 @@ from pymilvus import (
 )
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 RESOURCE_ID_FIELD = "resource_id"
 
@@ -157,10 +155,13 @@ class MilvusClient(VectorDBBase):
             for item in items
         ]
         collection.insert(entities)
-        collection.flush()
 
     def search(
-        self, collection_name: str, vectors: List[List[float]], limit: int
+        self,
+        collection_name: str,
+        vectors: List[List[float]],
+        filter: Optional[Dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         if not vectors:
             return None
@@ -263,15 +264,23 @@ class MilvusClient(VectorDBBase):
                 else:
                     expr.append(f"metadata['{key}'] == {value}")
 
-        results = collection.query(
+        iterator = collection.query_iterator(
             expr=" and ".join(expr),
             output_fields=["id", "text", "metadata"],
-            limit=limit,
+            limit=limit if limit else -1,
         )
 
-        ids = [res["id"] for res in results]
-        documents = [res["text"] for res in results]
-        metadatas = [res["metadata"] for res in results]
+        all_results = []
+        while True:
+            batch = iterator.next()
+            if not batch:
+                iterator.close()
+                break
+            all_results.extend(batch)
+
+        ids = [res["id"] for res in all_results]
+        documents = [res["text"] for res in all_results]
+        metadatas = [res["metadata"] for res in all_results]
 
         return GetResult(ids=[ids], documents=[documents], metadatas=[metadatas])
 

backend/open_webui/retrieval/vector/dbs/opengauss.py

@@ -0,0 +1,427 @@
+from typing import Optional, List, Dict, Any
+import logging
+import re
+import json
+from sqlalchemy import (
+    func,
+    literal,
+    cast,
+    column,
+    create_engine,
+    Column,
+    Integer,
+    MetaData,
+    LargeBinary,
+    select,
+    text,
+    Text,
+    Table,
+    values,
+)
+from sqlalchemy.sql import true
+from sqlalchemy.pool import NullPool, QueuePool
+
+from sqlalchemy.orm import declarative_base, scoped_session, sessionmaker
+from sqlalchemy.dialects.postgresql import JSONB, array
+from pgvector.sqlalchemy import Vector
+from sqlalchemy.ext.mutable import MutableDict
+from sqlalchemy.exc import NoSuchTableError
+
+from sqlalchemy.dialects.postgresql.psycopg2 import PGDialect_psycopg2
+from sqlalchemy.dialects import registry
+
+
+class OpenGaussDialect(PGDialect_psycopg2):
+    name = "opengauss"
+
+    def _get_server_version_info(self, connection):
+        try:
+            version = connection.exec_driver_sql("SELECT version()").scalar()
+            if not version:
+                return (9, 0, 0)
+
+            match = re.search(
+                r"openGauss\s+(\d+)\.(\d+)\.(\d+)(?:-\w+)?", version, re.IGNORECASE
+            )
+            if match:
+                return (int(match.group(1)), int(match.group(2)), int(match.group(3)))
+
+            return super()._get_server_version_info(connection)
+        except Exception:
+            return (9, 0, 0)
+
+
+# Register dialect
+registry.register("opengauss", __name__, "OpenGaussDialect")
+
+from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.retrieval.vector.main import (
+    VectorDBBase,
+    VectorItem,
+    SearchResult,
+    GetResult,
+)
+from open_webui.config import (
+    OPENGAUSS_DB_URL,
+    OPENGAUSS_INITIALIZE_MAX_VECTOR_LENGTH,
+    OPENGAUSS_POOL_SIZE,
+    OPENGAUSS_POOL_MAX_OVERFLOW,
+    OPENGAUSS_POOL_TIMEOUT,
+    OPENGAUSS_POOL_RECYCLE,
+)
+
+from open_webui.env import SRC_LOG_LEVELS
+
+VECTOR_LENGTH = OPENGAUSS_INITIALIZE_MAX_VECTOR_LENGTH
+Base = declarative_base()
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+class DocumentChunk(Base):
+    __tablename__ = "document_chunk"
+
+    id = Column(Text, primary_key=True)
+    vector = Column(Vector(dim=VECTOR_LENGTH), nullable=True)
+    collection_name = Column(Text, nullable=False)
+    text = Column(Text, nullable=True)
+    vmetadata = Column(MutableDict.as_mutable(JSONB), nullable=True)
+
+
+class OpenGaussClient(VectorDBBase):
+    def __init__(self) -> None:
+        if not OPENGAUSS_DB_URL:
+            from open_webui.internal.db import ScopedSession
+
+            self.session = ScopedSession
+        else:
+            engine_kwargs = {"pool_pre_ping": True, "dialect": OpenGaussDialect()}
+
+            if isinstance(OPENGAUSS_POOL_SIZE, int) and OPENGAUSS_POOL_SIZE > 0:
+                engine_kwargs.update(
+                    {
+                        "pool_size": OPENGAUSS_POOL_SIZE,
+                        "max_overflow": OPENGAUSS_POOL_MAX_OVERFLOW,
+                        "pool_timeout": OPENGAUSS_POOL_TIMEOUT,
+                        "pool_recycle": OPENGAUSS_POOL_RECYCLE,
+                        "poolclass": QueuePool,
+                    }
+                )
+            else:
+                engine_kwargs["poolclass"] = NullPool
+
+            engine = create_engine(OPENGAUSS_DB_URL, **engine_kwargs)
+
+            SessionLocal = sessionmaker(
+                autocommit=False, autoflush=False, bind=engine, expire_on_commit=False
+            )
+            self.session = scoped_session(SessionLocal)
+
+        try:
+            connection = self.session.connection()
+            Base.metadata.create_all(bind=connection)
+
+            self.session.execute(
+                text(
+                    "CREATE INDEX IF NOT EXISTS idx_document_chunk_vector "
+                    "ON document_chunk USING ivfflat (vector vector_cosine_ops) WITH (lists = 100);"
+                )
+            )
+            self.session.execute(
+                text(
+                    "CREATE INDEX IF NOT EXISTS idx_document_chunk_collection_name "
+                    "ON document_chunk (collection_name);"
+                )
+            )
+            self.session.commit()
+            log.info("OpenGauss vector database initialization completed.")
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"OpenGauss Initialization failed.: {e}")
+            raise
+
+    def check_vector_length(self) -> None:
+        metadata = MetaData()
+        try:
+            document_chunk_table = Table(
+                "document_chunk", metadata, autoload_with=self.session.bind
+            )
+        except NoSuchTableError:
+            return
+
+        if "vector" in document_chunk_table.columns:
+            vector_column = document_chunk_table.columns["vector"]
+            vector_type = vector_column.type
+            if isinstance(vector_type, Vector):
+                db_vector_length = vector_type.dim
+                if db_vector_length != VECTOR_LENGTH:
+                    raise Exception(
+                        f"Vector dimension mismatch: configured {VECTOR_LENGTH} vs. {db_vector_length} in the database."
+                    )
+            else:
+                raise Exception("The 'vector' column type is not Vector.")
+        else:
+            raise Exception(
+                "The 'vector' column does not exist in the 'document_chunk' table."
+            )
+
+    def adjust_vector_length(self, vector: List[float]) -> List[float]:
+        current_length = len(vector)
+        if current_length < VECTOR_LENGTH:
+            vector += [0.0] * (VECTOR_LENGTH - current_length)
+        elif current_length > VECTOR_LENGTH:
+            vector = vector[:VECTOR_LENGTH]
+        return vector
+
+    def insert(self, collection_name: str, items: List[VectorItem]) -> None:
+        try:
+            new_items = []
+            for item in items:
+                vector = self.adjust_vector_length(item["vector"])
+                new_chunk = DocumentChunk(
+                    id=item["id"],
+                    vector=vector,
+                    collection_name=collection_name,
+                    text=item["text"],
+                    vmetadata=process_metadata(item["metadata"]),
+                )
+                new_items.append(new_chunk)
+            self.session.bulk_save_objects(new_items)
+            self.session.commit()
+            log.info(
+                f"Inserting {len(new_items)} items into collection '{collection_name}'."
+            )
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Failed to insert data: {e}")
+            raise
+
+    def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
+        try:
+            for item in items:
+                vector = self.adjust_vector_length(item["vector"])
+                existing = (
+                    self.session.query(DocumentChunk)
+                    .filter(DocumentChunk.id == item["id"])
+                    .first()
+                )
+                if existing:
+                    existing.vector = vector
+                    existing.text = item["text"]
+                    existing.vmetadata = process_metadata(item["metadata"])
+                    existing.collection_name = collection_name
+                else:
+                    new_chunk = DocumentChunk(
+                        id=item["id"],
+                        vector=vector,
+                        collection_name=collection_name,
+                        text=item["text"],
+                        vmetadata=process_metadata(item["metadata"]),
+                    )
+                    self.session.add(new_chunk)
+            self.session.commit()
+            log.info(
+                f"Inserting/updating {len(items)} items in collection '{collection_name}'."
+            )
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Failed to insert or update data.: {e}")
+            raise
+
+    def search(
+        self,
+        collection_name: str,
+        vectors: List[List[float]],
+        filter: Optional[Dict[str, Any]] = None,
+        limit: int = 10,
+    ) -> Optional[SearchResult]:
+        try:
+            if not vectors:
+                return None
+
+            vectors = [self.adjust_vector_length(vector) for vector in vectors]
+            num_queries = len(vectors)
+
+            def vector_expr(vector):
+                return cast(array(vector), Vector(VECTOR_LENGTH))
+
+            qid_col = column("qid", Integer)
+            q_vector_col = column("q_vector", Vector(VECTOR_LENGTH))
+            query_vectors = (
+                values(qid_col, q_vector_col)
+                .data(
+                    [(idx, vector_expr(vector)) for idx, vector in enumerate(vectors)]
+                )
+                .alias("query_vectors")
+            )
+
+            result_fields = [
+                DocumentChunk.id,
+                DocumentChunk.text,
+                DocumentChunk.vmetadata,
+                (DocumentChunk.vector.cosine_distance(query_vectors.c.q_vector)).label(
+                    "distance"
+                ),
+            ]
+
+            subq = (
+                select(*result_fields)
+                .where(DocumentChunk.collection_name == collection_name)
+                .order_by(
+                    DocumentChunk.vector.cosine_distance(query_vectors.c.q_vector)
+                )
+            )
+            if limit is not None:
+                subq = subq.limit(limit)
+            subq = subq.lateral("result")
+
+            stmt = (
+                select(
+                    query_vectors.c.qid,
+                    subq.c.id,
+                    subq.c.text,
+                    subq.c.vmetadata,
+                    subq.c.distance,
+                )
+                .select_from(query_vectors)
+                .join(subq, true())
+                .order_by(query_vectors.c.qid, subq.c.distance)
+            )
+
+            result_proxy = self.session.execute(stmt)
+            results = result_proxy.all()
+
+            ids = [[] for _ in range(num_queries)]
+            distances = [[] for _ in range(num_queries)]
+            documents = [[] for _ in range(num_queries)]
+            metadatas = [[] for _ in range(num_queries)]
+
+            for row in results:
+                qid = int(row.qid)
+                ids[qid].append(row.id)
+                distances[qid].append((2.0 - row.distance) / 2.0)
+                documents[qid].append(row.text)
+                metadatas[qid].append(row.vmetadata)
+
+            self.session.rollback()
+            return SearchResult(
+                ids=ids, distances=distances, documents=documents, metadatas=metadatas
+            )
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Vector search failed: {e}")
+            return None
+
+    def query(
+        self, collection_name: str, filter: Dict[str, Any], limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        try:
+            query = self.session.query(DocumentChunk).filter(
+                DocumentChunk.collection_name == collection_name
+            )
+
+            for key, value in filter.items():
+                query = query.filter(DocumentChunk.vmetadata[key].astext == str(value))
+
+            if limit is not None:
+                query = query.limit(limit)
+
+            results = query.all()
+
+            if not results:
+                return None
+
+            ids = [[result.id for result in results]]
+            documents = [[result.text for result in results]]
+            metadatas = [[result.vmetadata for result in results]]
+
+            self.session.rollback()
+            return GetResult(ids=ids, documents=documents, metadatas=metadatas)
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Conditional query failed: {e}")
+            return None
+
+    def get(
+        self, collection_name: str, limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        try:
+            query = self.session.query(DocumentChunk).filter(
+                DocumentChunk.collection_name == collection_name
+            )
+            if limit is not None:
+                query = query.limit(limit)
+
+            results = query.all()
+
+            if not results:
+                return None
+
+            ids = [[result.id for result in results]]
+            documents = [[result.text for result in results]]
+            metadatas = [[result.vmetadata for result in results]]
+
+            self.session.rollback()
+            return GetResult(ids=ids, documents=documents, metadatas=metadatas)
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Failed to retrieve data: {e}")
+            return None
+
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[List[str]] = None,
+        filter: Optional[Dict[str, Any]] = None,
+    ) -> None:
+        try:
+            query = self.session.query(DocumentChunk).filter(
+                DocumentChunk.collection_name == collection_name
+            )
+            if ids:
+                query = query.filter(DocumentChunk.id.in_(ids))
+            if filter:
+                for key, value in filter.items():
+                    query = query.filter(
+                        DocumentChunk.vmetadata[key].astext == str(value)
+                    )
+            deleted = query.delete(synchronize_session=False)
+            self.session.commit()
+            log.info(f"Deleted {deleted} items from collection '{collection_name}'")
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Failed to delete data: {e}")
+            raise
+
+    def reset(self) -> None:
+        try:
+            deleted = self.session.query(DocumentChunk).delete()
+            self.session.commit()
+            log.info(f"Reset completed. Deleted {deleted} items")
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Reset failed: {e}")
+            raise
+
+    def close(self) -> None:
+        pass
+
+    def has_collection(self, collection_name: str) -> bool:
+        try:
+            exists = (
+                self.session.query(DocumentChunk)
+                .filter(DocumentChunk.collection_name == collection_name)
+                .first()
+                is not None
+            )
+            self.session.rollback()
+            return exists
+        except Exception as e:
+            self.session.rollback()
+            log.exception(f"Failed to check collection existence: {e}")
+            return False
+
+    def delete_collection(self, collection_name: str) -> None:
+        self.delete(collection_name)
+        log.info(f"Collection '{collection_name}' has been deleted")

backend/open_webui/retrieval/vector/dbs/opensearch.py

@@ -113,7 +113,11 @@ class OpenSearchClient(VectorDBBase):
         self.client.indices.delete(index=self._get_index_name(collection_name))
 
     def search(
-        self, collection_name: str, vectors: list[list[float | int]], limit: int
+        self,
+        collection_name: str,
+        vectors: list[list[float | int]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         try:
             if not self.has_collection(collection_name):

backend/open_webui/retrieval/vector/dbs/oracle23ai.py

@@ -55,10 +55,8 @@ from open_webui.config import (
     ORACLE_DB_POOL_MAX,
     ORACLE_DB_POOL_INCREMENT,
 )
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class Oracle23aiClient(VectorDBBase):
@@ -523,7 +521,11 @@ class Oracle23aiClient(VectorDBBase):
                 raise
 
     def search(
-        self, collection_name: str, vectors: List[List[Union[float, int]]], limit: int
+        self,
+        collection_name: str,
+        vectors: List[List[Union[float, int]]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         """
         Search for similar vectors in the database.

backend/open_webui/retrieval/vector/dbs/pgvector.py

@@ -1,4 +1,4 @@
-from typing import Optional, List, Dict, Any
+from typing import Optional, List, Dict, Any, Tuple
 import logging
 import json
 from sqlalchemy import (
@@ -22,7 +22,7 @@ from sqlalchemy.pool import NullPool, QueuePool
 
 from sqlalchemy.orm import declarative_base, scoped_session, sessionmaker
 from sqlalchemy.dialects.postgresql import JSONB, array
-from pgvector.sqlalchemy import Vector
+from pgvector.sqlalchemy import Vector, HALFVEC
 from sqlalchemy.ext.mutable import MutableDict
 from sqlalchemy.exc import NoSuchTableError
 
@@ -44,15 +44,22 @@ from open_webui.config import (
     PGVECTOR_POOL_MAX_OVERFLOW,
     PGVECTOR_POOL_TIMEOUT,
     PGVECTOR_POOL_RECYCLE,
+    PGVECTOR_INDEX_METHOD,
+    PGVECTOR_HNSW_M,
+    PGVECTOR_HNSW_EF_CONSTRUCTION,
+    PGVECTOR_IVFFLAT_LISTS,
+    PGVECTOR_USE_HALFVEC,
 )
 
-from open_webui.env import SRC_LOG_LEVELS
 
 VECTOR_LENGTH = PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH
+USE_HALFVEC = PGVECTOR_USE_HALFVEC
+
+VECTOR_TYPE_FACTORY = HALFVEC if USE_HALFVEC else Vector
+VECTOR_OPCLASS = "halfvec_cosine_ops" if USE_HALFVEC else "vector_cosine_ops"
 Base = declarative_base()
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def pgcrypto_encrypt(val, key):
@@ -67,7 +74,7 @@ class DocumentChunk(Base):
     __tablename__ = "document_chunk"
 
     id = Column(Text, primary_key=True)
-    vector = Column(Vector(dim=VECTOR_LENGTH), nullable=True)
+    vector = Column(VECTOR_TYPE_FACTORY(dim=VECTOR_LENGTH), nullable=True)
     collection_name = Column(Text, nullable=False)
 
     if PGVECTOR_PGCRYPTO:
@@ -83,9 +90,9 @@ class PgvectorClient(VectorDBBase):
 
         # if no pgvector uri, use the existing database connection
         if not PGVECTOR_DB_URL:
-            from open_webui.internal.db import Session
+            from open_webui.internal.db import ScopedSession
 
-            self.session = Session
+            self.session = ScopedSession
         else:
             if isinstance(PGVECTOR_POOL_SIZE, int):
                 if PGVECTOR_POOL_SIZE > 0:
@@ -157,13 +164,9 @@ class PgvectorClient(VectorDBBase):
             connection = self.session.connection()
             Base.metadata.create_all(bind=connection)
 
-            # Create an index on the vector column if it doesn't exist
-            self.session.execute(
-                text(
-                    "CREATE INDEX IF NOT EXISTS idx_document_chunk_vector "
-                    "ON document_chunk USING ivfflat (vector vector_cosine_ops) WITH (lists = 100);"
-                )
-            )
+            index_method, index_options = self._vector_index_configuration()
+            self._ensure_vector_index(index_method, index_options)
+
             self.session.execute(
                 text(
                     "CREATE INDEX IF NOT EXISTS idx_document_chunk_collection_name "
@@ -177,6 +180,78 @@ class PgvectorClient(VectorDBBase):
             log.exception(f"Error during initialization: {e}")
             raise
 
+    @staticmethod
+    def _extract_index_method(index_def: Optional[str]) -> Optional[str]:
+        if not index_def:
+            return None
+        try:
+            after_using = index_def.lower().split("using ", 1)[1]
+            return after_using.split()[0]
+        except (IndexError, AttributeError):
+            return None
+
+    def _vector_index_configuration(self) -> Tuple[str, str]:
+        if PGVECTOR_INDEX_METHOD:
+            index_method = PGVECTOR_INDEX_METHOD
+            log.info(
+                "Using vector index method '%s' from PGVECTOR_INDEX_METHOD.",
+                index_method,
+            )
+        elif USE_HALFVEC:
+            index_method = "hnsw"
+            log.info(
+                "VECTOR_LENGTH=%s exceeds 2000; using halfvec column type with hnsw index.",
+                VECTOR_LENGTH,
+            )
+        else:
+            index_method = "ivfflat"
+
+        if index_method == "hnsw":
+            index_options = f"WITH (m = {PGVECTOR_HNSW_M}, ef_construction = {PGVECTOR_HNSW_EF_CONSTRUCTION})"
+        else:
+            index_options = f"WITH (lists = {PGVECTOR_IVFFLAT_LISTS})"
+
+        return index_method, index_options
+
+    def _ensure_vector_index(self, index_method: str, index_options: str) -> None:
+        index_name = "idx_document_chunk_vector"
+        existing_index_def = self.session.execute(
+            text(
+                """
+                SELECT indexdef
+                FROM pg_indexes
+                WHERE schemaname = current_schema()
+                  AND tablename = 'document_chunk'
+                  AND indexname = :index_name
+                """
+            ),
+            {"index_name": index_name},
+        ).scalar()
+
+        existing_method = self._extract_index_method(existing_index_def)
+        if existing_method and existing_method != index_method:
+            raise RuntimeError(
+                f"Existing pgvector index '{index_name}' uses method '{existing_method}' but configuration now "
+                f"requires '{index_method}'. Automatic rebuild is disabled to prevent long-running maintenance. "
+                "Drop the index manually (optionally after tuning maintenance_work_mem/max_parallel_maintenance_workers) "
+                "and recreate it with the new method before restarting Open WebUI."
+            )
+
+        if not existing_index_def:
+            index_sql = (
+                f"CREATE INDEX IF NOT EXISTS {index_name} "
+                f"ON document_chunk USING {index_method} (vector {VECTOR_OPCLASS})"
+            )
+            if index_options:
+                index_sql = f"{index_sql} {index_options}"
+            self.session.execute(text(index_sql))
+            log.info(
+                "Ensured vector index '%s' using %s%s.",
+                index_name,
+                index_method,
+                f" {index_options}" if index_options else "",
+            )
+
     def check_vector_length(self) -> None:
         """
         Check if the VECTOR_LENGTH matches the existing vector column dimension in the database.
@@ -196,16 +271,19 @@ class PgvectorClient(VectorDBBase):
         if "vector" in document_chunk_table.columns:
             vector_column = document_chunk_table.columns["vector"]
             vector_type = vector_column.type
-            if isinstance(vector_type, Vector):
-                db_vector_length = vector_type.dim
-                if db_vector_length != VECTOR_LENGTH:
-                    raise Exception(
-                        f"VECTOR_LENGTH {VECTOR_LENGTH} does not match existing vector column dimension {db_vector_length}. "
-                        "Cannot change vector size after initialization without migrating the data."
-                    )
-            else:
+            expected_type = HALFVEC if USE_HALFVEC else Vector
+
+            if not isinstance(vector_type, expected_type):
                 raise Exception(
-                    "The 'vector' column exists but is not of type 'Vector'."
+                    "The 'vector' column type does not match the expected type "
+                    f"('{expected_type.__name__}') for VECTOR_LENGTH {VECTOR_LENGTH}."
+                )
+
+            db_vector_length = getattr(vector_type, "dim", None)
+            if db_vector_length is not None and db_vector_length != VECTOR_LENGTH:
+                raise Exception(
+                    f"VECTOR_LENGTH {VECTOR_LENGTH} does not match existing vector column dimension {db_vector_length}. "
+                    "Cannot change vector size after initialization without migrating the data."
                 )
         else:
             raise Exception(
@@ -349,7 +427,8 @@ class PgvectorClient(VectorDBBase):
         self,
         collection_name: str,
         vectors: List[List[float]],
-        limit: Optional[int] = None,
+        filter: Optional[Dict[str, Any]] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         try:
             if not vectors:
@@ -360,11 +439,11 @@ class PgvectorClient(VectorDBBase):
             num_queries = len(vectors)
 
             def vector_expr(vector):
-                return cast(array(vector), Vector(VECTOR_LENGTH))
+                return cast(array(vector), VECTOR_TYPE_FACTORY(VECTOR_LENGTH))
 
             # Create the values for query vectors
             qid_col = column("qid", Integer)
-            q_vector_col = column("q_vector", Vector(VECTOR_LENGTH))
+            q_vector_col = column("q_vector", VECTOR_TYPE_FACTORY(VECTOR_LENGTH))
             query_vectors = (
                 values(qid_col, q_vector_col)
                 .data(
@@ -397,9 +476,47 @@ class PgvectorClient(VectorDBBase):
             )
 
             # Build the lateral subquery for each query vector
+            where_clauses = [DocumentChunk.collection_name == collection_name]
+
+            # Apply metadata filter if provided
+            if filter:
+                for key, value in filter.items():
+                    if isinstance(value, dict) and "$in" in value:
+                        # Handle $in operator: {"field": {"$in": [values]}}
+                        in_values = value["$in"]
+                        if PGVECTOR_PGCRYPTO:
+                            where_clauses.append(
+                                pgcrypto_decrypt(
+                                    DocumentChunk.vmetadata,
+                                    PGVECTOR_PGCRYPTO_KEY,
+                                    JSONB,
+                                )[key].astext.in_([str(v) for v in in_values])
+                            )
+                        else:
+                            where_clauses.append(
+                                DocumentChunk.vmetadata[key].astext.in_(
+                                    [str(v) for v in in_values]
+                                )
+                            )
+                    else:
+                        # Handle simple equality: {"field": "value"}
+                        if PGVECTOR_PGCRYPTO:
+                            where_clauses.append(
+                                pgcrypto_decrypt(
+                                    DocumentChunk.vmetadata,
+                                    PGVECTOR_PGCRYPTO_KEY,
+                                    JSONB,
+                                )[key].astext
+                                == str(value)
+                            )
+                        else:
+                            where_clauses.append(
+                                DocumentChunk.vmetadata[key].astext == str(value)
+                            )
+
             subq = (
                 select(*result_fields)
-                .where(DocumentChunk.collection_name == collection_name)
+                .where(*where_clauses)
                 .order_by(
                     (DocumentChunk.vector.cosine_distance(query_vectors.c.q_vector))
                 )

backend/open_webui/retrieval/vector/dbs/pinecone.py

@@ -31,7 +31,6 @@ from open_webui.config import (
     PINECONE_METRIC,
     PINECONE_CLOUD,
 )
-from open_webui.env import SRC_LOG_LEVELS
 from open_webui.retrieval.vector.utils import process_metadata
 
 
@@ -39,7 +38,6 @@ NO_LIMIT = 10000  # Reasonable limit to avoid overwhelming the system
 BATCH_SIZE = 100  # Recommended batch size for Pinecone operations
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class PineconeClient(VectorDBBase):
@@ -393,7 +391,11 @@ class PineconeClient(VectorDBBase):
         )
 
     def search(
-        self, collection_name: str, vectors: List[List[Union[float, int]]], limit: int
+        self,
+        collection_name: str,
+        vectors: List[List[Union[float, int]]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         """Search for similar vectors in a collection."""
         if not vectors or not vectors[0]:

backend/open_webui/retrieval/vector/dbs/qdrant.py

@@ -22,12 +22,10 @@ from open_webui.config import (
     QDRANT_TIMEOUT,
     QDRANT_HNSW_M,
 )
-from open_webui.env import SRC_LOG_LEVELS
 
 NO_LIMIT = 999999999
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class QdrantClient(VectorDBBase):
@@ -147,7 +145,11 @@ class QdrantClient(VectorDBBase):
         )
 
     def search(
-        self, collection_name: str, vectors: list[list[float | int]], limit: int
+        self,
+        collection_name: str,
+        vectors: list[list[float | int]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
         if limit is None:

backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py

@@ -13,7 +13,6 @@ from open_webui.config import (
     QDRANT_TIMEOUT,
     QDRANT_HNSW_M,
 )
-from open_webui.env import SRC_LOG_LEVELS
 from open_webui.retrieval.vector.main import (
     GetResult,
     SearchResult,
@@ -30,7 +29,6 @@ TENANT_ID_FIELD = "tenant_id"
 DEFAULT_DIMENSION = 384
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def _tenant_filter(tenant_id: str) -> models.FieldCondition:
@@ -256,7 +254,11 @@ class QdrantClient(VectorDBBase):
         )
 
     def search(
-        self, collection_name: str, vectors: List[List[float | int]], limit: int
+        self,
+        collection_name: str,
+        vectors: List[List[float | int]],
+        filter: Optional[Dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         """
         Search for the nearest neighbor items based on the vectors with tenant isolation.

backend/open_webui/retrieval/vector/dbs/s3vector.py

@@ -6,13 +6,11 @@ from open_webui.retrieval.vector.main import (
     SearchResult,
 )
 from open_webui.config import S3_VECTOR_BUCKET_NAME, S3_VECTOR_REGION
-from open_webui.env import SRC_LOG_LEVELS
 from typing import List, Optional, Dict, Any, Union
 import logging
 import boto3
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class S3VectorClient(VectorDBBase):
@@ -117,15 +115,16 @@ class S3VectorClient(VectorDBBase):
 
     def has_collection(self, collection_name: str) -> bool:
         """
-        Check if a vector index (collection) exists in the S3 vector bucket.
+        Check if a vector index exists using direct lookup.
+        This avoids pagination issues with list_indexes() and is significantly faster.
         """
-
         try:
-            response = self.client.list_indexes(vectorBucketName=self.bucket_name)
-            indexes = response.get("indexes", [])
-            return any(idx.get("indexName") == collection_name for idx in indexes)
+            self.client.get_index(
+                vectorBucketName=self.bucket_name, indexName=collection_name
+            )
+            return True
         except Exception as e:
-            log.error(f"Error listing indexes: {e}")
+            log.error(f"Error checking if index '{collection_name}' exists: {e}")
             return False
 
     def delete_collection(self, collection_name: str) -> None:
@@ -296,7 +295,11 @@ class S3VectorClient(VectorDBBase):
             raise
 
     def search(
-        self, collection_name: str, vectors: List[List[Union[float, int]]], limit: int
+        self,
+        collection_name: str,
+        vectors: List[List[Union[float, int]]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         """
         Search for similar vectors in a collection using multiple query vectors.

backend/open_webui/retrieval/vector/dbs/weaviate.py

@@ -0,0 +1,344 @@
+import weaviate
+import re
+import uuid
+from typing import Any, Dict, List, Optional, Union
+
+from open_webui.retrieval.vector.main import (
+    VectorDBBase,
+    VectorItem,
+    SearchResult,
+    GetResult,
+)
+from open_webui.retrieval.vector.utils import process_metadata
+from open_webui.config import (
+    WEAVIATE_HTTP_HOST,
+    WEAVIATE_HTTP_PORT,
+    WEAVIATE_GRPC_PORT,
+    WEAVIATE_API_KEY,
+)
+
+
+def _convert_uuids_to_strings(obj: Any) -> Any:
+    """
+    Recursively convert UUID objects to strings in nested data structures.
+
+    This function handles:
+    - UUID objects -> string
+    - Dictionaries with UUID values
+    - Lists/Tuples with UUID values
+    - Nested combinations of the above
+
+    Args:
+        obj: Any object that might contain UUIDs
+
+    Returns:
+        The same object structure with UUIDs converted to strings
+    """
+    if isinstance(obj, uuid.UUID):
+        return str(obj)
+    elif isinstance(obj, dict):
+        return {key: _convert_uuids_to_strings(value) for key, value in obj.items()}
+    elif isinstance(obj, (list, tuple)):
+        return type(obj)(_convert_uuids_to_strings(item) for item in obj)
+    elif isinstance(obj, (str, int, float, bool, type(None))):
+        return obj
+    else:
+        return obj
+
+
+class WeaviateClient(VectorDBBase):
+    def __init__(self):
+        self.url = WEAVIATE_HTTP_HOST
+        try:
+            # Build connection parameters
+            connection_params = {
+                "host": WEAVIATE_HTTP_HOST,
+                "port": WEAVIATE_HTTP_PORT,
+                "grpc_port": WEAVIATE_GRPC_PORT,
+            }
+
+            # Only add auth_credentials if WEAVIATE_API_KEY exists and is not empty
+            if WEAVIATE_API_KEY:
+                connection_params["auth_credentials"] = (
+                    weaviate.classes.init.Auth.api_key(WEAVIATE_API_KEY)
+                )
+
+            self.client = weaviate.connect_to_local(**connection_params)
+            self.client.connect()
+        except Exception as e:
+            raise ConnectionError(f"Failed to connect to Weaviate: {e}") from e
+
+    def _sanitize_collection_name(self, collection_name: str) -> str:
+        """Sanitize collection name to be a valid Weaviate class name."""
+        if not isinstance(collection_name, str) or not collection_name.strip():
+            raise ValueError("Collection name must be a non-empty string")
+
+        # Requirements for a valid Weaviate class name:
+        # The collection name must begin with a capital letter.
+        # The name can only contain letters, numbers, and the underscore (_) character. Spaces are not allowed.
+
+        # Replace hyphens with underscores and keep only alphanumeric characters
+        name = re.sub(r"[^a-zA-Z0-9_]", "", collection_name.replace("-", "_"))
+        name = name.strip("_")
+
+        if not name:
+            raise ValueError(
+                "Could not sanitize collection name to be a valid Weaviate class name"
+            )
+
+        # Ensure it starts with a letter and is capitalized
+        if not name[0].isalpha():
+            name = "C" + name
+
+        return name[0].upper() + name[1:]
+
+    def has_collection(self, collection_name: str) -> bool:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        return self.client.collections.exists(sane_collection_name)
+
+    def delete_collection(self, collection_name: str) -> None:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        if self.client.collections.exists(sane_collection_name):
+            self.client.collections.delete(sane_collection_name)
+
+    def _create_collection(self, collection_name: str) -> None:
+        self.client.collections.create(
+            name=collection_name,
+            vector_config=weaviate.classes.config.Configure.Vectors.self_provided(),
+            properties=[
+                weaviate.classes.config.Property(
+                    name="text", data_type=weaviate.classes.config.DataType.TEXT
+                ),
+            ],
+        )
+
+    def insert(self, collection_name: str, items: List[VectorItem]) -> None:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        if not self.client.collections.exists(sane_collection_name):
+            self._create_collection(sane_collection_name)
+
+        collection = self.client.collections.get(sane_collection_name)
+
+        with collection.batch.fixed_size(batch_size=100) as batch:
+            for item in items:
+                item_uuid = str(uuid.uuid4()) if not item["id"] else str(item["id"])
+
+                properties = {"text": item["text"]}
+                if item["metadata"]:
+                    clean_metadata = _convert_uuids_to_strings(
+                        process_metadata(item["metadata"])
+                    )
+                    clean_metadata.pop("text", None)
+                    properties.update(clean_metadata)
+
+                batch.add_object(
+                    properties=properties, uuid=item_uuid, vector=item["vector"]
+                )
+
+    def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        if not self.client.collections.exists(sane_collection_name):
+            self._create_collection(sane_collection_name)
+
+        collection = self.client.collections.get(sane_collection_name)
+
+        with collection.batch.fixed_size(batch_size=100) as batch:
+            for item in items:
+                item_uuid = str(item["id"]) if item["id"] else None
+
+                properties = {"text": item["text"]}
+                if item["metadata"]:
+                    clean_metadata = _convert_uuids_to_strings(
+                        process_metadata(item["metadata"])
+                    )
+                    clean_metadata.pop("text", None)
+                    properties.update(clean_metadata)
+
+                batch.add_object(
+                    properties=properties, uuid=item_uuid, vector=item["vector"]
+                )
+
+    def search(
+        self,
+        collection_name: str,
+        vectors: List[List[Union[float, int]]],
+        filter: Optional[dict] = None,
+        limit: int = 10,
+    ) -> Optional[SearchResult]:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        if not self.client.collections.exists(sane_collection_name):
+            return None
+
+        collection = self.client.collections.get(sane_collection_name)
+
+        result_ids, result_documents, result_metadatas, result_distances = (
+            [],
+            [],
+            [],
+            [],
+        )
+
+        for vector_embedding in vectors:
+            try:
+                response = collection.query.near_vector(
+                    near_vector=vector_embedding,
+                    limit=limit,
+                    return_metadata=weaviate.classes.query.MetadataQuery(distance=True),
+                )
+
+                ids = [str(obj.uuid) for obj in response.objects]
+                documents = []
+                metadatas = []
+                distances = []
+
+                for obj in response.objects:
+                    properties = dict(obj.properties) if obj.properties else {}
+                    documents.append(properties.pop("text", ""))
+                    metadatas.append(_convert_uuids_to_strings(properties))
+
+                # Weaviate has cosine distance, 2 (worst) -> 0 (best). Re-ordering to 0 -> 1
+                raw_distances = [
+                    (
+                        obj.metadata.distance
+                        if obj.metadata and obj.metadata.distance
+                        else 2.0
+                    )
+                    for obj in response.objects
+                ]
+                distances = [(2 - dist) / 2 for dist in raw_distances]
+
+                result_ids.append(ids)
+                result_documents.append(documents)
+                result_metadatas.append(metadatas)
+                result_distances.append(distances)
+            except Exception:
+                result_ids.append([])
+                result_documents.append([])
+                result_metadatas.append([])
+                result_distances.append([])
+
+        return SearchResult(
+            **{
+                "ids": result_ids,
+                "documents": result_documents,
+                "metadatas": result_metadatas,
+                "distances": result_distances,
+            }
+        )
+
+    def query(
+        self, collection_name: str, filter: Dict, limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        if not self.client.collections.exists(sane_collection_name):
+            return None
+
+        collection = self.client.collections.get(sane_collection_name)
+
+        weaviate_filter = None
+        if filter:
+            for key, value in filter.items():
+                prop_filter = weaviate.classes.query.Filter.by_property(name=key).equal(
+                    value
+                )
+                weaviate_filter = (
+                    prop_filter
+                    if weaviate_filter is None
+                    else weaviate.classes.query.Filter.all_of(
+                        [weaviate_filter, prop_filter]
+                    )
+                )
+
+        try:
+            response = collection.query.fetch_objects(
+                filters=weaviate_filter, limit=limit
+            )
+
+            ids = [str(obj.uuid) for obj in response.objects]
+            documents = []
+            metadatas = []
+
+            for obj in response.objects:
+                properties = dict(obj.properties) if obj.properties else {}
+                documents.append(properties.pop("text", ""))
+                metadatas.append(_convert_uuids_to_strings(properties))
+
+            return GetResult(
+                **{
+                    "ids": [ids],
+                    "documents": [documents],
+                    "metadatas": [metadatas],
+                }
+            )
+        except Exception:
+            return None
+
+    def get(self, collection_name: str) -> Optional[GetResult]:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        if not self.client.collections.exists(sane_collection_name):
+            return None
+
+        collection = self.client.collections.get(sane_collection_name)
+        ids, documents, metadatas = [], [], []
+
+        try:
+            for item in collection.iterator():
+                ids.append(str(item.uuid))
+                properties = dict(item.properties) if item.properties else {}
+                documents.append(properties.pop("text", ""))
+                metadatas.append(_convert_uuids_to_strings(properties))
+
+            if not ids:
+                return None
+
+            return GetResult(
+                **{
+                    "ids": [ids],
+                    "documents": [documents],
+                    "metadatas": [metadatas],
+                }
+            )
+        except Exception:
+            return None
+
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[List[str]] = None,
+        filter: Optional[Dict] = None,
+    ) -> None:
+        sane_collection_name = self._sanitize_collection_name(collection_name)
+        if not self.client.collections.exists(sane_collection_name):
+            return
+
+        collection = self.client.collections.get(sane_collection_name)
+
+        try:
+            if ids:
+                for item_id in ids:
+                    collection.data.delete_by_id(uuid=item_id)
+            elif filter:
+                weaviate_filter = None
+                for key, value in filter.items():
+                    prop_filter = weaviate.classes.query.Filter.by_property(
+                        name=key
+                    ).equal(value)
+                    weaviate_filter = (
+                        prop_filter
+                        if weaviate_filter is None
+                        else weaviate.classes.query.Filter.all_of(
+                            [weaviate_filter, prop_filter]
+                        )
+                    )
+
+                if weaviate_filter:
+                    collection.data.delete_many(where=weaviate_filter)
+        except Exception:
+            pass
+
+    def reset(self) -> None:
+        try:
+            for collection_name in self.client.collections.list_all().keys():
+                self.client.collections.delete(collection_name)
+        except Exception:
+            pass

backend/open_webui/retrieval/vector/factory.py

@@ -53,6 +53,10 @@ class Vector:
                 from open_webui.retrieval.vector.dbs.pgvector import PgvectorClient
 
                 return PgvectorClient()
+            case VectorType.OPENGAUSS:
+                from open_webui.retrieval.vector.dbs.opengauss import OpenGaussClient
+
+                return OpenGaussClient()
             case VectorType.ELASTICSEARCH:
                 from open_webui.retrieval.vector.dbs.elasticsearch import (
                     ElasticsearchClient,
@@ -67,6 +71,10 @@ class Vector:
                 from open_webui.retrieval.vector.dbs.oracle23ai import Oracle23aiClient
 
                 return Oracle23aiClient()
+            case VectorType.WEAVIATE:
+                from open_webui.retrieval.vector.dbs.weaviate import WeaviateClient
+
+                return WeaviateClient()
             case _:
                 raise ValueError(f"Unsupported vector type: {vector_type}")
 

backend/open_webui/retrieval/vector/main.py

@@ -53,7 +53,11 @@ class VectorDBBase(ABC):
 
     @abstractmethod
     def search(
-        self, collection_name: str, vectors: List[List[Union[float, int]]], limit: int
+        self,
+        collection_name: str,
+        vectors: List[List[Union[float, int]]],
+        filter: Optional[Dict] = None,
+        limit: int = 10,
     ) -> Optional[SearchResult]:
         """Search for similar vectors in a collection."""
         pass

backend/open_webui/retrieval/vector/type.py

@@ -11,3 +11,5 @@ class VectorType(StrEnum):
     PGVECTOR = "pgvector"
     ORACLE23AI = "oracle23ai"
     S3VECTOR = "s3vector"
+    WEAVIATE = "weaviate"
+    OPENGAUSS = "opengauss"

backend/open_webui/retrieval/web/azure.py

@@ -0,0 +1,126 @@
+import logging
+from typing import Optional
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+
+log = logging.getLogger(__name__)
+
+"""
+Azure AI Search integration for Open WebUI.
+Documentation: https://learn.microsoft.com/en-us/python/api/overview/azure/search-documents-readme?view=azure-python
+
+Required package: azure-search-documents
+Install: pip install azure-search-documents
+"""
+
+
+def search_azure(
+    api_key: str,
+    endpoint: str,
+    index_name: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    """
+    Search using Azure AI Search.
+
+    Args:
+        api_key: Azure Search API key (query key or admin key)
+        endpoint: Azure Search service endpoint (e.g., https://myservice.search.windows.net)
+        index_name: Name of the search index to query
+        query: Search query string
+        count: Number of results to return
+        filter_list: Optional list of domains to filter results
+
+    Returns:
+        List of SearchResult objects with link, title, and snippet
+    """
+    try:
+        from azure.core.credentials import AzureKeyCredential
+        from azure.search.documents import SearchClient
+    except ImportError:
+        log.error(
+            "azure-search-documents package is not installed. "
+            "Install it with: pip install azure-search-documents"
+        )
+        raise ImportError(
+            "azure-search-documents is required for Azure AI Search. "
+            "Install it with: pip install azure-search-documents"
+        )
+
+    try:
+        # Create search client with API key authentication
+        credential = AzureKeyCredential(api_key)
+        search_client = SearchClient(
+            endpoint=endpoint, index_name=index_name, credential=credential
+        )
+
+        # Perform the search
+        results = search_client.search(search_text=query, top=count)
+
+        # Convert results to list and extract fields
+        search_results = []
+        for result in results:
+            # Azure AI Search returns documents with custom schemas
+            # We need to extract common fields that might represent URL, title, and content
+            # Common field names to look for:
+            result_dict = dict(result)
+
+            # Try to find URL field (common names)
+            link = (
+                result_dict.get("url")
+                or result_dict.get("link")
+                or result_dict.get("uri")
+                or result_dict.get("metadata_storage_path")
+                or ""
+            )
+
+            # Try to find title field (common names)
+            title = (
+                result_dict.get("title")
+                or result_dict.get("name")
+                or result_dict.get("metadata_title")
+                or result_dict.get("metadata_storage_name")
+                or None
+            )
+
+            # Try to find content/snippet field (common names)
+            snippet = (
+                result_dict.get("content")
+                or result_dict.get("snippet")
+                or result_dict.get("description")
+                or result_dict.get("summary")
+                or result_dict.get("text")
+                or None
+            )
+
+            # Truncate snippet if too long
+            if snippet and len(snippet) > 500:
+                snippet = snippet[:497] + "..."
+
+            if link:  # Only add if we found a valid link
+                search_results.append(
+                    {
+                        "link": link,
+                        "title": title,
+                        "snippet": snippet,
+                    }
+                )
+
+        # Apply domain filtering if specified
+        if filter_list:
+            search_results = get_filtered_results(search_results, filter_list)
+
+        # Convert to SearchResult objects
+        return [
+            SearchResult(
+                link=result["link"],
+                title=result.get("title"),
+                snippet=result.get("snippet"),
+            )
+            for result in search_results
+        ]
+
+    except Exception as ex:
+        log.error(f"Azure AI Search error: {ex}")
+        raise ex

backend/open_webui/retrieval/web/bing.py

@@ -4,11 +4,9 @@ from pprint import pprint
 from typing import Optional
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 import argparse
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 """
 Documentation: https://docs.microsoft.com/en-us/bing/search-apis/bing-web-search/overview
 """

backend/open_webui/retrieval/web/bocha.py

@@ -4,20 +4,18 @@ from typing import Optional
 import requests
 import json
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def _parse_response(response):
-    result = {}
+    results = []
     if "data" in response:
         data = response["data"]
         if "webPages" in data:
             webPages = data["webPages"]
             if "value" in webPages:
-                result["webpage"] = [
+                results = [
                     {
                         "id": item.get("id", ""),
                         "name": item.get("name", ""),
@@ -31,7 +29,7 @@ def _parse_response(response):
                     }
                     for item in webPages["value"]
                 ]
-    return result
+    return results
 
 
 def search_bocha(
@@ -53,7 +51,7 @@ def search_bocha(
     response = requests.post(url, headers=headers, data=payload, timeout=5)
     response.raise_for_status()
     results = _parse_response(response.json())
-    print(results)
+
     if filter_list:
         results = get_filtered_results(results, filter_list)
 
@@ -61,5 +59,5 @@ def search_bocha(
         SearchResult(
             link=result["url"], title=result.get("name"), snippet=result.get("summary")
         )
-        for result in results.get("webpage", [])[:count]
+        for result in results[:count]
     ]

backend/open_webui/retrieval/web/brave.py

@@ -1,12 +1,11 @@
 import logging
+import time
 from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_brave(
@@ -27,6 +26,14 @@ def search_brave(
     params = {"q": query, "count": count}
 
     response = requests.get(url, headers=headers, params=params)
+
+    # Handle 429 rate limiting - Brave free tier allows 1 request/second
+    # If rate limited, wait 1 second and retry once before failing
+    if response.status_code == 429:
+        log.info("Brave Search API rate limited (429), retrying after 1 second...")
+        time.sleep(1)
+        response = requests.get(url, headers=headers, params=params)
+
     response.raise_for_status()
 
     json_response = response.json()

backend/open_webui/retrieval/web/duckduckgo.py

@@ -4,10 +4,8 @@ from typing import Optional
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 from ddgs import DDGS
 from ddgs.exceptions import RatelimitException
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_duckduckgo(
@@ -15,12 +13,14 @@ def search_duckduckgo(
     count: int,
     filter_list: Optional[list[str]] = None,
     concurrent_requests: Optional[int] = None,
+    backend: Optional[str] = "auto",
 ) -> list[SearchResult]:
     """
     Search using DuckDuckGo's Search API and return the results as a list of SearchResult objects.
     Args:
         query (str): The query to search for
         count (int): The number of results to return
+        backend (str): The search backend to use (auto, duckduckgo, google, brave, etc.)
 
     Returns:
         list[SearchResult]: A list of search results
@@ -34,7 +34,7 @@ def search_duckduckgo(
         # Use the ddgs.text() method to perform the search
         try:
             search_results = ddgs.text(
-                query, safesearch="moderate", max_results=count, backend="lite"
+                query, safesearch="moderate", max_results=count, backend=backend
             )
         except RatelimitException as e:
             log.error(f"RatelimitException: {e}")

backend/open_webui/retrieval/web/exa.py

@@ -3,11 +3,9 @@ from dataclasses import dataclass
 from typing import Optional
 
 import requests
-from open_webui.env import SRC_LOG_LEVELS
 from open_webui.retrieval.web.main import SearchResult
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 EXA_API_BASE = "https://api.exa.ai"
 

backend/open_webui/retrieval/web/external.py

@@ -2,27 +2,40 @@ import logging
 from typing import Optional, List
 
 import requests
+
+from fastapi import Request
+
+
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.utils.headers import include_user_info_headers
+
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_external(
+    request: Request,
     external_url: str,
     external_api_key: str,
     query: str,
     count: int,
     filter_list: Optional[List[str]] = None,
+    user=None,
 ) -> List[SearchResult]:
     try:
+        headers = {
+            "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot",
+            "Authorization": f"Bearer {external_api_key}",
+        }
+        headers = include_user_info_headers(headers, user)
+
+        chat_id = getattr(request.state, "chat_id", None)
+        if chat_id:
+            headers["X-OpenWebUI-Chat-Id"] = str(chat_id)
+
         response = requests.post(
             external_url,
-            headers={
-                "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot",
-                "Authorization": f"Bearer {external_api_key}",
-            },
+            headers=headers,
             json={
                 "query": query,
                 "count": count,

backend/open_webui/retrieval/web/firecrawl.py

@@ -2,11 +2,9 @@ import logging
 from typing import Optional, List
 
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_firecrawl(

backend/open_webui/retrieval/web/google_pse.py

@@ -3,10 +3,8 @@ from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_google_pse(

backend/open_webui/retrieval/web/jina_search.py

@@ -2,24 +2,26 @@ import logging
 
 import requests
 from open_webui.retrieval.web.main import SearchResult
-from open_webui.env import SRC_LOG_LEVELS
 from yarl import URL
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
-def search_jina(api_key: str, query: str, count: int) -> list[SearchResult]:
+def search_jina(
+    api_key: str, query: str, count: int, base_url: str = ""
+) -> list[SearchResult]:
     """
     Search using Jina's Search API and return the results as a list of SearchResult objects.
     Args:
+        api_key (str): The Jina API key
         query (str): The query to search for
         count (int): The number of results to return
+        base_url (str): Optional custom base URL for the Jina API
 
     Returns:
         list[SearchResult]: A list of search results
     """
-    jina_search_endpoint = "https://s.jina.ai/"
+    jina_search_endpoint = base_url if base_url else "https://s.jina.ai/"
 
     headers = {
         "Accept": "application/json",

backend/open_webui/retrieval/web/kagi.py

@@ -3,10 +3,8 @@ from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_kagi(

backend/open_webui/retrieval/web/main.py

@@ -5,18 +5,38 @@ from urllib.parse import urlparse
 
 from pydantic import BaseModel
 
+from open_webui.retrieval.web.utils import resolve_hostname
+from open_webui.utils.misc import is_string_allowed
+
 
 def get_filtered_results(results, filter_list):
     if not filter_list:
         return results
+
     filtered_results = []
+
     for result in results:
         url = result.get("url") or result.get("link", "") or result.get("href", "")
         if not validators.url(url):
             continue
+
         domain = urlparse(url).netloc
-        if any(domain.endswith(filtered_domain) for filtered_domain in filter_list):
+        if not domain:
+            continue
+
+        hostnames = [domain]
+
+        try:
+            ipv4_addresses, ipv6_addresses = resolve_hostname(domain)
+            hostnames.extend(ipv4_addresses)
+            hostnames.extend(ipv6_addresses)
+        except Exception:
+            pass
+
+        if is_string_allowed(hostnames, filter_list):
             filtered_results.append(result)
+            continue
+
     return filtered_results
 
 

backend/open_webui/retrieval/web/mojeek.py

@@ -3,10 +3,8 @@ from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_mojeek(

backend/open_webui/retrieval/web/ollama.py

@@ -3,11 +3,9 @@ from dataclasses import dataclass
 from typing import Optional
 
 import requests
-from open_webui.env import SRC_LOG_LEVELS
-from open_webui.retrieval.web.main import SearchResult
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_ollama_cloud(
@@ -38,6 +36,9 @@ def search_ollama_cloud(
         results = data.get("results", [])
         log.info(f"Found {len(results)} results")
 
+        if filter_list:
+            results = get_filtered_results(results, filter_list)
+
         return [
             SearchResult(
                 link=result.get("url", ""),

backend/open_webui/retrieval/web/perplexity.py

@@ -3,7 +3,6 @@ from typing import Optional, Literal
 import requests
 
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 MODELS = Literal[
     "sonar",
@@ -16,7 +15,6 @@ SEARCH_CONTEXT_USAGE_LEVELS = Literal["low", "medium", "high"]
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_perplexity(

backend/open_webui/retrieval/web/perplexity_search.py

@@ -3,11 +3,10 @@ from typing import Optional, Literal
 import requests
 
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.utils.headers import include_user_info_headers
 
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_perplexity_search(
@@ -15,6 +14,8 @@ def search_perplexity_search(
     query: str,
     count: int,
     filter_list: Optional[list[str]] = None,
+    api_url: str = "https://api.perplexity.ai/search",
+    user=None,
 ) -> list[SearchResult]:
     """Search using Perplexity API and return the results as a list of SearchResult objects.
 
@@ -23,6 +24,8 @@ def search_perplexity_search(
       query (str): The query to search for
       count (int): Maximum number of results to return
       filter_list (Optional[list[str]]): List of domains to filter results
+      api_url (str): Custom API URL (defaults to https://api.perplexity.ai/search)
+      user: Optional user object for forwarding user info headers
 
     """
 
@@ -30,8 +33,11 @@ def search_perplexity_search(
     if hasattr(api_key, "__str__"):
         api_key = str(api_key)
 
+    if hasattr(api_url, "__str__"):
+        api_url = str(api_url)
+
     try:
-        url = "https://api.perplexity.ai/search"
+        url = api_url
 
         # Create payload for the API call
         payload = {
@@ -44,6 +50,10 @@ def search_perplexity_search(
             "Content-Type": "application/json",
         }
 
+        # Forward user info headers if user is provided
+        if user is not None:
+            headers = include_user_info_headers(headers, user)
+
         # Make the API request
         response = requests.request("POST", url, json=payload, headers=headers)
         # Parse the JSON response

backend/open_webui/retrieval/web/searchapi.py

@@ -4,10 +4,8 @@ from urllib.parse import urlencode
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_searchapi(

backend/open_webui/retrieval/web/searxng.py

@@ -3,10 +3,8 @@ from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_searxng(
@@ -27,7 +25,7 @@ def search_searxng(
         count (int): The maximum number of results to retrieve from the search.
 
     Keyword Args:
-        language (str): Language filter for the search results; e.g., "en-US". Defaults to an empty string.
+        language (str): Language filter for the search results; e.g., "all", "en-US", "es". Defaults to "all".
         safesearch (int): Safe search filter for safer web results; 0 = off, 1 = moderate, 2 = strict. Defaults to 1 (moderate).
         time_range (str): Time range for filtering results by date; e.g., "2023-04-05..today" or "all-time". Defaults to ''.
         categories: (Optional[list[str]]): Specific categories within which the search should be performed, defaulting to an empty string if not provided.
@@ -40,7 +38,7 @@ def search_searxng(
     """
 
     # Default values for optional parameters are provided as empty strings or None when not specified.
-    language = kwargs.get("language", "en-US")
+    language = kwargs.get("language", "all")
     safesearch = kwargs.get("safesearch", "1")
     time_range = kwargs.get("time_range", "")
     categories = "".join(kwargs.get("categories", []))

backend/open_webui/retrieval/web/serpapi.py

@@ -4,10 +4,8 @@ from urllib.parse import urlencode
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_serpapi(

backend/open_webui/retrieval/web/serper.py

@@ -4,10 +4,8 @@ from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_serper(

backend/open_webui/retrieval/web/serply.py

@@ -4,10 +4,8 @@ from urllib.parse import urlencode
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_serply(

backend/open_webui/retrieval/web/serpstack.py

@@ -3,10 +3,8 @@ from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_serpstack(

backend/open_webui/retrieval/web/sougou.py

@@ -4,10 +4,8 @@ from typing import Optional, List
 
 
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_sougou(

backend/open_webui/retrieval/web/tavily.py

@@ -3,10 +3,8 @@ from typing import Optional
 
 import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_tavily(

backend/open_webui/retrieval/web/utils.py

@@ -24,6 +24,7 @@ import validators
 from langchain_community.document_loaders import PlaywrightURLLoader, WebBaseLoader
 from langchain_community.document_loaders.base import BaseLoader
 from langchain_core.documents import Document
+
 from open_webui.retrieval.loaders.tavily import TavilyLoader
 from open_webui.retrieval.loaders.external_web import ExternalWebLoader
 from open_webui.constants import ERROR_MESSAGES
@@ -32,24 +33,52 @@ from open_webui.config import (
     PLAYWRIGHT_WS_URL,
     PLAYWRIGHT_TIMEOUT,
     WEB_LOADER_ENGINE,
+    WEB_LOADER_TIMEOUT,
     FIRECRAWL_API_BASE_URL,
     FIRECRAWL_API_KEY,
+    FIRECRAWL_TIMEOUT,
     TAVILY_API_KEY,
     TAVILY_EXTRACT_DEPTH,
     EXTERNAL_WEB_LOADER_URL,
     EXTERNAL_WEB_LOADER_API_KEY,
+    WEB_FETCH_FILTER_LIST,
 )
-from open_webui.env import SRC_LOG_LEVELS
-
+from open_webui.utils.misc import is_string_allowed
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def resolve_hostname(hostname):
+    # Get address information
+    addr_info = socket.getaddrinfo(hostname, None)
+
+    # Extract IP addresses from address information
+    ipv4_addresses = [info[4][0] for info in addr_info if info[0] == socket.AF_INET]
+    ipv6_addresses = [info[4][0] for info in addr_info if info[0] == socket.AF_INET6]
+
+    return ipv4_addresses, ipv6_addresses
 
 
 def validate_url(url: Union[str, Sequence[str]]):
     if isinstance(url, str):
         if isinstance(validators.url(url), validators.ValidationError):
             raise ValueError(ERROR_MESSAGES.INVALID_URL)
+
+        parsed_url = urllib.parse.urlparse(url)
+
+        # Protocol validation - only allow http/https
+        if parsed_url.scheme not in ["http", "https"]:
+            log.warning(
+                f"Blocked non-HTTP(S) protocol: {parsed_url.scheme} in URL: {url}"
+            )
+            raise ValueError(ERROR_MESSAGES.INVALID_URL)
+
+        # Blocklist check using unified filtering logic
+        if WEB_FETCH_FILTER_LIST:
+            if not is_string_allowed(url, WEB_FETCH_FILTER_LIST):
+                log.warning(f"URL blocked by filter list: {url}")
+                raise ValueError(ERROR_MESSAGES.INVALID_URL)
+
         if not ENABLE_RAG_LOCAL_WEB_FETCH:
             # Local web fetch is disabled, filter out any URLs that resolve to private IP addresses
             parsed_url = urllib.parse.urlparse(url)
@@ -82,17 +111,6 @@ def safe_validate_urls(url: Sequence[str]) -> Sequence[str]:
     return valid_urls
 
 
-def resolve_hostname(hostname):
-    # Get address information
-    addr_info = socket.getaddrinfo(hostname, None)
-
-    # Extract IP addresses from address information
-    ipv4_addresses = [info[4][0] for info in addr_info if info[0] == socket.AF_INET]
-    ipv6_addresses = [info[4][0] for info in addr_info if info[0] == socket.AF_INET6]
-
-    return ipv4_addresses, ipv6_addresses
-
-
 def extract_metadata(soup, url):
     metadata = {"source": url}
     if title := soup.find("title"):
@@ -172,6 +190,7 @@ class SafeFireCrawlLoader(BaseLoader, RateLimitMixin, URLProcessingMixin):
         continue_on_failure: bool = True,
         api_key: Optional[str] = None,
         api_url: Optional[str] = None,
+        timeout: Optional[int] = None,
         mode: Literal["crawl", "scrape", "map"] = "scrape",
         proxy: Optional[Dict[str, str]] = None,
         params: Optional[Dict] = None,
@@ -214,6 +233,7 @@ class SafeFireCrawlLoader(BaseLoader, RateLimitMixin, URLProcessingMixin):
         self.continue_on_failure = continue_on_failure
         self.api_key = api_key
         self.api_url = api_url
+        self.timeout = timeout
         self.mode = mode
         self.params = params or {}
 
@@ -236,7 +256,7 @@ class SafeFireCrawlLoader(BaseLoader, RateLimitMixin, URLProcessingMixin):
                 ignore_invalid_urls=True,
                 remove_base64_images=True,
                 max_age=300000,  # 5 minutes https://docs.firecrawl.dev/features/fast-scraping#common-maxage-values
-                wait_timeout=len(self.web_paths) * 3,
+                wait_timeout=self.timeout if self.timeout else len(self.web_paths) * 3,
                 **self.params,
             )
 
@@ -277,7 +297,7 @@ class SafeFireCrawlLoader(BaseLoader, RateLimitMixin, URLProcessingMixin):
                 ignore_invalid_urls=True,
                 remove_base64_images=True,
                 max_age=300000,  # 5 minutes https://docs.firecrawl.dev/features/fast-scraping#common-maxage-values
-                wait_timeout=len(self.web_paths) * 3,
+                wait_timeout=self.timeout if self.timeout else len(self.web_paths) * 3,
                 **self.params,
             )
 
@@ -642,6 +662,10 @@ def get_web_loader(
     # Check if the URLs are valid
     safe_urls = safe_validate_urls([urls] if isinstance(urls, str) else urls)
 
+    if not safe_urls:
+        log.warning(f"All provided URLs were blocked or invalid: {urls}")
+        raise ValueError(ERROR_MESSAGES.INVALID_URL)
+
     web_loader_args = {
         "web_paths": safe_urls,
         "verify_ssl": verify_ssl,
@@ -652,6 +676,20 @@ def get_web_loader(
 
     if WEB_LOADER_ENGINE.value == "" or WEB_LOADER_ENGINE.value == "safe_web":
         WebLoaderClass = SafeWebBaseLoader
+
+        request_kwargs = {}
+        if WEB_LOADER_TIMEOUT.value:
+            try:
+                timeout_value = float(WEB_LOADER_TIMEOUT.value)
+            except ValueError:
+                timeout_value = None
+
+            if timeout_value:
+                request_kwargs["timeout"] = timeout_value
+
+        if request_kwargs:
+            web_loader_args["requests_kwargs"] = request_kwargs
+
     if WEB_LOADER_ENGINE.value == "playwright":
         WebLoaderClass = SafePlaywrightURLLoader
         web_loader_args["playwright_timeout"] = PLAYWRIGHT_TIMEOUT.value
@@ -662,6 +700,11 @@ def get_web_loader(
         WebLoaderClass = SafeFireCrawlLoader
         web_loader_args["api_key"] = FIRECRAWL_API_KEY.value
         web_loader_args["api_url"] = FIRECRAWL_API_BASE_URL.value
+        if FIRECRAWL_TIMEOUT.value:
+            try:
+                web_loader_args["timeout"] = int(FIRECRAWL_TIMEOUT.value)
+            except ValueError:
+                pass
 
     if WEB_LOADER_ENGINE.value == "tavily":
         WebLoaderClass = SafeTavilyLoader

backend/open_webui/retrieval/web/yacy.py

@@ -4,10 +4,8 @@ from typing import Optional
 import requests
 from requests.auth import HTTPDigestAuth
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_yacy(

backend/open_webui/routers/audio.py

@@ -16,7 +16,6 @@ import aiohttp
 import aiofiles
 import requests
 import mimetypes
-from urllib.parse import urljoin, quote
 
 from fastapi import (
     Depends,
@@ -34,12 +33,18 @@ from fastapi.responses import FileResponse
 from pydantic import BaseModel
 
 
+from open_webui.utils.misc import strict_match_mime_type
 from open_webui.utils.auth import get_admin_user, get_verified_user
+from open_webui.utils.access_control import has_permission
+from open_webui.utils.headers import include_user_info_headers
 from open_webui.config import (
     WHISPER_MODEL_AUTO_UPDATE,
+    WHISPER_COMPUTE_TYPE,
     WHISPER_MODEL_DIR,
+    WHISPER_VAD_FILTER,
     CACHE_DIR,
     WHISPER_LANGUAGE,
+    WHISPER_MULTILINGUAL,
     ELEVENLABS_API_BASE_URL,
 )
 
@@ -48,7 +53,6 @@ from open_webui.env import (
     ENV,
     AIOHTTP_CLIENT_SESSION_SSL,
     AIOHTTP_CLIENT_TIMEOUT,
-    SRC_LOG_LEVELS,
     DEVICE_TYPE,
     ENABLE_FORWARD_USER_INFO_HEADERS,
 )
@@ -63,7 +67,6 @@ AZURE_MAX_FILE_SIZE_MB = 200
 AZURE_MAX_FILE_SIZE = AZURE_MAX_FILE_SIZE_MB * 1024 * 1024  # Convert MB to bytes
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["AUDIO"])
 
 SPEECH_CACHE_DIR = CACHE_DIR / "audio" / "speech"
 SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
@@ -130,7 +133,7 @@ def set_faster_whisper_model(model: str, auto_update: bool = False):
         faster_whisper_kwargs = {
             "model_size_or_path": model,
             "device": DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu",
-            "compute_type": "int8",
+            "compute_type": WHISPER_COMPUTE_TYPE,
             "download_root": WHISPER_MODEL_DIR,
             "local_files_only": not auto_update,
         }
@@ -329,6 +332,20 @@ def load_speech_pipeline(request):
 
 @router.post("/speech")
 async def speech(request: Request, user=Depends(get_verified_user)):
+    if request.app.state.config.TTS_ENGINE == "":
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    if user.role != "admin" and not has_permission(
+        user.id, "chat.tts", request.app.state.config.USER_PERMISSIONS
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     body = await request.body()
     name = hashlib.sha256(
         body
@@ -364,23 +381,17 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                     **(request.app.state.config.TTS_OPENAI_PARAMS or {}),
                 }
 
+                headers = {
+                    "Content-Type": "application/json",
+                    "Authorization": f"Bearer {request.app.state.config.TTS_OPENAI_API_KEY}",
+                }
+                if ENABLE_FORWARD_USER_INFO_HEADERS:
+                    headers = include_user_info_headers(headers, user)
+
                 r = await session.post(
                     url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
                     json=payload,
-                    headers={
-                        "Content-Type": "application/json",
-                        "Authorization": f"Bearer {request.app.state.config.TTS_OPENAI_API_KEY}",
-                        **(
-                            {
-                                "X-OpenWebUI-User-Name": quote(user.name, safe=" "),
-                                "X-OpenWebUI-User-Id": user.id,
-                                "X-OpenWebUI-User-Email": user.email,
-                                "X-OpenWebUI-User-Role": user.role,
-                            }
-                            if ENABLE_FORWARD_USER_INFO_HEADERS
-                            else {}
-                        ),
-                    },
+                    headers=headers,
                     ssl=AIOHTTP_CLIENT_SESSION_SSL,
                 )
 
@@ -570,7 +581,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         return FileResponse(file_path)
 
 
-def transcription_handler(request, file_path, metadata):
+def transcription_handler(request, file_path, metadata, user=None):
     filename = os.path.basename(file_path)
     file_dir = os.path.dirname(file_path)
     id = filename.split(".")[0]
@@ -592,8 +603,9 @@ def transcription_handler(request, file_path, metadata):
         segments, info = model.transcribe(
             file_path,
             beam_size=5,
-            vad_filter=request.app.state.config.WHISPER_VAD_FILTER,
+            vad_filter=WHISPER_VAD_FILTER,
             language=languages[0],
+            multilingual=WHISPER_MULTILINGUAL,
         )
         log.info(
             "Detected language '%s' with probability %f"
@@ -621,11 +633,15 @@ def transcription_handler(request, file_path, metadata):
                 if language:
                     payload["language"] = language
 
+                headers = {
+                    "Authorization": f"Bearer {request.app.state.config.STT_OPENAI_API_KEY}"
+                }
+                if user and ENABLE_FORWARD_USER_INFO_HEADERS:
+                    headers = include_user_info_headers(headers, user)
+
                 r = requests.post(
                     url=f"{request.app.state.config.STT_OPENAI_API_BASE_URL}/audio/transcriptions",
-                    headers={
-                        "Authorization": f"Bearer {request.app.state.config.STT_OPENAI_API_KEY}"
-                    },
+                    headers=headers,
                     files={"file": (filename, open(file_path, "rb"))},
                     data=payload,
                 )
@@ -1027,7 +1043,9 @@ def transcription_handler(request, file_path, metadata):
             )
 
 
-def transcribe(request: Request, file_path: str, metadata: Optional[dict] = None):
+def transcribe(
+    request: Request, file_path: str, metadata: Optional[dict] = None, user=None
+):
     log.info(f"transcribe: {file_path} {metadata}")
 
     if is_audio_conversion_required(file_path):
@@ -1054,7 +1072,9 @@ def transcribe(request: Request, file_path: str, metadata: Optional[dict] = None
         with ThreadPoolExecutor() as executor:
             # Submit tasks for each chunk_path
             futures = [
-                executor.submit(transcription_handler, request, chunk_path, metadata)
+                executor.submit(
+                    transcription_handler, request, chunk_path, metadata, user
+                )
                 for chunk_path in chunk_paths
             ]
             # Gather results as they complete
@@ -1149,21 +1169,25 @@ def transcription(
     language: Optional[str] = Form(None),
     user=Depends(get_verified_user),
 ):
-    log.info(f"file.content_type: {file.content_type}")
+    if request.app.state.config.STT_ENGINE == "":
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
 
+    if user.role != "admin" and not has_permission(
+        user.id, "chat.stt", request.app.state.config.USER_PERMISSIONS
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+    log.info(f"file.content_type: {file.content_type}")
     stt_supported_content_types = getattr(
         request.app.state.config, "STT_SUPPORTED_CONTENT_TYPES", []
     )
 
-    if not any(
-        fnmatch(file.content_type, content_type)
-        for content_type in (
-            stt_supported_content_types
-            if stt_supported_content_types
-            and any(t.strip() for t in stt_supported_content_types)
-            else ["audio/*", "video/webm"]
-        )
-    ):
+    if not strict_match_mime_type(stt_supported_content_types, file.content_type):
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
@@ -1189,7 +1213,7 @@ def transcription(
             if language:
                 metadata = {"language": language}
 
-            result = transcribe(request, file_path, metadata)
+            result = transcribe(request, file_path, metadata, user)
 
             return {
                 **result,

backend/open_webui/routers/auths.py

@@ -4,6 +4,8 @@ import time
 import datetime
 import logging
 from aiohttp import ClientSession
+import urllib
+
 
 from open_webui.models.auths import (
     AddUserForm,
@@ -15,9 +17,13 @@ from open_webui.models.auths import (
     SigninResponse,
     SignupForm,
     UpdatePasswordForm,
-    UserResponse,
 )
-from open_webui.models.users import Users, UpdateProfileForm
+from open_webui.models.users import (
+    UserProfileImageResponse,
+    Users,
+    UpdateProfileForm,
+    UserStatus,
+)
 from open_webui.models.groups import Groups
 from open_webui.models.oauth_sessions import OAuthSessions
 
@@ -31,16 +37,23 @@ from open_webui.env import (
     WEBUI_AUTH_COOKIE_SECURE,
     WEBUI_AUTH_SIGNOUT_REDIRECT_URL,
     ENABLE_INITIAL_ADMIN_SIGNUP,
-    SRC_LOG_LEVELS,
 )
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from fastapi.responses import RedirectResponse, Response, JSONResponse
-from open_webui.config import OPENID_PROVIDER_URL, ENABLE_OAUTH_SIGNUP, ENABLE_LDAP
+from open_webui.config import (
+    OPENID_PROVIDER_URL,
+    ENABLE_OAUTH_SIGNUP,
+    ENABLE_LDAP,
+    ENABLE_PASSWORD_AUTH,
+)
 from pydantic import BaseModel
 
 from open_webui.utils.misc import parse_duration, validate_email_format
 from open_webui.utils.auth import (
+    validate_password,
+    verify_password,
     decode_token,
+    invalidate_token,
     create_api_key,
     create_token,
     get_admin_user,
@@ -49,8 +62,15 @@ from open_webui.utils.auth import (
     get_password_hash,
     get_http_authorization_cred,
 )
+from open_webui.internal.db import get_session
+from sqlalchemy.orm import Session
 from open_webui.utils.webhook import post_webhook
-from open_webui.utils.access_control import get_permissions
+from open_webui.utils.access_control import get_permissions, has_permission
+from open_webui.utils.groups import apply_default_group_assignment
+
+from open_webui.utils.redis import get_redis_client
+from open_webui.utils.rate_limit import RateLimiter
+
 
 from typing import Optional, List
 
@@ -62,19 +82,22 @@ from ldap3.utils.conv import escape_filter_chars
 router = APIRouter()
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
+
+signin_rate_limiter = RateLimiter(
+    redis_client=get_redis_client(), limit=5 * 3, window=60 * 3
+)
 
 ############################
 # GetSessionUser
 ############################
 
 
-class SessionUserResponse(Token, UserResponse):
+class SessionUserResponse(Token, UserProfileImageResponse):
     expires_at: Optional[int] = None
     permissions: Optional[dict] = None
 
 
-class SessionUserInfoResponse(SessionUserResponse):
+class SessionUserInfoResponse(SessionUserResponse, UserStatus):
     bio: Optional[str] = None
     gender: Optional[str] = None
     date_of_birth: Optional[datetime.date] = None
@@ -82,7 +105,10 @@ class SessionUserInfoResponse(SessionUserResponse):
 
 @router.get("/", response_model=SessionUserInfoResponse)
 async def get_session_user(
-    request: Request, response: Response, user=Depends(get_current_user)
+    request: Request,
+    response: Response,
+    user=Depends(get_current_user),
+    db: Session = Depends(get_session),
 ):
 
     auth_header = request.headers.get("Authorization")
@@ -116,7 +142,7 @@ async def get_session_user(
         )
 
     user_permissions = get_permissions(
-        user.id, request.app.state.config.USER_PERMISSIONS
+        user.id, request.app.state.config.USER_PERMISSIONS, db=db
     )
 
     return {
@@ -131,6 +157,9 @@ async def get_session_user(
         "bio": user.bio,
         "gender": user.gender,
         "date_of_birth": user.date_of_birth,
+        "status_emoji": user.status_emoji,
+        "status_message": user.status_message,
+        "status_expires_at": user.status_expires_at,
         "permissions": user_permissions,
     }
 
@@ -140,14 +169,17 @@ async def get_session_user(
 ############################
 
 
-@router.post("/update/profile", response_model=UserResponse)
+@router.post("/update/profile", response_model=UserProfileImageResponse)
 async def update_profile(
-    form_data: UpdateProfileForm, session_user=Depends(get_verified_user)
+    form_data: UpdateProfileForm,
+    session_user=Depends(get_verified_user),
+    db: Session = Depends(get_session),
 ):
     if session_user:
         user = Users.update_user_by_id(
             session_user.id,
             form_data.model_dump(),
+            db=db,
         )
         if user:
             return user
@@ -157,6 +189,32 @@ async def update_profile(
         raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
 
 
+############################
+# Update Timezone
+############################
+
+
+class UpdateTimezoneForm(BaseModel):
+    timezone: str
+
+
+@router.post("/update/timezone")
+async def update_timezone(
+    form_data: UpdateTimezoneForm,
+    session_user=Depends(get_current_user),
+    db: Session = Depends(get_session),
+):
+    if session_user:
+        Users.update_user_by_id(
+            session_user.id,
+            {"timezone": form_data.timezone},
+            db=db,
+        )
+        return {"status": True}
+    else:
+        raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+
+
 ############################
 # Update Password
 ############################
@@ -164,18 +222,28 @@ async def update_profile(
 
 @router.post("/update/password", response_model=bool)
 async def update_password(
-    form_data: UpdatePasswordForm, session_user=Depends(get_current_user)
+    form_data: UpdatePasswordForm,
+    session_user=Depends(get_current_user),
+    db: Session = Depends(get_session),
 ):
     if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
         raise HTTPException(400, detail=ERROR_MESSAGES.ACTION_PROHIBITED)
     if session_user:
-        user = Auths.authenticate_user(session_user.email, form_data.password)
+        user = Auths.authenticate_user(
+            session_user.email,
+            lambda pw: verify_password(form_data.password, pw),
+            db=db,
+        )
 
         if user:
+            try:
+                validate_password(form_data.password)
+            except Exception as e:
+                raise HTTPException(400, detail=str(e))
             hashed = get_password_hash(form_data.new_password)
-            return Auths.update_user_password_by_id(user.id, hashed)
+            return Auths.update_user_password_by_id(user.id, hashed, db=db)
         else:
-            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_PASSWORD)
+            raise HTTPException(400, detail=ERROR_MESSAGES.INCORRECT_PASSWORD)
     else:
         raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
 
@@ -184,8 +252,23 @@ async def update_password(
 # LDAP Authentication
 ############################
 @router.post("/ldap", response_model=SessionUserResponse)
-async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
-    ENABLE_LDAP = request.app.state.config.ENABLE_LDAP
+async def ldap_auth(
+    request: Request,
+    response: Response,
+    form_data: LdapForm,
+    db: Session = Depends(get_session),
+):
+    # Security checks FIRST - before loading any config
+    if not request.app.state.config.ENABLE_LDAP:
+        raise HTTPException(400, detail="LDAP authentication is not enabled")
+
+    if not ENABLE_PASSWORD_AUTH:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.ACTION_PROHIBITED,
+        )
+
+    # NOW load LDAP config variables
     LDAP_SERVER_LABEL = request.app.state.config.LDAP_SERVER_LABEL
     LDAP_SERVER_HOST = request.app.state.config.LDAP_SERVER_HOST
     LDAP_SERVER_PORT = request.app.state.config.LDAP_SERVER_PORT
@@ -206,9 +289,6 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
         else "ALL"
     )
 
-    if not ENABLE_LDAP:
-        raise HTTPException(400, detail="LDAP authentication is not enabled")
-
     try:
         tls = Tls(
             validate=LDAP_VALIDATE_CERT,
@@ -249,13 +329,11 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
             f"{LDAP_ATTRIBUTE_FOR_MAIL}",
             "cn",
         ]
-
         if ENABLE_LDAP_GROUP_MANAGEMENT:
             search_attributes.append(f"{LDAP_ATTRIBUTE_FOR_GROUPS}")
             log.info(
                 f"LDAP Group Management enabled. Adding {LDAP_ATTRIBUTE_FOR_GROUPS} to search attributes"
             )
-
         log.info(f"LDAP search attributes: {search_attributes}")
 
         search_success = connection_app.search(
@@ -263,15 +341,22 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
             search_filter=f"(&({LDAP_ATTRIBUTE_FOR_USERNAME}={escape_filter_chars(form_data.user.lower())}){LDAP_SEARCH_FILTERS})",
             attributes=search_attributes,
         )
-
         if not search_success or not connection_app.entries:
             raise HTTPException(400, detail="User not found in the LDAP server")
 
         entry = connection_app.entries[0]
-        username = str(entry[f"{LDAP_ATTRIBUTE_FOR_USERNAME}"]).lower()
+        entry_username = entry[f"{LDAP_ATTRIBUTE_FOR_USERNAME}"].value
         email = entry[
             f"{LDAP_ATTRIBUTE_FOR_MAIL}"
         ].value  # retrieve the Attribute value
+
+        username_list = []  # list of usernames from LDAP attribute
+        if isinstance(entry_username, list):
+            username_list = [str(name).lower() for name in entry_username]
+        else:
+            username_list = [str(entry_username).lower()]
+
+        # TODO: support multiple emails if LDAP returns a list
         if not email:
             raise HTTPException(400, "User does not have a valid email address.")
         elif isinstance(email, str):
@@ -281,13 +366,13 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
         else:
             email = str(email).lower()
 
-        cn = str(entry["cn"])
-        user_dn = entry.entry_dn
+        cn = str(entry["cn"])  # common name
+        user_dn = entry.entry_dn  # user distinguished name
 
         user_groups = []
         if ENABLE_LDAP_GROUP_MANAGEMENT and LDAP_ATTRIBUTE_FOR_GROUPS in entry:
             group_dns = entry[LDAP_ATTRIBUTE_FOR_GROUPS]
-            log.info(f"LDAP raw group DNs for user {username}: {group_dns}")
+            log.info(f"LDAP raw group DNs for user {username_list}: {group_dns}")
 
             if group_dns:
                 log.info(f"LDAP group_dns original: {group_dns}")
@@ -338,16 +423,16 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                         )
 
                 log.info(
-                    f"LDAP groups for user {username}: {user_groups} (total: {len(user_groups)})"
+                    f"LDAP groups for user {username_list}: {user_groups} (total: {len(user_groups)})"
                 )
             else:
-                log.info(f"No groups found for user {username}")
+                log.info(f"No groups found for user {username_list}")
         elif ENABLE_LDAP_GROUP_MANAGEMENT:
             log.warning(
                 f"LDAP Group Management enabled but {LDAP_ATTRIBUTE_FOR_GROUPS} attribute not found in user entry"
             )
 
-        if username == form_data.user.lower():
+        if username_list and form_data.user.lower() in username_list:
             connection_user = Connection(
                 server,
                 user_dn,
@@ -358,12 +443,12 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
             if not connection_user.bind():
                 raise HTTPException(400, "Authentication failed.")
 
-            user = Users.get_user_by_email(email)
+            user = Users.get_user_by_email(email, db=db)
             if not user:
                 try:
                     role = (
                         "admin"
-                        if not Users.has_users()
+                        if not Users.has_users(db=db)
                         else request.app.state.config.DEFAULT_USER_ROLE
                     )
 
@@ -372,6 +457,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                         password=str(uuid.uuid4()),
                         name=cn,
                         role=role,
+                        db=db,
                     )
 
                     if not user:
@@ -379,6 +465,12 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                             500, detail=ERROR_MESSAGES.CREATE_USER_ERROR
                         )
 
+                    apply_default_group_assignment(
+                        request.app.state.config.DEFAULT_GROUP_ID,
+                        user.id,
+                        db=db,
+                    )
+
                 except HTTPException:
                     raise
                 except Exception as err:
@@ -387,7 +479,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                         500, detail="Internal error occurred during LDAP user creation."
                     )
 
-            user = Auths.authenticate_user_by_email(email)
+            user = Auths.authenticate_user_by_email(email, db=db)
 
             if user:
                 expires_delta = parse_duration(request.app.state.config.JWT_EXPIRES_IN)
@@ -417,7 +509,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                 )
 
                 user_permissions = get_permissions(
-                    user.id, request.app.state.config.USER_PERMISSIONS
+                    user.id, request.app.state.config.USER_PERMISSIONS, db=db
                 )
 
                 if (
@@ -426,10 +518,9 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                     and user_groups
                 ):
                     if ENABLE_LDAP_GROUP_CREATION:
-                        Groups.create_groups_by_group_names(user.id, user_groups)
-
+                        Groups.create_groups_by_group_names(user.id, user_groups, db=db)
                     try:
-                        Groups.sync_groups_by_group_names(user.id, user_groups)
+                        Groups.sync_groups_by_group_names(user.id, user_groups, db=db)
                         log.info(
                             f"Successfully synced groups for user {user.id}: {user_groups}"
                         )
@@ -462,7 +553,18 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
 
 
 @router.post("/signin", response_model=SessionUserResponse)
-async def signin(request: Request, response: Response, form_data: SigninForm):
+async def signin(
+    request: Request,
+    response: Response,
+    form_data: SigninForm,
+    db: Session = Depends(get_session),
+):
+    if not ENABLE_PASSWORD_AUTH:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.ACTION_PROHIBITED,
+        )
+
     if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
         if WEBUI_AUTH_TRUSTED_EMAIL_HEADER not in request.headers:
             raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_TRUSTED_HEADER)
@@ -472,15 +574,20 @@ async def signin(request: Request, response: Response, form_data: SigninForm):
 
         if WEBUI_AUTH_TRUSTED_NAME_HEADER:
             name = request.headers.get(WEBUI_AUTH_TRUSTED_NAME_HEADER, email)
+            try:
+                name = urllib.parse.unquote(name, encoding="utf-8")
+            except Exception as e:
+                pass
 
-        if not Users.get_user_by_email(email.lower()):
+        if not Users.get_user_by_email(email.lower(), db=db):
             await signup(
                 request,
                 response,
                 SignupForm(email=email, password=str(uuid.uuid4()), name=name),
+                db=db,
             )
 
-        user = Auths.authenticate_user_by_email(email)
+        user = Auths.authenticate_user_by_email(email, db=db)
         if WEBUI_AUTH_TRUSTED_GROUPS_HEADER and user and user.role != "admin":
             group_names = request.headers.get(
                 WEBUI_AUTH_TRUSTED_GROUPS_HEADER, ""
@@ -488,26 +595,41 @@ async def signin(request: Request, response: Response, form_data: SigninForm):
             group_names = [name.strip() for name in group_names if name.strip()]
 
             if group_names:
-                Groups.sync_groups_by_group_names(user.id, group_names)
+                Groups.sync_groups_by_group_names(user.id, group_names, db=db)
 
     elif WEBUI_AUTH == False:
         admin_email = "admin@localhost"
         admin_password = "admin"
 
-        if Users.get_user_by_email(admin_email.lower()):
-            user = Auths.authenticate_user(admin_email.lower(), admin_password)
+        if Users.get_user_by_email(admin_email.lower(), db=db):
+            user = Auths.authenticate_user(
+                admin_email.lower(),
+                lambda pw: verify_password(admin_password, pw),
+                db=db,
+            )
         else:
-            if Users.has_users():
+            if Users.has_users(db=db):
                 raise HTTPException(400, detail=ERROR_MESSAGES.EXISTING_USERS)
 
             await signup(
                 request,
                 response,
                 SignupForm(email=admin_email, password=admin_password, name="User"),
+                db=db,
             )
 
-            user = Auths.authenticate_user(admin_email.lower(), admin_password)
+            user = Auths.authenticate_user(
+                admin_email.lower(),
+                lambda pw: verify_password(admin_password, pw),
+                db=db,
+            )
     else:
+        if signin_rate_limiter.is_limited(form_data.email.lower()):
+            raise HTTPException(
+                status_code=status.HTTP_429_TOO_MANY_REQUESTS,
+                detail=ERROR_MESSAGES.RATE_LIMIT_EXCEEDED,
+            )
+
         password_bytes = form_data.password.encode("utf-8")
         if len(password_bytes) > 72:
             # TODO: Implement other hashing algorithms that support longer passwords
@@ -517,7 +639,11 @@ async def signin(request: Request, response: Response, form_data: SigninForm):
             # decode safely — ignore incomplete UTF-8 sequences
             form_data.password = password_bytes.decode("utf-8", errors="ignore")
 
-        user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
+        user = Auths.authenticate_user(
+            form_data.email.lower(),
+            lambda pw: verify_password(form_data.password, pw),
+            db=db,
+        )
 
     if user:
 
@@ -548,7 +674,7 @@ async def signin(request: Request, response: Response, form_data: SigninForm):
         )
 
         user_permissions = get_permissions(
-            user.id, request.app.state.config.USER_PERMISSIONS
+            user.id, request.app.state.config.USER_PERMISSIONS, db=db
         )
 
         return {
@@ -572,8 +698,13 @@ async def signin(request: Request, response: Response, form_data: SigninForm):
 
 
 @router.post("/signup", response_model=SessionUserResponse)
-async def signup(request: Request, response: Response, form_data: SignupForm):
-    has_users = Users.has_users()
+async def signup(
+    request: Request,
+    response: Response,
+    form_data: SignupForm,
+    db: Session = Depends(get_session),
+):
+    has_users = Users.has_users(db=db)
 
     if WEBUI_AUTH:
         if (
@@ -595,26 +726,25 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
             status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT
         )
 
-    if Users.get_user_by_email(form_data.email.lower()):
+    if Users.get_user_by_email(form_data.email.lower(), db=db):
         raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
 
     try:
-        role = "admin" if not has_users else request.app.state.config.DEFAULT_USER_ROLE
-
-        # The password passed to bcrypt must be 72 bytes or fewer. If it is longer, it will be truncated before hashing.
-        if len(form_data.password.encode("utf-8")) > 72:
-            raise HTTPException(
-                status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.PASSWORD_TOO_LONG,
-            )
+        try:
+            validate_password(form_data.password)
+        except Exception as e:
+            raise HTTPException(400, detail=str(e))
 
         hashed = get_password_hash(form_data.password)
+
+        role = "admin" if not has_users else request.app.state.config.DEFAULT_USER_ROLE
         user = Auths.insert_new_auth(
             form_data.email.lower(),
             hashed,
             form_data.name,
             form_data.profile_image_url,
             role,
+            db=db,
         )
 
         if user:
@@ -657,13 +787,19 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
                 )
 
             user_permissions = get_permissions(
-                user.id, request.app.state.config.USER_PERMISSIONS
+                user.id, request.app.state.config.USER_PERMISSIONS, db=db
             )
 
             if not has_users:
                 # Disable signup after the first user is created
                 request.app.state.config.ENABLE_SIGNUP = False
 
+            apply_default_group_assignment(
+                request.app.state.config.DEFAULT_GROUP_ID,
+                user.id,
+                db=db,
+            )
+
             return {
                 "token": token,
                 "token_type": "Bearer",
@@ -683,7 +819,22 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
 
 
 @router.get("/signout")
-async def signout(request: Request, response: Response):
+async def signout(
+    request: Request, response: Response, db: Session = Depends(get_session)
+):
+
+    # get auth token from headers or cookies
+    token = None
+    auth_header = request.headers.get("Authorization")
+    if auth_header:
+        auth_cred = get_http_authorization_cred(auth_header)
+        token = auth_cred.credentials
+    else:
+        token = request.cookies.get("token")
+
+    if token:
+        await invalidate_token(request, token)
+
     response.delete_cookie("token")
     response.delete_cookie("oui-session")
     response.delete_cookie("oauth_id_token")
@@ -692,7 +843,7 @@ async def signout(request: Request, response: Response):
     if oauth_session_id:
         response.delete_cookie("oauth_session_id")
 
-        session = OAuthSessions.get_session_by_id(oauth_session_id)
+        session = OAuthSessions.get_session_by_id(oauth_session_id, db=db)
         oauth_server_metadata_url = (
             request.app.state.oauth_manager.get_server_metadata_url(session.provider)
             if session
@@ -754,16 +905,26 @@ async def signout(request: Request, response: Response):
 
 
 @router.post("/add", response_model=SigninResponse)
-async def add_user(form_data: AddUserForm, user=Depends(get_admin_user)):
+async def add_user(
+    request: Request,
+    form_data: AddUserForm,
+    user=Depends(get_admin_user),
+    db: Session = Depends(get_session),
+):
     if not validate_email_format(form_data.email.lower()):
         raise HTTPException(
             status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT
         )
 
-    if Users.get_user_by_email(form_data.email.lower()):
+    if Users.get_user_by_email(form_data.email.lower(), db=db):
         raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
 
     try:
+        try:
+            validate_password(form_data.password)
+        except Exception as e:
+            raise HTTPException(400, detail=str(e))
+
         hashed = get_password_hash(form_data.password)
         user = Auths.insert_new_auth(
             form_data.email.lower(),
@@ -771,9 +932,16 @@ async def add_user(form_data: AddUserForm, user=Depends(get_admin_user)):
             form_data.name,
             form_data.profile_image_url,
             form_data.role,
+            db=db,
         )
 
         if user:
+            apply_default_group_assignment(
+                request.app.state.config.DEFAULT_GROUP_ID,
+                user.id,
+                db=db,
+            )
+
             token = create_token(data={"id": user.id})
             return {
                 "token": token,
@@ -799,7 +967,9 @@ async def add_user(form_data: AddUserForm, user=Depends(get_admin_user)):
 
 
 @router.get("/admin/details")
-async def get_admin_details(request: Request, user=Depends(get_current_user)):
+async def get_admin_details(
+    request: Request, user=Depends(get_current_user), db: Session = Depends(get_session)
+):
     if request.app.state.config.SHOW_ADMIN_DETAILS:
         admin_email = request.app.state.config.ADMIN_EMAIL
         admin_name = None
@@ -807,11 +977,11 @@ async def get_admin_details(request: Request, user=Depends(get_current_user)):
         log.info(f"Admin details - Email: {admin_email}, Name: {admin_name}")
 
         if admin_email:
-            admin = Users.get_user_by_email(admin_email)
+            admin = Users.get_user_by_email(admin_email, db=db)
             if admin:
                 admin_name = admin.name
         else:
-            admin = Users.get_first_user()
+            admin = Users.get_first_user(db=db)
             if admin:
                 admin_email = admin.email
                 admin_name = admin.name
@@ -833,18 +1003,24 @@ async def get_admin_details(request: Request, user=Depends(get_current_user)):
 async def get_admin_config(request: Request, user=Depends(get_admin_user)):
     return {
         "SHOW_ADMIN_DETAILS": request.app.state.config.SHOW_ADMIN_DETAILS,
+        "ADMIN_EMAIL": request.app.state.config.ADMIN_EMAIL,
         "WEBUI_URL": request.app.state.config.WEBUI_URL,
         "ENABLE_SIGNUP": request.app.state.config.ENABLE_SIGNUP,
-        "ENABLE_API_KEY": request.app.state.config.ENABLE_API_KEY,
-        "ENABLE_API_KEY_ENDPOINT_RESTRICTIONS": request.app.state.config.ENABLE_API_KEY_ENDPOINT_RESTRICTIONS,
-        "API_KEY_ALLOWED_ENDPOINTS": request.app.state.config.API_KEY_ALLOWED_ENDPOINTS,
+        "ENABLE_API_KEYS": request.app.state.config.ENABLE_API_KEYS,
+        "ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS": request.app.state.config.ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS,
+        "API_KEYS_ALLOWED_ENDPOINTS": request.app.state.config.API_KEYS_ALLOWED_ENDPOINTS,
         "DEFAULT_USER_ROLE": request.app.state.config.DEFAULT_USER_ROLE,
+        "DEFAULT_GROUP_ID": request.app.state.config.DEFAULT_GROUP_ID,
         "JWT_EXPIRES_IN": request.app.state.config.JWT_EXPIRES_IN,
         "ENABLE_COMMUNITY_SHARING": request.app.state.config.ENABLE_COMMUNITY_SHARING,
         "ENABLE_MESSAGE_RATING": request.app.state.config.ENABLE_MESSAGE_RATING,
+        "ENABLE_FOLDERS": request.app.state.config.ENABLE_FOLDERS,
+        "FOLDER_MAX_FILE_COUNT": request.app.state.config.FOLDER_MAX_FILE_COUNT,
         "ENABLE_CHANNELS": request.app.state.config.ENABLE_CHANNELS,
+        "ENABLE_MEMORIES": request.app.state.config.ENABLE_MEMORIES,
         "ENABLE_NOTES": request.app.state.config.ENABLE_NOTES,
         "ENABLE_USER_WEBHOOKS": request.app.state.config.ENABLE_USER_WEBHOOKS,
+        "ENABLE_USER_STATUS": request.app.state.config.ENABLE_USER_STATUS,
         "PENDING_USER_OVERLAY_TITLE": request.app.state.config.PENDING_USER_OVERLAY_TITLE,
         "PENDING_USER_OVERLAY_CONTENT": request.app.state.config.PENDING_USER_OVERLAY_CONTENT,
         "RESPONSE_WATERMARK": request.app.state.config.RESPONSE_WATERMARK,
@@ -853,18 +1029,24 @@ async def get_admin_config(request: Request, user=Depends(get_admin_user)):
 
 class AdminConfig(BaseModel):
     SHOW_ADMIN_DETAILS: bool
+    ADMIN_EMAIL: Optional[str] = None
     WEBUI_URL: str
     ENABLE_SIGNUP: bool
-    ENABLE_API_KEY: bool
-    ENABLE_API_KEY_ENDPOINT_RESTRICTIONS: bool
-    API_KEY_ALLOWED_ENDPOINTS: str
+    ENABLE_API_KEYS: bool
+    ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS: bool
+    API_KEYS_ALLOWED_ENDPOINTS: str
     DEFAULT_USER_ROLE: str
+    DEFAULT_GROUP_ID: str
     JWT_EXPIRES_IN: str
     ENABLE_COMMUNITY_SHARING: bool
     ENABLE_MESSAGE_RATING: bool
+    ENABLE_FOLDERS: bool
+    FOLDER_MAX_FILE_COUNT: Optional[int | str] = None
     ENABLE_CHANNELS: bool
+    ENABLE_MEMORIES: bool
     ENABLE_NOTES: bool
     ENABLE_USER_WEBHOOKS: bool
+    ENABLE_USER_STATUS: bool
     PENDING_USER_OVERLAY_TITLE: Optional[str] = None
     PENDING_USER_OVERLAY_CONTENT: Optional[str] = None
     RESPONSE_WATERMARK: Optional[str] = None
@@ -875,23 +1057,31 @@ async def update_admin_config(
     request: Request, form_data: AdminConfig, user=Depends(get_admin_user)
 ):
     request.app.state.config.SHOW_ADMIN_DETAILS = form_data.SHOW_ADMIN_DETAILS
+    request.app.state.config.ADMIN_EMAIL = form_data.ADMIN_EMAIL
     request.app.state.config.WEBUI_URL = form_data.WEBUI_URL
     request.app.state.config.ENABLE_SIGNUP = form_data.ENABLE_SIGNUP
 
-    request.app.state.config.ENABLE_API_KEY = form_data.ENABLE_API_KEY
-    request.app.state.config.ENABLE_API_KEY_ENDPOINT_RESTRICTIONS = (
-        form_data.ENABLE_API_KEY_ENDPOINT_RESTRICTIONS
+    request.app.state.config.ENABLE_API_KEYS = form_data.ENABLE_API_KEYS
+    request.app.state.config.ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS = (
+        form_data.ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS
     )
-    request.app.state.config.API_KEY_ALLOWED_ENDPOINTS = (
-        form_data.API_KEY_ALLOWED_ENDPOINTS
+    request.app.state.config.API_KEYS_ALLOWED_ENDPOINTS = (
+        form_data.API_KEYS_ALLOWED_ENDPOINTS
     )
 
+    request.app.state.config.ENABLE_FOLDERS = form_data.ENABLE_FOLDERS
+    request.app.state.config.FOLDER_MAX_FILE_COUNT = (
+        int(form_data.FOLDER_MAX_FILE_COUNT) if form_data.FOLDER_MAX_FILE_COUNT else ""
+    )
     request.app.state.config.ENABLE_CHANNELS = form_data.ENABLE_CHANNELS
+    request.app.state.config.ENABLE_MEMORIES = form_data.ENABLE_MEMORIES
     request.app.state.config.ENABLE_NOTES = form_data.ENABLE_NOTES
 
     if form_data.DEFAULT_USER_ROLE in ["pending", "user", "admin"]:
         request.app.state.config.DEFAULT_USER_ROLE = form_data.DEFAULT_USER_ROLE
 
+    request.app.state.config.DEFAULT_GROUP_ID = form_data.DEFAULT_GROUP_ID
+
     pattern = r"^(-1|0|(-?\d+(\.\d+)?)(ms|s|m|h|d|w))$"
 
     # Check if the input string matches the pattern
@@ -904,6 +1094,7 @@ async def update_admin_config(
     request.app.state.config.ENABLE_MESSAGE_RATING = form_data.ENABLE_MESSAGE_RATING
 
     request.app.state.config.ENABLE_USER_WEBHOOKS = form_data.ENABLE_USER_WEBHOOKS
+    request.app.state.config.ENABLE_USER_STATUS = form_data.ENABLE_USER_STATUS
 
     request.app.state.config.PENDING_USER_OVERLAY_TITLE = (
         form_data.PENDING_USER_OVERLAY_TITLE
@@ -916,18 +1107,24 @@ async def update_admin_config(
 
     return {
         "SHOW_ADMIN_DETAILS": request.app.state.config.SHOW_ADMIN_DETAILS,
+        "ADMIN_EMAIL": request.app.state.config.ADMIN_EMAIL,
         "WEBUI_URL": request.app.state.config.WEBUI_URL,
         "ENABLE_SIGNUP": request.app.state.config.ENABLE_SIGNUP,
-        "ENABLE_API_KEY": request.app.state.config.ENABLE_API_KEY,
-        "ENABLE_API_KEY_ENDPOINT_RESTRICTIONS": request.app.state.config.ENABLE_API_KEY_ENDPOINT_RESTRICTIONS,
-        "API_KEY_ALLOWED_ENDPOINTS": request.app.state.config.API_KEY_ALLOWED_ENDPOINTS,
+        "ENABLE_API_KEYS": request.app.state.config.ENABLE_API_KEYS,
+        "ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS": request.app.state.config.ENABLE_API_KEYS_ENDPOINT_RESTRICTIONS,
+        "API_KEYS_ALLOWED_ENDPOINTS": request.app.state.config.API_KEYS_ALLOWED_ENDPOINTS,
         "DEFAULT_USER_ROLE": request.app.state.config.DEFAULT_USER_ROLE,
+        "DEFAULT_GROUP_ID": request.app.state.config.DEFAULT_GROUP_ID,
         "JWT_EXPIRES_IN": request.app.state.config.JWT_EXPIRES_IN,
         "ENABLE_COMMUNITY_SHARING": request.app.state.config.ENABLE_COMMUNITY_SHARING,
         "ENABLE_MESSAGE_RATING": request.app.state.config.ENABLE_MESSAGE_RATING,
+        "ENABLE_FOLDERS": request.app.state.config.ENABLE_FOLDERS,
+        "FOLDER_MAX_FILE_COUNT": request.app.state.config.FOLDER_MAX_FILE_COUNT,
         "ENABLE_CHANNELS": request.app.state.config.ENABLE_CHANNELS,
+        "ENABLE_MEMORIES": request.app.state.config.ENABLE_MEMORIES,
         "ENABLE_NOTES": request.app.state.config.ENABLE_NOTES,
         "ENABLE_USER_WEBHOOKS": request.app.state.config.ENABLE_USER_WEBHOOKS,
+        "ENABLE_USER_STATUS": request.app.state.config.ENABLE_USER_STATUS,
         "PENDING_USER_OVERLAY_TITLE": request.app.state.config.PENDING_USER_OVERLAY_TITLE,
         "PENDING_USER_OVERLAY_CONTENT": request.app.state.config.PENDING_USER_OVERLAY_CONTENT,
         "RESPONSE_WATERMARK": request.app.state.config.RESPONSE_WATERMARK,
@@ -1044,15 +1241,19 @@ async def update_ldap_config(
 
 # create api key
 @router.post("/api_key", response_model=ApiKey)
-async def generate_api_key(request: Request, user=Depends(get_current_user)):
-    if not request.app.state.config.ENABLE_API_KEY:
+async def generate_api_key(
+    request: Request, user=Depends(get_current_user), db: Session = Depends(get_session)
+):
+    if not request.app.state.config.ENABLE_API_KEYS or not has_permission(
+        user.id, "features.api_keys", request.app.state.config.USER_PERMISSIONS
+    ):
         raise HTTPException(
-            status.HTTP_403_FORBIDDEN,
+            status_code=status.HTTP_403_FORBIDDEN,
             detail=ERROR_MESSAGES.API_KEY_CREATION_NOT_ALLOWED,
         )
 
     api_key = create_api_key()
-    success = Users.update_user_api_key_by_id(user.id, api_key)
+    success = Users.update_user_api_key_by_id(user.id, api_key, db=db)
 
     if success:
         return {
@@ -1064,15 +1265,18 @@ async def generate_api_key(request: Request, user=Depends(get_current_user)):
 
 # delete api key
 @router.delete("/api_key", response_model=bool)
-async def delete_api_key(user=Depends(get_current_user)):
-    success = Users.update_user_api_key_by_id(user.id, None)
-    return success
+async def delete_api_key(
+    user=Depends(get_current_user), db: Session = Depends(get_session)
+):
+    return Users.delete_user_api_key_by_id(user.id, db=db)
 
 
 # get api key
 @router.get("/api_key", response_model=ApiKey)
-async def get_api_key(user=Depends(get_current_user)):
-    api_key = Users.get_user_api_key_by_id(user.id)
+async def get_api_key(
+    user=Depends(get_current_user), db: Session = Depends(get_session)
+):
+    api_key = Users.get_user_api_key_by_id(user.id, db=db)
     if api_key:
         return {
             "api_key": api_key,

backend/open_webui/routers/configs.py

@@ -6,6 +6,7 @@ import aiohttp
 
 from typing import Optional
 
+from open_webui.env import AIOHTTP_CLIENT_TIMEOUT
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.config import get_config, save_config
 from open_webui.config import BannerModel
@@ -18,7 +19,6 @@ from open_webui.utils.tools import (
 from open_webui.utils.mcp.client import MCPClient
 from open_webui.models.oauth_sessions import OAuthSessions
 
-from open_webui.env import SRC_LOG_LEVELS
 
 from open_webui.utils.oauth import (
     get_discovery_urls,
@@ -32,7 +32,6 @@ from mcp.shared.auth import OAuthMetadata
 router = APIRouter()
 
 log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 ############################
@@ -144,6 +143,7 @@ class ToolServerConnection(BaseModel):
     path: str
     type: Optional[str] = "openapi"  # openapi, mcp
     auth_type: Optional[str]
+    headers: Optional[dict | str] = None
     key: Optional[str]
     config: Optional[dict]
 
@@ -229,7 +229,10 @@ async def verify_tool_servers_config(
                     log.debug(
                         f"Trying to fetch OAuth 2.1 discovery document from {discovery_url}"
                     )
-                    async with aiohttp.ClientSession(trust_env=True) as session:
+                    async with aiohttp.ClientSession(
+                        trust_env=True,
+                        timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT),
+                    ) as session:
                         async with session.get(
                             discovery_url
                         ) as oauth_server_metadata_response:
@@ -270,18 +273,26 @@ async def verify_tool_servers_config(
                     elif form_data.auth_type == "session":
                         token = request.state.token.credentials
                     elif form_data.auth_type == "system_oauth":
+                        oauth_token = None
                         try:
                             if request.cookies.get("oauth_session_id", None):
-                                token = await request.app.state.oauth_manager.get_oauth_token(
+                                oauth_token = await request.app.state.oauth_manager.get_oauth_token(
                                     user.id,
                                     request.cookies.get("oauth_session_id", None),
                                 )
+
+                                if oauth_token:
+                                    token = oauth_token.get("access_token", "")
                         except Exception as e:
                             pass
-
                     if token:
                         headers = {"Authorization": f"Bearer {token}"}
 
+                    if form_data.headers and isinstance(form_data.headers, dict):
+                        if headers is None:
+                            headers = {}
+                        headers.update(form_data.headers)
+
                     await client.connect(form_data.url, headers=headers)
                     specs = await client.list_tool_specs()
                     return {
@@ -299,6 +310,7 @@ async def verify_tool_servers_config(
                         await client.disconnect()
         else:  # openapi
             token = None
+            headers = None
             if form_data.auth_type == "bearer":
                 token = form_data.key
             elif form_data.auth_type == "session":
@@ -306,15 +318,29 @@ async def verify_tool_servers_config(
             elif form_data.auth_type == "system_oauth":
                 try:
                     if request.cookies.get("oauth_session_id", None):
-                        token = await request.app.state.oauth_manager.get_oauth_token(
-                            user.id,
-                            request.cookies.get("oauth_session_id", None),
+                        oauth_token = (
+                            await request.app.state.oauth_manager.get_oauth_token(
+                                user.id,
+                                request.cookies.get("oauth_session_id", None),
+                            )
                         )
+
+                        if oauth_token:
+                            token = oauth_token.get("access_token", "")
+
                 except Exception as e:
                     pass
 
+            if token:
+                headers = {"Authorization": f"Bearer {token}"}
+
+            if form_data.headers and isinstance(form_data.headers, dict):
+                if headers is None:
+                    headers = {}
+                headers.update(form_data.headers)
+
             url = get_tool_server_url(form_data.url, form_data.path)
-            return await get_tool_server_data(token, url)
+            return await get_tool_server_data(url, headers=headers)
     except HTTPException as e:
         raise e
     except Exception as e:
@@ -439,6 +465,7 @@ async def set_code_execution_config(
 ############################
 class ModelsConfigForm(BaseModel):
     DEFAULT_MODELS: Optional[str]
+    DEFAULT_PINNED_MODELS: Optional[str]
     MODEL_ORDER_LIST: Optional[list[str]]
 
 
@@ -446,6 +473,7 @@ class ModelsConfigForm(BaseModel):
 async def get_models_config(request: Request, user=Depends(get_admin_user)):
     return {
         "DEFAULT_MODELS": request.app.state.config.DEFAULT_MODELS,
+        "DEFAULT_PINNED_MODELS": request.app.state.config.DEFAULT_PINNED_MODELS,
         "MODEL_ORDER_LIST": request.app.state.config.MODEL_ORDER_LIST,
     }
 
@@ -455,9 +483,11 @@ async def set_models_config(
     request: Request, form_data: ModelsConfigForm, user=Depends(get_admin_user)
 ):
     request.app.state.config.DEFAULT_MODELS = form_data.DEFAULT_MODELS
+    request.app.state.config.DEFAULT_PINNED_MODELS = form_data.DEFAULT_PINNED_MODELS
     request.app.state.config.MODEL_ORDER_LIST = form_data.MODEL_ORDER_LIST
     return {
         "DEFAULT_MODELS": request.app.state.config.DEFAULT_MODELS,
+        "DEFAULT_PINNED_MODELS": request.app.state.config.DEFAULT_PINNED_MODELS,
         "MODEL_ORDER_LIST": request.app.state.config.MODEL_ORDER_LIST,
     }
 

backend/open_webui/routers/evaluations.py

@@ -1,21 +1,279 @@
 from typing import Optional
+import logging
 from fastapi import APIRouter, Depends, HTTPException, status, Request
+from fastapi.concurrency import run_in_threadpool
 from pydantic import BaseModel
 
 from open_webui.models.users import Users, UserModel
 from open_webui.models.feedbacks import (
+    FeedbackIdResponse,
     FeedbackModel,
     FeedbackResponse,
     FeedbackForm,
+    FeedbackUserResponse,
+    FeedbackListResponse,
+    LeaderboardFeedbackData,
+    ModelHistoryEntry,
+    ModelHistoryResponse,
     Feedbacks,
 )
 
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.utils.auth import get_admin_user, get_verified_user
+from open_webui.internal.db import get_session
+from sqlalchemy.orm import Session
+
+log = logging.getLogger(__name__)
+
 
 router = APIRouter()
 
 
+# Leaderboard Elo Rating Computation
+#
+# How it works:
+# 1. Each model starts with a rating of 1000
+# 2. When a user picks a winner between two models, ratings are adjusted:
+#    - Winner gains points, loser loses points
+#    - The amount depends on expected outcome (upset = bigger change)
+# 3. The Elo formula: new_rating = old_rating + K * (actual - expected)
+#    - K=32 controls how much ratings can change per match
+#    - expected = probability of winning based on current ratings
+#
+# Query-based re-ranking (optional):
+#    When a user searches for a topic (e.g., "coding"), we want to show
+#    which models perform best FOR THAT TOPIC. We do this by:
+#    1. Computing semantic similarity between the query and each feedback's tags
+#    2. Using that similarity as a weight in the Elo calculation
+#    3. Feedbacks about "coding" contribute more to the final ranking
+#    4. Feedbacks about unrelated topics (e.g., "cooking") contribute less
+#    This gives topic-specific leaderboards without needing separate data.
+
+import os
+
+EMBEDDING_MODEL_NAME = os.environ.get(
+    "AUXILIARY_EMBEDDING_MODEL", "TaylorAI/bge-micro-v2"
+)
+_embedding_model = None
+
+
+def _get_embedding_model():
+    global _embedding_model
+    if _embedding_model is None:
+        try:
+            from sentence_transformers import SentenceTransformer
+
+            _embedding_model = SentenceTransformer(EMBEDDING_MODEL_NAME)
+        except Exception as e:
+            log.error(f"Embedding model load failed: {e}")
+    return _embedding_model
+
+
+def _calculate_elo(
+    feedbacks: list[LeaderboardFeedbackData], similarities: dict = None
+) -> dict:
+    """
+    Calculate Elo ratings for models based on user feedback.
+
+    Each feedback represents a comparison where a user rated one model
+    against its opponents (sibling_model_ids). Rating=1 means the model won,
+    rating=-1 means it lost.
+
+    The Elo system adjusts ratings based on:
+    - Current rating difference (upsets cause bigger swings)
+    - Optional similarity weights (for query-based filtering)
+
+    Returns: {model_id: {"rating": float, "won": int, "lost": int}}
+    """
+    K_FACTOR = 32  # Standard Elo K-factor for rating volatility
+    model_stats = {}
+
+    def get_or_create_stats(model_id):
+        if model_id not in model_stats:
+            model_stats[model_id] = {"rating": 1000.0, "won": 0, "lost": 0}
+        return model_stats[model_id]
+
+    for feedback in feedbacks:
+        data = feedback.data or {}
+        winner_id = data.get("model_id")
+        rating_value = str(data.get("rating", ""))
+        if not winner_id or rating_value not in ("1", "-1"):
+            continue
+
+        won = rating_value == "1"
+        weight = similarities.get(feedback.id, 1.0) if similarities else 1.0
+
+        for opponent_id in data.get("sibling_model_ids") or []:
+            winner = get_or_create_stats(winner_id)
+            opponent = get_or_create_stats(opponent_id)
+            expected = 1 / (1 + 10 ** ((opponent["rating"] - winner["rating"]) / 400))
+
+            winner["rating"] += K_FACTOR * ((1 if won else 0) - expected) * weight
+            opponent["rating"] += (
+                K_FACTOR * ((0 if won else 1) - (1 - expected)) * weight
+            )
+
+            if won:
+                winner["won"] += 1
+                opponent["lost"] += 1
+            else:
+                winner["lost"] += 1
+                opponent["won"] += 1
+
+    return model_stats
+
+
+def _get_top_tags(feedbacks: list[LeaderboardFeedbackData], limit: int = 5) -> dict:
+    """
+    Count tag occurrences per model and return the most frequent ones.
+
+    Each feedback can have tags describing the conversation topic.
+    This aggregates those tags per model to show what topics each model
+    is commonly used for.
+
+    Returns: {model_id: [{"tag": str, "count": int}, ...]}
+    """
+    from collections import defaultdict
+
+    tag_counts = defaultdict(lambda: defaultdict(int))
+
+    for feedback in feedbacks:
+        data = feedback.data or {}
+        model_id = data.get("model_id")
+        if model_id:
+            for tag in data.get("tags", []):
+                tag_counts[model_id][tag] += 1
+
+    return {
+        model_id: [
+            {"tag": tag, "count": count}
+            for tag, count in sorted(tags.items(), key=lambda x: -x[1])[:limit]
+        ]
+        for model_id, tags in tag_counts.items()
+    }
+
+
+def _compute_similarities(feedbacks: list[LeaderboardFeedbackData], query: str) -> dict:
+    """
+    Compute how relevant each feedback is to a search query.
+
+    Uses embeddings to find semantic similarity between the query and
+    each feedback's tags. Higher similarity means the feedback is more
+    relevant to what the user searched for.
+
+    This is used to weight Elo calculations - feedbacks matching the
+    query have more influence on the final rankings.
+
+    Returns: {feedback_id: similarity_score (0-1)}
+    """
+    import numpy as np
+
+    embedding_model = _get_embedding_model()
+    if not embedding_model:
+        return {}
+
+    all_tags = list(
+        {
+            tag
+            for feedback in feedbacks
+            if feedback.data
+            for tag in feedback.data.get("tags", [])
+        }
+    )
+    if not all_tags:
+        return {}
+
+    try:
+        tag_embeddings = embedding_model.encode(all_tags)
+        query_embedding = embedding_model.encode([query])[0]
+    except Exception as e:
+        log.error(f"Embedding error: {e}")
+        return {}
+
+    # Vectorized cosine similarity
+    tag_norms = np.linalg.norm(tag_embeddings, axis=1)
+    query_norm = np.linalg.norm(query_embedding)
+    similarities = np.dot(tag_embeddings, query_embedding) / (
+        tag_norms * query_norm + 1e-9
+    )
+    tag_similarity_map = dict(zip(all_tags, similarities.tolist()))
+
+    return {
+        feedback.id: max(
+            (
+                tag_similarity_map.get(tag, 0)
+                for tag in (feedback.data or {}).get("tags", [])
+            ),
+            default=0,
+        )
+        for feedback in feedbacks
+    }
+
+
+class LeaderboardEntry(BaseModel):
+    model_id: str
+    rating: int
+    won: int
+    lost: int
+    count: int
+    top_tags: list[dict]
+
+
+class LeaderboardResponse(BaseModel):
+    entries: list[LeaderboardEntry]
+
+
+@router.get("/leaderboard", response_model=LeaderboardResponse)
+async def get_leaderboard(
+    query: Optional[str] = None,
+    user=Depends(get_admin_user),
+    db: Session = Depends(get_session),
+):
+    """Get model leaderboard with Elo ratings. Query filters by tag similarity."""
+    feedbacks = Feedbacks.get_feedbacks_for_leaderboard(db=db)
+
+    similarities = None
+    if query and query.strip():
+        similarities = await run_in_threadpool(
+            _compute_similarities, feedbacks, query.strip()
+        )
+
+    elo_stats = _calculate_elo(feedbacks, similarities)
+    tags_by_model = _get_top_tags(feedbacks)
+
+    entries = sorted(
+        [
+            LeaderboardEntry(
+                model_id=mid,
+                rating=round(s["rating"]),
+                won=s["won"],
+                lost=s["lost"],
+                count=s["won"] + s["lost"],
+                top_tags=tags_by_model.get(mid, []),
+            )
+            for mid, s in elo_stats.items()
+        ],
+        key=lambda e: e.rating,
+        reverse=True,
+    )
+
+    return LeaderboardResponse(entries=entries)
+
+
+@router.get("/leaderboard/{model_id}/history", response_model=ModelHistoryResponse)
+async def get_model_history(
+    model_id: str,
+    days: int = 30,
+    user=Depends(get_admin_user),
+    db: Session = Depends(get_session),
+):
+    """Get daily win/loss history for a specific model."""
+    history = Feedbacks.get_model_evaluation_history(
+        model_id=model_id, days=days, db=db
+    )
+    return ModelHistoryResponse(model_id=model_id, history=history)
+
+
 ############################
 # GetConfig
 ############################
@@ -56,68 +314,89 @@ async def update_config(
     }
 
 
-class UserResponse(BaseModel):
-    id: str
-    name: str
-    email: str
-    role: str = "pending"
-
-    last_active_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
-    created_at: int  # timestamp in epoch
+@router.get("/feedbacks/all", response_model=list[FeedbackResponse])
+async def get_all_feedbacks(
+    user=Depends(get_admin_user), db: Session = Depends(get_session)
+):
+    feedbacks = Feedbacks.get_all_feedbacks(db=db)
+    return feedbacks
 
 
-class FeedbackUserResponse(FeedbackResponse):
-    user: Optional[UserResponse] = None
-
-
-@router.get("/feedbacks/all", response_model=list[FeedbackUserResponse])
-async def get_all_feedbacks(user=Depends(get_admin_user)):
-    feedbacks = Feedbacks.get_all_feedbacks()
-
-    feedback_list = []
-    for feedback in feedbacks:
-        user = Users.get_user_by_id(feedback.user_id)
-        feedback_list.append(
-            FeedbackUserResponse(
-                **feedback.model_dump(),
-                user=UserResponse(**user.model_dump()) if user else None,
-            )
-        )
-    return feedback_list
+@router.get("/feedbacks/all/ids", response_model=list[FeedbackIdResponse])
+async def get_all_feedback_ids(
+    user=Depends(get_admin_user), db: Session = Depends(get_session)
+):
+    return Feedbacks.get_all_feedback_ids(db=db)
 
 
 @router.delete("/feedbacks/all")
-async def delete_all_feedbacks(user=Depends(get_admin_user)):
-    success = Feedbacks.delete_all_feedbacks()
+async def delete_all_feedbacks(
+    user=Depends(get_admin_user), db: Session = Depends(get_session)
+):
+    success = Feedbacks.delete_all_feedbacks(db=db)
     return success
 
 
 @router.get("/feedbacks/all/export", response_model=list[FeedbackModel])
-async def get_all_feedbacks(user=Depends(get_admin_user)):
-    feedbacks = Feedbacks.get_all_feedbacks()
+async def export_all_feedbacks(
+    user=Depends(get_admin_user), db: Session = Depends(get_session)
+):
+    feedbacks = Feedbacks.get_all_feedbacks(db=db)
     return feedbacks
 
 
 @router.get("/feedbacks/user", response_model=list[FeedbackUserResponse])
-async def get_feedbacks(user=Depends(get_verified_user)):
-    feedbacks = Feedbacks.get_feedbacks_by_user_id(user.id)
+async def get_feedbacks(
+    user=Depends(get_verified_user), db: Session = Depends(get_session)
+):
+    feedbacks = Feedbacks.get_feedbacks_by_user_id(user.id, db=db)
     return feedbacks
 
 
 @router.delete("/feedbacks", response_model=bool)
-async def delete_feedbacks(user=Depends(get_verified_user)):
-    success = Feedbacks.delete_feedbacks_by_user_id(user.id)
+async def delete_feedbacks(
+    user=Depends(get_verified_user), db: Session = Depends(get_session)
+):
+    success = Feedbacks.delete_feedbacks_by_user_id(user.id, db=db)
     return success
 
 
+PAGE_ITEM_COUNT = 30
+
+
+@router.get("/feedbacks/list", response_model=FeedbackListResponse)
+async def get_feedbacks(
+    order_by: Optional[str] = None,
+    direction: Optional[str] = None,
+    page: Optional[int] = 1,
+    user=Depends(get_admin_user),
+    db: Session = Depends(get_session),
+):
+    limit = PAGE_ITEM_COUNT
+
+    page = max(1, page)
+    skip = (page - 1) * limit
+
+    filter = {}
+    if order_by:
+        filter["order_by"] = order_by
+    if direction:
+        filter["direction"] = direction
+
+    result = Feedbacks.get_feedback_items(filter=filter, skip=skip, limit=limit, db=db)
+    return result
+
+
 @router.post("/feedback", response_model=FeedbackModel)
 async def create_feedback(
     request: Request,
     form_data: FeedbackForm,
     user=Depends(get_verified_user),
+    db: Session = Depends(get_session),
 ):
-    feedback = Feedbacks.insert_new_feedback(user_id=user.id, form_data=form_data)
+    feedback = Feedbacks.insert_new_feedback(
+        user_id=user.id, form_data=form_data, db=db
+    )
     if not feedback:
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
@@ -128,11 +407,15 @@ async def create_feedback(
 
 
 @router.get("/feedback/{id}", response_model=FeedbackModel)
-async def get_feedback_by_id(id: str, user=Depends(get_verified_user)):
+async def get_feedback_by_id(
+    id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)
+):
     if user.role == "admin":
-        feedback = Feedbacks.get_feedback_by_id(id=id)
+        feedback = Feedbacks.get_feedback_by_id(id=id, db=db)
     else:
-        feedback = Feedbacks.get_feedback_by_id_and_user_id(id=id, user_id=user.id)
+        feedback = Feedbacks.get_feedback_by_id_and_user_id(
+            id=id, user_id=user.id, db=db
+        )
 
     if not feedback:
         raise HTTPException(
@@ -144,13 +427,16 @@ async def get_feedback_by_id(id: str, user=Depends(get_verified_user)):
 
 @router.post("/feedback/{id}", response_model=FeedbackModel)
 async def update_feedback_by_id(
-    id: str, form_data: FeedbackForm, user=Depends(get_verified_user)
+    id: str,
+    form_data: FeedbackForm,
+    user=Depends(get_verified_user),
+    db: Session = Depends(get_session),
 ):
     if user.role == "admin":
-        feedback = Feedbacks.update_feedback_by_id(id=id, form_data=form_data)
+        feedback = Feedbacks.update_feedback_by_id(id=id, form_data=form_data, db=db)
     else:
         feedback = Feedbacks.update_feedback_by_id_and_user_id(
-            id=id, user_id=user.id, form_data=form_data
+            id=id, user_id=user.id, form_data=form_data, db=db
         )
 
     if not feedback:
@@ -162,11 +448,15 @@ async def update_feedback_by_id(
 
 
 @router.delete("/feedback/{id}")
-async def delete_feedback_by_id(id: str, user=Depends(get_verified_user)):
+async def delete_feedback_by_id(
+    id: str, user=Depends(get_verified_user), db: Session = Depends(get_session)
+):
     if user.role == "admin":
-        success = Feedbacks.delete_feedback_by_id(id=id)
+        success = Feedbacks.delete_feedback_by_id(id=id, db=db)
     else:
-        success = Feedbacks.delete_feedback_by_id_and_user_id(id=id, user_id=user.id)
+        success = Feedbacks.delete_feedback_by_id_and_user_id(
+            id=id, user_id=user.id, db=db
+        )
 
     if not success:
         raise HTTPException(