Merge pull request #11257 from open-webui/dev

0.5.20

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,80 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-labels: ''
-assignees: ''
----
-
-# Bug Report
-
-## Important Notes
-
-- **Before submitting a bug report**: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project.
-
-- **Collaborate respectfully**: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours.
-
-- **Contributing**: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.
-
-- **Bug reproducibility**: If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!
-
-Note: Please remove the notes above when submitting your post. Thank you for your understanding and support!
-
----
-
-## Installation Method
-
-[Describe the method you used to install the project, e.g., git clone, Docker, pip, etc.]
-
-## Environment
-
-- **Open WebUI Version:** [e.g., v0.3.11]
-- **Ollama (if applicable):** [e.g., v0.2.0, v0.1.32-rc1]
-
-- **Operating System:** [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04]
-- **Browser (if applicable):** [e.g., Chrome 100.0, Firefox 98.0]
-
-**Confirmation:**
-
-- [ ] I have read and followed all the instructions provided in the README.md.
-- [ ] I am on the latest version of both Open WebUI and Ollama.
-- [ ] I have included the browser console logs.
-- [ ] I have included the Docker container logs.
-- [ ] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
-
-## Expected Behavior:
-
-[Describe what you expected to happen.]
-
-## Actual Behavior:
-
-[Describe what actually happened.]
-
-## Description
-
-**Bug Summary:**
-[Provide a brief but clear summary of the bug]
-
-## Reproduction Details
-
-**Steps to Reproduce:**
-[Outline the steps to reproduce the bug. Be as detailed as possible.]
-
-## Logs and Screenshots
-
-**Browser Console Logs:**
-[Include relevant browser console logs, if applicable]
-
-**Docker Container Logs:**
-[Include relevant Docker container logs, if applicable]
-
-**Screenshots/Screen Recordings (if applicable):**
-[Attach any relevant screenshots to help illustrate the issue]
-
-## Additional Information
-
-[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]
-
-## Note
-
-If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -0,0 +1,144 @@
+name: Bug Report
+description: Create a detailed bug report to help us improve Open WebUI.
+title: 'issue: '
+labels: ['bug', 'triage']
+assignees: []
+body:
+  - type: markdown
+    attributes:
+      value: |
+        # Bug Report
+
+        ## Important Notes
+
+        - **Before submitting a bug report**: Please check the [Issues](https://github.com/open-webui/open-webui/issues) or [Discussions](https://github.com/open-webui/open-webui/discussions) sections to see if a similar issue has already been reported. If unsure, start a discussion first, as this helps us efficiently focus on improving the project.
+
+        - **Respectful collaboration**: Open WebUI is a volunteer-driven project with a single maintainer and contributors who also have full-time jobs. Please be constructive and respectful in your communication.
+
+        - **Contributing**: If you encounter an issue, consider submitting a pull request or forking the project. We prioritize preventing contributor burnout to maintain Open WebUI's quality.
+
+        - **Bug Reproducibility**: If a bug cannot be reproduced using a `:main` or `:dev` Docker setup or with `pip install` on Python 3.11, community assistance may be required. In such cases, we will move it to the "[Issues](https://github.com/open-webui/open-webui/discussions/categories/issues)" Discussions section. Your help is appreciated!
+
+  - type: checkboxes
+    id: issue-check
+    attributes:
+      label: Check Existing Issues
+      description: Confirm that you’ve checked for existing reports before submitting a new one.
+      options:
+        - label: I have searched the existing issues and discussions.
+          required: true
+
+  - type: dropdown
+    id: installation-method
+    attributes:
+      label: Installation Method
+      description: How did you install Open WebUI?
+      options:
+        - Git Clone
+        - Pip Install
+        - Docker
+        - Other
+    validations:
+      required: true
+
+  - type: input
+    id: open-webui-version
+    attributes:
+      label: Open WebUI Version
+      description: Specify the version (e.g., v0.3.11)
+    validations:
+      required: true
+
+  - type: input
+    id: ollama-version
+    attributes:
+      label: Ollama Version (if applicable)
+      description: Specify the version (e.g., v0.2.0, or v0.1.32-rc1)
+    validations:
+      required: false
+
+  - type: input
+    id: operating-system
+    attributes:
+      label: Operating System
+      description: Specify the OS (e.g., Windows 10, macOS Sonoma, Ubuntu 22.04)
+    validations:
+      required: true
+
+  - type: input
+    id: browser
+    attributes:
+      label: Browser (if applicable)
+      description: Specify the browser/version (e.g., Chrome 100.0, Firefox 98.0)
+    validations:
+      required: false
+
+  - type: checkboxes
+    id: confirmation
+    attributes:
+      label: Confirmation
+      description: Ensure the following prerequisites have been met.
+      options:
+        - label: I have read and followed all instructions in `README.md`.
+          required: true
+        - label: I am using the latest version of **both** Open WebUI and Ollama.
+          required: true
+        - label: I have checked the browser console logs.
+          required: true
+        - label: I have checked the Docker container logs.
+          required: true
+        - label: I have listed steps to reproduce the bug in detail.
+          required: true
+
+  - type: textarea
+    id: expected-behavior
+    attributes:
+      label: Expected Behavior
+      description: Describe what should have happened.
+    validations:
+      required: true
+
+  - type: textarea
+    id: actual-behavior
+    attributes:
+      label: Actual Behavior
+      description: Describe what actually happened.
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduction-steps
+    attributes:
+      label: Steps to Reproduce
+      description: Provide step-by-step instructions to reproduce the issue.
+      placeholder: |
+        1. Go to '...'
+        2. Click on '...'
+        3. Scroll down to '...'
+        4. See the error message '...'
+    validations:
+      required: true
+
+  - type: textarea
+    id: logs-screenshots
+    attributes:
+      label: Logs & Screenshots
+      description: Include relevant logs, errors, or screenshots to help diagnose the issue.
+      placeholder: 'Attach logs from the browser console, Docker logs, or error messages.'
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional-info
+    attributes:
+      label: Additional Information
+      description: Provide any extra details that may assist in understanding the issue.
+    validations:
+      required: false
+
+  - type: markdown
+    attributes:
+      value: |
+        ## Note
+        If the bug report is incomplete or does not follow instructions, it may not be addressed. Ensure that you've followed all the **README.md** and **troubleshooting.md** guidelines, and provide all necessary information for us to reproduce the issue.  
+        Thank you for contributing to Open WebUI!

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,35 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
----
-
-# Feature Request
-
-## Important Notes
-
-- **Before submitting a report**: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project.
-
-- **Collaborate respectfully**: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours.
-
-- **Contributing**: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.
-
-- **Bug reproducibility**: If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!
-
-Note: Please remove the notes above when submitting your post. Thank you for your understanding and support!
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -0,0 +1,64 @@
+name: Feature Request
+description: Suggest an idea for this project
+title: 'feat: '
+labels: ['triage']
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Important Notes
+        ### Before submitting
+        Please check the [Issues](https://github.com/open-webui/open-webui/issues) or [Discussions](https://github.com/open-webui/open-webui/discussions) to see if a similar request has been posted.
+        It's likely we're already tracking it! If you’re unsure, start a discussion post first.
+        This will help us efficiently focus on improving the project.
+
+        ### Collaborate respectfully
+        We value a **constructive attitude**, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We're here to help if you're **open to learning** and **communicating positively**.
+
+        Remember:
+        - Open WebUI is a **volunteer-driven project**
+        - It's managed by a **single maintainer**
+        - It's supported by contributors who also have **full-time jobs**
+
+        We appreciate your time and ask that you **respect ours**.
+
+
+        ### Contributing
+        If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.
+
+        ### Bug reproducibility
+        If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a `pip install` with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "[issues](https://github.com/open-webui/open-webui/discussions/categories/issues)" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!
+
+  - type: checkboxes
+    id: existing-issue
+    attributes:
+      label: Check Existing Issues
+      description: Please confirm that you've checked for existing similar requests
+      options:
+        - label: I have searched the existing issues and discussions.
+          required: true
+  - type: textarea
+    id: problem-description
+    attributes:
+      label: Problem Description
+      description: Is your feature request related to a problem? Please provide a clear and concise description of what the problem is.
+      placeholder: "Ex. I'm always frustrated when..."
+    validations:
+      required: true
+  - type: textarea
+    id: solution-description
+    attributes:
+      label: Desired Solution you'd like
+      description: Clearly describe what you want to happen.
+    validations:
+      required: true
+  - type: textarea
+    id: alternatives-considered
+    attributes:
+      label: Alternatives Considered
+      description: A clear and concise description of any alternative solutions or features you've considered.
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Add any other context or screenshots about the feature request here.

.github/workflows/docker-build.yaml

@@ -14,7 +14,7 @@ env:
 
 jobs:
   build-main-image:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.platform == 'linux/arm64' && 'ubuntu-24.04-arm' || 'ubuntu-latest' }}
     permissions:
       contents: read
       packages: write
@@ -111,7 +111,7 @@ jobs:
           retention-days: 1
 
   build-cuda-image:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.platform == 'linux/arm64' && 'ubuntu-24.04-arm' || 'ubuntu-latest' }}
     permissions:
       contents: read
       packages: write
@@ -211,7 +211,7 @@ jobs:
           retention-days: 1
 
   build-ollama-image:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.platform == 'linux/arm64' && 'ubuntu-24.04-arm' || 'ubuntu-latest' }}
     permissions:
       contents: read
       packages: write

CHANGELOG.md

@@ -5,6 +5,65 @@ 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).
 
+## [0.5.20] - 2025-03-05
+
+### Added
+
+- **⚡ Toggle Code Execution On/Off**: You can now enable or disable code execution, providing more control over security, ensuring a safer and more customizable experience.
+
+### Fixed
+
+- **📜 Pinyin Keyboard Enter Key Now Works Properly**: Resolved an issue where the Enter key for Pinyin keyboards was not functioning as expected, ensuring seamless input for Chinese users.
+- **🖼️ Web Manifest Loading Issue Fixed**: Addressed inconsistencies with 'site.webmanifest', guaranteeing proper loading and representation of the app across different browsers and devices.
+- **📦 Non-Root Container Issue Resolved**: Fixed a critical issue where the UI failed to load correctly in non-root containers, ensuring reliable deployment in various environments.
+
+## [0.5.19] - 2025-03-04
+
+### Added
+
+- **📊 Logit Bias Parameter Support**: Fine-tune conversation dynamics by adjusting the Logit Bias parameter directly in chat settings, giving you more control over model responses.
+- **⌨️ Customizable Enter Behavior**: You can now configure Enter to send messages only when combined with Ctrl (Ctrl+Enter) via Settings > Interface, preventing accidental message sends.
+- **📝 Collapsible Code Blocks**: Easily collapse long code blocks to declutter your chat, making it easier to focus on important details.
+- **🏷️ Tag Selector in Model Selector**: Quickly find and categorize models with the new tag filtering system in the Model Selector, streamlining model discovery.
+- **📈 Experimental Elasticsearch Vector DB Support**: Now supports Elasticsearch as a vector database, offering more flexibility for data retrieval in Retrieval-Augmented Generation (RAG) workflows.
+- **⚙️ General Reliability Enhancements**: Various stability improvements across the WebUI, ensuring a smoother, more consistent experience.
+- **🌍 Updated Translations**: Refined multilingual support for better localization and accuracy across various languages.
+
+### Fixed
+
+- **🔄 "Stream" Hook Activation**: Fixed an issue where the "Stream" hook only worked when globally enabled, ensuring reliable real-time filtering.
+- **📧 LDAP Email Case Sensitivity**: Resolved an issue where LDAP login failed due to email case sensitivity mismatches, improving authentication reliability.
+- **💬 WebSocket Chat Event Registration**: Fixed a bug preventing chat event listeners from being registered upon sign-in, ensuring real-time updates work properly.
+
+## [0.5.18] - 2025-02-27
+
+### Fixed
+
+- **🌐 Open WebUI Now Works Over LAN in Insecure Context**: Resolved an issue preventing Open WebUI from functioning when accessed over a local network in an insecure context, ensuring seamless connectivity.
+- **🔄 UI Now Reflects Deleted Connections Instantly**: Fixed an issue where deleting a connection did not update the UI in real time, ensuring accurate system state visibility.
+- **🛠️ Models Now Display Correctly with ENABLE_FORWARD_USER_INFO_HEADERS**: Addressed a bug where models were not visible when ENABLE_FORWARD_USER_INFO_HEADERS was set, restoring proper model listing.
+
+## [0.5.17] - 2025-02-27
+
+### Added
+
+- **🚀 Instant Document Upload with Bypass Embedding & Retrieval**: Admins can now enable "Bypass Embedding & Retrieval" in Admin Settings > Documents, significantly speeding up document uploads and ensuring full document context is retained without chunking.
+- **🔎 "Stream" Hook for Real-Time Filtering**: The new "stream" hook allows dynamic real-time message filtering. Learn more in our documentation (https://docs.openwebui.com/features/plugin/functions/filter).
+- **☁️ OneDrive Integration**: Early support for OneDrive storage integration has been introduced, expanding file import options.
+- **📈 Enhanced Logging with Loguru**: Backend logging has been improved with Loguru, making debugging and issue tracking far more efficient.
+- **⚙️ General Stability Enhancements**: Backend and frontend refactoring improves performance, ensuring a smoother and more reliable user experience.
+- **🌍 Updated Translations**: Refined multilingual support for better localization and accuracy across various languages.
+
+### Fixed
+
+- **🔄 Reliable Model Imports from the Community Platform**: Resolved import failures, allowing seamless integration of community-shared models without errors.
+- **📊 OpenAI Usage Statistics Restored**: Fixed an issue where OpenAI usage metrics were not displaying correctly, ensuring accurate tracking of usage data.
+- **🗂️ Deduplication for Retrieved Documents**: Documents retrieved during searches are now intelligently deduplicated, meaning no more redundant results—helping to keep information concise and relevant.
+
+### Changed
+
+- **📝 "Full Context Mode" Renamed for Clarity**: The "Full Context Mode" toggle in Web Search settings is now labeled "Bypass Embedding & Retrieval" for consistency across the UI.
+
 ## [0.5.16] - 2025-02-20
 
 ### Fixed

backend/open_webui/config.py

@@ -9,7 +9,6 @@ from pathlib import Path
 from typing import Generic, Optional, TypeVar
 from urllib.parse import urlparse
 
-import chromadb
 import requests
 from pydantic import BaseModel
 from sqlalchemy import JSON, Column, DateTime, Integer, func
@@ -44,7 +43,7 @@ logging.getLogger("uvicorn.access").addFilter(EndpointFilter())
 
 # Function to run the alembic migrations
 def run_migrations():
-    print("Running migrations")
+    log.info("Running migrations")
     try:
         from alembic import command
         from alembic.config import Config
@@ -57,7 +56,7 @@ def run_migrations():
 
         command.upgrade(alembic_cfg, "head")
     except Exception as e:
-        print(f"Error: {e}")
+        log.exception(f"Error running migrations: {e}")
 
 
 run_migrations()
@@ -588,6 +587,17 @@ load_oauth_providers()
 
 STATIC_DIR = Path(os.getenv("STATIC_DIR", OPEN_WEBUI_DIR / "static")).resolve()
 
+for file_path in (FRONTEND_BUILD_DIR / "static").glob("**/*"):
+    if file_path.is_file():
+        target_path = STATIC_DIR / file_path.relative_to(
+            (FRONTEND_BUILD_DIR / "static")
+        )
+        target_path.parent.mkdir(parents=True, exist_ok=True)
+        try:
+            shutil.copyfile(file_path, target_path)
+        except Exception as e:
+            logging.error(f"An error occurred: {e}")
+
 frontend_favicon = FRONTEND_BUILD_DIR / "static" / "favicon.png"
 
 if frontend_favicon.exists():
@@ -660,11 +670,7 @@ if CUSTOM_NAME:
 # LICENSE_KEY
 ####################################
 
-LICENSE_KEY = PersistentConfig(
+LICENSE_KEY = os.environ.get("LICENSE_KEY", "")
-    "LICENSE_KEY",
-    "license.key",
-    os.environ.get("LICENSE_KEY", ""),
-)
 
 ####################################
 # STORAGE PROVIDER
@@ -678,6 +684,10 @@ S3_REGION_NAME = os.environ.get("S3_REGION_NAME", None)
 S3_BUCKET_NAME = os.environ.get("S3_BUCKET_NAME", None)
 S3_KEY_PREFIX = os.environ.get("S3_KEY_PREFIX", None)
 S3_ENDPOINT_URL = os.environ.get("S3_ENDPOINT_URL", None)
+S3_USE_ACCELERATE_ENDPOINT = (
+    os.environ.get("S3_USE_ACCELERATE_ENDPOINT", "False").lower() == "true"
+)
+S3_ADDRESSING_STYLE = os.environ.get("S3_ADDRESSING_STYLE", None)
 
 GCS_BUCKET_NAME = os.environ.get("GCS_BUCKET_NAME", None)
 GOOGLE_APPLICATION_CREDENTIALS_JSON = os.environ.get(
@@ -692,16 +702,16 @@ AZURE_STORAGE_KEY = os.environ.get("AZURE_STORAGE_KEY", None)
 # File Upload DIR
 ####################################
 
-UPLOAD_DIR = f"{DATA_DIR}/uploads"
+UPLOAD_DIR = DATA_DIR / "uploads"
-Path(UPLOAD_DIR).mkdir(parents=True, exist_ok=True)
+UPLOAD_DIR.mkdir(parents=True, exist_ok=True)
 
 
 ####################################
 # Cache DIR
 ####################################
 
-CACHE_DIR = f"{DATA_DIR}/cache"
+CACHE_DIR = DATA_DIR / "cache"
-Path(CACHE_DIR).mkdir(parents=True, exist_ok=True)
+CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 
 ####################################
@@ -1094,7 +1104,7 @@ try:
     banners = json.loads(os.environ.get("WEBUI_BANNERS", "[]"))
     banners = [BannerModel(**banner) for banner in banners]
 except Exception as e:
-    print(f"Error loading WEBUI_BANNERS: {e}")
+    log.exception(f"Error loading WEBUI_BANNERS: {e}")
     banners = []
 
 WEBUI_BANNERS = PersistentConfig("WEBUI_BANNERS", "ui.banners", banners)
@@ -1370,6 +1380,11 @@ Responses from models: {{responses}}"""
 # Code Interpreter
 ####################################
 
+ENABLE_CODE_EXECUTION = PersistentConfig(
+    "ENABLE_CODE_EXECUTION",
+    "code_execution.enable",
+    os.environ.get("ENABLE_CODE_EXECUTION", "True").lower() == "true",
+)
 
 CODE_EXECUTION_ENGINE = PersistentConfig(
     "CODE_EXECUTION_ENGINE",
@@ -1498,21 +1513,27 @@ VECTOR_DB = os.environ.get("VECTOR_DB", "chroma")
 
 # Chroma
 CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
-CHROMA_TENANT = os.environ.get("CHROMA_TENANT", chromadb.DEFAULT_TENANT)
+
-CHROMA_DATABASE = os.environ.get("CHROMA_DATABASE", chromadb.DEFAULT_DATABASE)
+if VECTOR_DB == "chroma":
-CHROMA_HTTP_HOST = os.environ.get("CHROMA_HTTP_HOST", "")
+    import chromadb
-CHROMA_HTTP_PORT = int(os.environ.get("CHROMA_HTTP_PORT", "8000"))
+
-CHROMA_CLIENT_AUTH_PROVIDER = os.environ.get("CHROMA_CLIENT_AUTH_PROVIDER", "")
+    CHROMA_TENANT = os.environ.get("CHROMA_TENANT", chromadb.DEFAULT_TENANT)
-CHROMA_CLIENT_AUTH_CREDENTIALS = os.environ.get("CHROMA_CLIENT_AUTH_CREDENTIALS", "")
+    CHROMA_DATABASE = os.environ.get("CHROMA_DATABASE", chromadb.DEFAULT_DATABASE)
-# Comma-separated list of header=value pairs
+    CHROMA_HTTP_HOST = os.environ.get("CHROMA_HTTP_HOST", "")
-CHROMA_HTTP_HEADERS = os.environ.get("CHROMA_HTTP_HEADERS", "")
+    CHROMA_HTTP_PORT = int(os.environ.get("CHROMA_HTTP_PORT", "8000"))
-if CHROMA_HTTP_HEADERS:
+    CHROMA_CLIENT_AUTH_PROVIDER = os.environ.get("CHROMA_CLIENT_AUTH_PROVIDER", "")
-    CHROMA_HTTP_HEADERS = dict(
+    CHROMA_CLIENT_AUTH_CREDENTIALS = os.environ.get(
-        [pair.split("=") for pair in CHROMA_HTTP_HEADERS.split(",")]
+        "CHROMA_CLIENT_AUTH_CREDENTIALS", ""
     )
-else:
+    # Comma-separated list of header=value pairs
-    CHROMA_HTTP_HEADERS = None
+    CHROMA_HTTP_HEADERS = os.environ.get("CHROMA_HTTP_HEADERS", "")
-CHROMA_HTTP_SSL = os.environ.get("CHROMA_HTTP_SSL", "false").lower() == "true"
+    if CHROMA_HTTP_HEADERS:
+        CHROMA_HTTP_HEADERS = dict(
+            [pair.split("=") for pair in CHROMA_HTTP_HEADERS.split(",")]
+        )
+    else:
+        CHROMA_HTTP_HEADERS = None
+    CHROMA_HTTP_SSL = os.environ.get("CHROMA_HTTP_SSL", "false").lower() == "true"
 # this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (sentence-transformers/all-MiniLM-L6-v2)
 
 # Milvus
@@ -1532,6 +1553,17 @@ OPENSEARCH_CERT_VERIFY = os.environ.get("OPENSEARCH_CERT_VERIFY", False)
 OPENSEARCH_USERNAME = os.environ.get("OPENSEARCH_USERNAME", None)
 OPENSEARCH_PASSWORD = os.environ.get("OPENSEARCH_PASSWORD", None)
 
+# ElasticSearch
+ELASTICSEARCH_URL = os.environ.get("ELASTICSEARCH_URL", "https://localhost:9200")
+ELASTICSEARCH_CA_CERTS = os.environ.get("ELASTICSEARCH_CA_CERTS", None)
+ELASTICSEARCH_API_KEY = os.environ.get("ELASTICSEARCH_API_KEY", None)
+ELASTICSEARCH_USERNAME = os.environ.get("ELASTICSEARCH_USERNAME", None)
+ELASTICSEARCH_PASSWORD = os.environ.get("ELASTICSEARCH_PASSWORD", None)
+ELASTICSEARCH_CLOUD_ID = os.environ.get("ELASTICSEARCH_CLOUD_ID", None)
+SSL_ASSERT_FINGERPRINT = os.environ.get("SSL_ASSERT_FINGERPRINT", None)
+ELASTICSEARCH_INDEX_PREFIX = os.environ.get(
+    "ELASTICSEARCH_INDEX_PREFIX", "open_webui_collections"
+)
 # Pgvector
 PGVECTOR_DB_URL = os.environ.get("PGVECTOR_DB_URL", DATABASE_URL)
 if VECTOR_DB == "pgvector" and not PGVECTOR_DB_URL.startswith("postgres"):
@@ -1566,6 +1598,18 @@ GOOGLE_DRIVE_API_KEY = PersistentConfig(
     os.environ.get("GOOGLE_DRIVE_API_KEY", ""),
 )
 
+ENABLE_ONEDRIVE_INTEGRATION = PersistentConfig(
+    "ENABLE_ONEDRIVE_INTEGRATION",
+    "onedrive.enable",
+    os.getenv("ENABLE_ONEDRIVE_INTEGRATION", "False").lower() == "true",
+)
+
+ONEDRIVE_CLIENT_ID = PersistentConfig(
+    "ONEDRIVE_CLIENT_ID",
+    "onedrive.client_id",
+    os.environ.get("ONEDRIVE_CLIENT_ID", ""),
+)
+
 # RAG Content Extraction
 CONTENT_EXTRACTION_ENGINE = PersistentConfig(
     "CONTENT_EXTRACTION_ENGINE",
@@ -1579,6 +1623,26 @@ TIKA_SERVER_URL = PersistentConfig(
     os.getenv("TIKA_SERVER_URL", "http://tika:9998"),  # Default for sidecar deployment
 )
 
+DOCUMENT_INTELLIGENCE_ENDPOINT = PersistentConfig(
+    "DOCUMENT_INTELLIGENCE_ENDPOINT",
+    "rag.document_intelligence_endpoint",
+    os.getenv("DOCUMENT_INTELLIGENCE_ENDPOINT", ""),
+)
+
+DOCUMENT_INTELLIGENCE_KEY = PersistentConfig(
+    "DOCUMENT_INTELLIGENCE_KEY",
+    "rag.document_intelligence_key",
+    os.getenv("DOCUMENT_INTELLIGENCE_KEY", ""),
+)
+
+
+BYPASS_EMBEDDING_AND_RETRIEVAL = PersistentConfig(
+    "BYPASS_EMBEDDING_AND_RETRIEVAL",
+    "rag.bypass_embedding_and_retrieval",
+    os.environ.get("BYPASS_EMBEDDING_AND_RETRIEVAL", "False").lower() == "true",
+)
+
+
 RAG_TOP_K = PersistentConfig(
     "RAG_TOP_K", "rag.top_k", int(os.environ.get("RAG_TOP_K", "3"))
 )
@@ -1795,10 +1859,10 @@ RAG_WEB_SEARCH_ENGINE = PersistentConfig(
     os.getenv("RAG_WEB_SEARCH_ENGINE", ""),
 )
 
-RAG_WEB_SEARCH_FULL_CONTEXT = PersistentConfig(
+BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = PersistentConfig(
-    "RAG_WEB_SEARCH_FULL_CONTEXT",
+    "BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL",
-    "rag.web.search.full_context",
+    "rag.web.search.bypass_embedding_and_retrieval",
-    os.getenv("RAG_WEB_SEARCH_FULL_CONTEXT", "False").lower() == "true",
+    os.getenv("BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL", "False").lower() == "true",
 )
 
 # You can provide a list of your own websites to filter after performing a web search.
@@ -1936,6 +2000,12 @@ EXA_API_KEY = PersistentConfig(
     os.getenv("EXA_API_KEY", ""),
 )
 
+PERPLEXITY_API_KEY = PersistentConfig(
+    "PERPLEXITY_API_KEY",
+    "rag.web.search.perplexity_api_key",
+    os.getenv("PERPLEXITY_API_KEY", ""),
+)
+
 RAG_WEB_SEARCH_RESULT_COUNT = PersistentConfig(
     "RAG_WEB_SEARCH_RESULT_COUNT",
     "rag.web.search.result_count",
@@ -2375,7 +2445,7 @@ LDAP_SEARCH_BASE = PersistentConfig(
 LDAP_SEARCH_FILTERS = PersistentConfig(
     "LDAP_SEARCH_FILTER",
     "ldap.server.search_filter",
-    os.environ.get("LDAP_SEARCH_FILTER", ""),
+    os.environ.get("LDAP_SEARCH_FILTER", os.environ.get("LDAP_SEARCH_FILTERS", "")),
 )
 
 LDAP_USE_TLS = PersistentConfig(

backend/open_webui/env.py

@@ -65,10 +65,8 @@ except Exception:
 # LOGGING
 ####################################
 
-log_levels = ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]
-
 GLOBAL_LOG_LEVEL = os.environ.get("GLOBAL_LOG_LEVEL", "").upper()
-if GLOBAL_LOG_LEVEL in log_levels:
+if GLOBAL_LOG_LEVEL in logging.getLevelNamesMapping():
     logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL, force=True)
 else:
     GLOBAL_LOG_LEVEL = "INFO"
@@ -78,6 +76,7 @@ log.info(f"GLOBAL_LOG_LEVEL: {GLOBAL_LOG_LEVEL}")
 
 if "cuda_error" in locals():
     log.exception(cuda_error)
+    del cuda_error
 
 log_sources = [
     "AUDIO",
@@ -100,7 +99,7 @@ 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 log_levels:
+    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]}")
 
@@ -386,6 +385,7 @@ ENABLE_WEBSOCKET_SUPPORT = (
 WEBSOCKET_MANAGER = os.environ.get("WEBSOCKET_MANAGER", "")
 
 WEBSOCKET_REDIS_URL = os.environ.get("WEBSOCKET_REDIS_URL", REDIS_URL)
+WEBSOCKET_REDIS_LOCK_TIMEOUT = os.environ.get("WEBSOCKET_REDIS_LOCK_TIMEOUT", 60)
 
 AIOHTTP_CLIENT_TIMEOUT = os.environ.get("AIOHTTP_CLIENT_TIMEOUT", "")
 
@@ -397,19 +397,20 @@ else:
     except Exception:
         AIOHTTP_CLIENT_TIMEOUT = 300
 
-AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = os.environ.get(
+AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST = os.environ.get(
-    "AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST", ""
+    "AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST",
+    os.environ.get("AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST", ""),
 )
 
-if AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST == "":
+
-    AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = None
+if AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST == "":
+    AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST = None
 else:
     try:
-        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = int(
+        AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST = int(AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST)
-            AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST
-        )
     except Exception:
-        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = 5
+        AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST = 5
+
 
 ####################################
 # OFFLINE_MODE
@@ -419,3 +420,25 @@ OFFLINE_MODE = os.environ.get("OFFLINE_MODE", "false").lower() == "true"
 
 if OFFLINE_MODE:
     os.environ["HF_HUB_OFFLINE"] = "1"
+
+####################################
+# AUDIT LOGGING
+####################################
+ENABLE_AUDIT_LOGS = os.getenv("ENABLE_AUDIT_LOGS", "false").lower() == "true"
+# Where to store log file
+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")
+# METADATA | REQUEST | REQUEST_RESPONSE
+AUDIT_LOG_LEVEL = os.getenv("AUDIT_LOG_LEVEL", "REQUEST_RESPONSE").upper()
+try:
+    MAX_BODY_LOG_SIZE = int(os.environ.get("MAX_BODY_LOG_SIZE") or 2048)
+except ValueError:
+    MAX_BODY_LOG_SIZE = 2048
+
+# Comma separated list for urls to exclude from audit
+AUDIT_EXCLUDED_PATHS = os.getenv("AUDIT_EXCLUDED_PATHS", "/chats,/chat,/folders").split(
+    ","
+)
+AUDIT_EXCLUDED_PATHS = [path.strip() for path in AUDIT_EXCLUDED_PATHS]
+AUDIT_EXCLUDED_PATHS = [path.lstrip("/") for path in AUDIT_EXCLUDED_PATHS]

backend/open_webui/functions.py

@@ -2,6 +2,7 @@ import logging
 import sys
 import inspect
 import json
+import asyncio
 
 from pydantic import BaseModel
 from typing import AsyncGenerator, Generator, Iterator
@@ -76,11 +77,13 @@ async def get_function_models(request):
         if hasattr(function_module, "pipes"):
             sub_pipes = []
 
-            # Check if pipes is a function or a list
+            # Handle pipes being a list, sync function, or async function
-
             try:
                 if callable(function_module.pipes):
-                    sub_pipes = function_module.pipes()
+                    if asyncio.iscoroutinefunction(function_module.pipes):
+                        sub_pipes = await function_module.pipes()
+                    else:
+                        sub_pipes = function_module.pipes()
                 else:
                     sub_pipes = function_module.pipes
             except Exception as e:

backend/open_webui/main.py

@@ -45,6 +45,9 @@ from starlette.middleware.sessions import SessionMiddleware
 from starlette.responses import Response, StreamingResponse
 
 
+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 (
     app as socket_app,
     periodic_usage_pool_cleanup,
@@ -95,12 +98,14 @@ from open_webui.config import (
     OLLAMA_API_CONFIGS,
     # OpenAI
     ENABLE_OPENAI_API,
+    ONEDRIVE_CLIENT_ID,
     OPENAI_API_BASE_URLS,
     OPENAI_API_KEYS,
     OPENAI_API_CONFIGS,
     # Direct Connections
     ENABLE_DIRECT_CONNECTIONS,
     # Code Execution
+    ENABLE_CODE_EXECUTION,
     CODE_EXECUTION_ENGINE,
     CODE_EXECUTION_JUPYTER_URL,
     CODE_EXECUTION_JUPYTER_AUTH,
@@ -161,6 +166,7 @@ from open_webui.config import (
     RAG_TEMPLATE,
     DEFAULT_RAG_TEMPLATE,
     RAG_FULL_CONTEXT,
+    BYPASS_EMBEDDING_AND_RETRIEVAL,
     RAG_EMBEDDING_MODEL,
     RAG_EMBEDDING_MODEL_AUTO_UPDATE,
     RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
@@ -180,6 +186,8 @@ from open_webui.config import (
     CHUNK_SIZE,
     CONTENT_EXTRACTION_ENGINE,
     TIKA_SERVER_URL,
+    DOCUMENT_INTELLIGENCE_ENDPOINT,
+    DOCUMENT_INTELLIGENCE_KEY,
     RAG_TOP_K,
     RAG_TEXT_SPLITTER,
     TIKTOKEN_ENCODING_NAME,
@@ -188,7 +196,7 @@ from open_webui.config import (
     YOUTUBE_LOADER_PROXY_URL,
     # Retrieval (Web Search)
     RAG_WEB_SEARCH_ENGINE,
-    RAG_WEB_SEARCH_FULL_CONTEXT,
+    BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
     RAG_WEB_SEARCH_RESULT_COUNT,
     RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
     RAG_WEB_SEARCH_TRUST_ENV,
@@ -208,6 +216,7 @@ from open_webui.config import (
     BING_SEARCH_V7_SUBSCRIPTION_KEY,
     BRAVE_SEARCH_API_KEY,
     EXA_API_KEY,
+    PERPLEXITY_API_KEY,
     KAGI_SEARCH_API_KEY,
     MOJEEK_SEARCH_API_KEY,
     BOCHA_SEARCH_API_KEY,
@@ -215,11 +224,13 @@ from open_webui.config import (
     GOOGLE_PSE_ENGINE_ID,
     GOOGLE_DRIVE_CLIENT_ID,
     GOOGLE_DRIVE_API_KEY,
+    ONEDRIVE_CLIENT_ID,
     ENABLE_RAG_HYBRID_SEARCH,
     ENABLE_RAG_LOCAL_WEB_FETCH,
     ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
     ENABLE_RAG_WEB_SEARCH,
     ENABLE_GOOGLE_DRIVE_INTEGRATION,
+    ENABLE_ONEDRIVE_INTEGRATION,
     UPLOAD_DIR,
     # WebUI
     WEBUI_AUTH,
@@ -298,8 +309,11 @@ from open_webui.config import (
     reset_config,
 )
 from open_webui.env import (
+    AUDIT_EXCLUDED_PATHS,
+    AUDIT_LOG_LEVEL,
     CHANGELOG,
     GLOBAL_LOG_LEVEL,
+    MAX_BODY_LOG_SIZE,
     SAFE_MODE,
     SRC_LOG_LEVELS,
     VERSION,
@@ -384,11 +398,12 @@ https://github.com/open-webui/open-webui
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
+    start_logger()
     if RESET_CONFIG_ON_START:
         reset_config()
 
-    if app.state.config.LICENSE_KEY:
+    if LICENSE_KEY:
-        get_license_data(app, app.state.config.LICENSE_KEY)
+        get_license_data(app, LICENSE_KEY)
 
     asyncio.create_task(periodic_usage_pool_cleanup())
     yield
@@ -406,7 +421,7 @@ oauth_manager = OAuthManager(app)
 app.state.config = AppConfig()
 
 app.state.WEBUI_NAME = WEBUI_NAME
-app.state.config.LICENSE_KEY = LICENSE_KEY
+app.state.LICENSE_METADATA = None
 
 ########################################
 #
@@ -526,6 +541,7 @@ app.state.config.FILE_MAX_COUNT = RAG_FILE_MAX_COUNT
 
 
 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_WEB_LOADER_SSL_VERIFICATION = (
     ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION
@@ -533,6 +549,8 @@ app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION = (
 
 app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
 app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
+app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT
+app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
 
 app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
 app.state.config.TIKTOKEN_ENCODING_NAME = TIKTOKEN_ENCODING_NAME
@@ -560,10 +578,13 @@ app.state.config.YOUTUBE_LOADER_PROXY_URL = YOUTUBE_LOADER_PROXY_URL
 
 app.state.config.ENABLE_RAG_WEB_SEARCH = ENABLE_RAG_WEB_SEARCH
 app.state.config.RAG_WEB_SEARCH_ENGINE = RAG_WEB_SEARCH_ENGINE
-app.state.config.RAG_WEB_SEARCH_FULL_CONTEXT = RAG_WEB_SEARCH_FULL_CONTEXT
+app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
+    BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
+)
 app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST = RAG_WEB_SEARCH_DOMAIN_FILTER_LIST
 
 app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = ENABLE_GOOGLE_DRIVE_INTEGRATION
+app.state.config.ENABLE_ONEDRIVE_INTEGRATION = ENABLE_ONEDRIVE_INTEGRATION
 app.state.config.SEARXNG_QUERY_URL = SEARXNG_QUERY_URL
 app.state.config.GOOGLE_PSE_API_KEY = GOOGLE_PSE_API_KEY
 app.state.config.GOOGLE_PSE_ENGINE_ID = GOOGLE_PSE_ENGINE_ID
@@ -584,6 +605,7 @@ app.state.config.JINA_API_KEY = JINA_API_KEY
 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.RAG_WEB_SEARCH_RESULT_COUNT = RAG_WEB_SEARCH_RESULT_COUNT
 app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = RAG_WEB_SEARCH_CONCURRENT_REQUESTS
@@ -639,6 +661,7 @@ app.state.EMBEDDING_FUNCTION = get_embedding_function(
 #
 ########################################
 
+app.state.config.ENABLE_CODE_EXECUTION = ENABLE_CODE_EXECUTION
 app.state.config.CODE_EXECUTION_ENGINE = CODE_EXECUTION_ENGINE
 app.state.config.CODE_EXECUTION_JUPYTER_URL = CODE_EXECUTION_JUPYTER_URL
 app.state.config.CODE_EXECUTION_JUPYTER_AUTH = CODE_EXECUTION_JUPYTER_AUTH
@@ -879,6 +902,19 @@ app.include_router(
 app.include_router(utils.router, prefix="/api/v1/utils", tags=["utils"])
 
 
+try:
+    audit_level = AuditLevel(AUDIT_LOG_LEVEL)
+except ValueError as e:
+    logger.error(f"Invalid audit level: {AUDIT_LOG_LEVEL}. Error: {e}")
+    audit_level = AuditLevel.NONE
+
+if audit_level != AuditLevel.NONE:
+    app.add_middleware(
+        AuditLoggingMiddleware,
+        audit_level=audit_level,
+        excluded_paths=AUDIT_EXCLUDED_PATHS,
+        max_body_size=MAX_BODY_LOG_SIZE,
+    )
 ##################################
 #
 # Chat Endpoints
@@ -911,7 +947,7 @@ async def get_models(request: Request, user=Depends(get_verified_user)):
 
         return filtered_models
 
-    models = await get_all_models(request)
+    models = await get_all_models(request, user=user)
 
     # Filter out filter pipelines
     models = [
@@ -940,7 +976,7 @@ async def get_models(request: Request, user=Depends(get_verified_user)):
 
 @app.get("/api/models/base")
 async def get_base_models(request: Request, user=Depends(get_admin_user)):
-    models = await get_all_base_models(request)
+    models = await get_all_base_models(request, user=user)
     return {"data": models}
 
 
@@ -951,7 +987,7 @@ async def chat_completion(
     user=Depends(get_verified_user),
 ):
     if not request.app.state.MODELS:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
 
     model_item = form_data.pop("model_item", {})
     tasks = form_data.pop("background_tasks", None)
@@ -987,7 +1023,7 @@ async def chat_completion(
             "files": form_data.get("files", None),
             "features": form_data.get("features", None),
             "variables": form_data.get("variables", None),
-            "model": model_info.model_dump() if model_info else model,
+            "model": model,
             "direct": model_item.get("direct", False),
             **(
                 {"function_calling": "native"}
@@ -1005,7 +1041,7 @@ async def chat_completion(
         form_data["metadata"] = metadata
 
         form_data, metadata, events = await process_chat_payload(
-            request, form_data, metadata, user, model
+            request, form_data, user, metadata, model
         )
 
     except Exception as e:
@@ -1019,7 +1055,7 @@ async def chat_completion(
         response = await chat_completion_handler(request, form_data, user)
 
         return await process_chat_response(
-            request, response, form_data, user, events, metadata, tasks
+            request, response, form_data, user, metadata, model, events, tasks
         )
     except Exception as e:
         raise HTTPException(
@@ -1108,9 +1144,10 @@ async def get_app_config(request: Request):
         if data is not None and "id" in data:
             user = Users.get_user_by_id(data["id"])
 
+    user_count = Users.get_num_users()
     onboarding = False
+
     if user is None:
-        user_count = Users.get_num_users()
         onboarding = user_count == 0
 
     return {
@@ -1138,6 +1175,7 @@ async def get_app_config(request: Request):
                     "enable_direct_connections": app.state.config.ENABLE_DIRECT_CONNECTIONS,
                     "enable_channels": app.state.config.ENABLE_CHANNELS,
                     "enable_web_search": app.state.config.ENABLE_RAG_WEB_SEARCH,
+                    "enable_code_execution": app.state.config.ENABLE_CODE_EXECUTION,
                     "enable_code_interpreter": app.state.config.ENABLE_CODE_INTERPRETER,
                     "enable_image_generation": app.state.config.ENABLE_IMAGE_GENERATION,
                     "enable_autocomplete_generation": app.state.config.ENABLE_AUTOCOMPLETE_GENERATION,
@@ -1146,6 +1184,7 @@ async def get_app_config(request: Request):
                     "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,
                 }
                 if user is not None
                 else {}
@@ -1155,6 +1194,7 @@ async def get_app_config(request: Request):
             {
                 "default_models": app.state.config.DEFAULT_MODELS,
                 "default_prompt_suggestions": app.state.config.DEFAULT_PROMPT_SUGGESTIONS,
+                "user_count": user_count,
                 "code": {
                     "engine": app.state.config.CODE_EXECUTION_ENGINE,
                 },
@@ -1177,6 +1217,15 @@ async def get_app_config(request: Request):
                     "client_id": GOOGLE_DRIVE_CLIENT_ID.value,
                     "api_key": GOOGLE_DRIVE_API_KEY.value,
                 },
+                "onedrive": {"client_id": ONEDRIVE_CLIENT_ID.value},
+                "license_metadata": app.state.LICENSE_METADATA,
+                **(
+                    {
+                        "active_entries": app.state.USER_COUNT,
+                    }
+                    if user.role == "admin"
+                    else {}
+                ),
             }
             if user is not None
             else {}

backend/open_webui/models/chats.py

@@ -1,3 +1,4 @@
+import logging
 import json
 import time
 import uuid
@@ -5,7 +6,7 @@ from typing import Optional
 
 from open_webui.internal.db import Base, get_db
 from open_webui.models.tags import TagModel, Tag, Tags
-
+from open_webui.env import SRC_LOG_LEVELS
 
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
@@ -16,6 +17,9 @@ from sqlalchemy.sql import exists
 # Chat DB Schema
 ####################
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 
 class Chat(Base):
     __tablename__ = "chat"
@@ -670,7 +674,7 @@ class ChatTable:
             # Perform pagination at the SQL level
             all_chats = query.offset(skip).limit(limit).all()
 
-            print(len(all_chats))
+            log.info(f"The number of chats: {len(all_chats)}")
 
             # Validate and return chats
             return [ChatModel.model_validate(chat) for chat in all_chats]
@@ -731,7 +735,7 @@ class ChatTable:
             query = db.query(Chat).filter_by(user_id=user_id)
             tag_id = tag_name.replace(" ", "_").lower()
 
-            print(db.bind.dialect.name)
+            log.info(f"DB dialect name: {db.bind.dialect.name}")
             if db.bind.dialect.name == "sqlite":
                 # SQLite JSON1 querying for tags within the meta JSON field
                 query = query.filter(
@@ -752,7 +756,7 @@ class ChatTable:
                 )
 
             all_chats = query.all()
-            print("all_chats", all_chats)
+            log.debug(f"all_chats: {all_chats}")
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
     def add_chat_tag_by_id_and_user_id_and_tag_name(
@@ -810,7 +814,7 @@ class ChatTable:
             count = query.count()
 
             # Debugging output for inspection
-            print(f"Count of chats for tag '{tag_name}':", count)
+            log.info(f"Count of chats for tag '{tag_name}': {count}")
 
             return count
 

backend/open_webui/models/feedbacks.py

@@ -118,7 +118,7 @@ class FeedbackTable:
                 else:
                     return None
             except Exception as e:
-                print(e)
+                log.exception(f"Error creating a new feedback: {e}")
                 return None
 
     def get_feedback_by_id(self, id: str) -> Optional[FeedbackModel]:

backend/open_webui/models/files.py

@@ -119,7 +119,7 @@ class FilesTable:
                 else:
                     return None
             except Exception as e:
-                print(f"Error creating tool: {e}")
+                log.exception(f"Error inserting a new file: {e}")
                 return None
 
     def get_file_by_id(self, id: str) -> Optional[FileModel]:

backend/open_webui/models/folders.py

@@ -82,7 +82,7 @@ class FolderTable:
                 else:
                     return None
             except Exception as e:
-                print(e)
+                log.exception(f"Error inserting a new folder: {e}")
                 return None
 
     def get_folder_by_id_and_user_id(

backend/open_webui/models/functions.py

@@ -105,7 +105,7 @@ class FunctionsTable:
                 else:
                     return None
         except Exception as e:
-            print(f"Error creating tool: {e}")
+            log.exception(f"Error creating a new function: {e}")
             return None
 
     def get_function_by_id(self, id: str) -> Optional[FunctionModel]:
@@ -170,7 +170,7 @@ class FunctionsTable:
                 function = db.get(Function, id)
                 return function.valves if function.valves else {}
             except Exception as e:
-                print(f"An error occurred: {e}")
+                log.exception(f"Error getting function valves by id {id}: {e}")
                 return None
 
     def update_function_valves_by_id(
@@ -202,7 +202,9 @@ class FunctionsTable:
 
             return user_settings["functions"]["valves"].get(id, {})
         except Exception as e:
-            print(f"An error occurred: {e}")
+            log.exception(
+                f"Error getting user values by id {id} and user id {user_id}: {e}"
+            )
             return None
 
     def update_user_valves_by_id_and_user_id(
@@ -225,7 +227,9 @@ class FunctionsTable:
 
             return user_settings["functions"]["valves"][id]
         except Exception as e:
-            print(f"An error occurred: {e}")
+            log.exception(
+                f"Error updating user valves by id {id} and user_id {user_id}: {e}"
+            )
             return None
 
     def update_function_by_id(self, id: str, updated: dict) -> Optional[FunctionModel]:

backend/open_webui/models/models.py

@@ -166,7 +166,7 @@ class ModelsTable:
                 else:
                     return None
         except Exception as e:
-            print(e)
+            log.exception(f"Failed to insert a new model: {e}")
             return None
 
     def get_all_models(self) -> list[ModelModel]:
@@ -246,8 +246,7 @@ class ModelsTable:
                 db.refresh(model)
                 return ModelModel.model_validate(model)
         except Exception as e:
-            print(e)
+            log.exception(f"Failed to update the model by id {id}: {e}")
-
             return None
 
     def delete_model_by_id(self, id: str) -> bool:

backend/open_webui/models/tags.py

@@ -61,7 +61,7 @@ class TagTable:
                 else:
                     return None
             except Exception as e:
-                print(e)
+                log.exception(f"Error inserting a new tag: {e}")
                 return None
 
     def get_tag_by_name_and_user_id(

backend/open_webui/models/tools.py

@@ -131,7 +131,7 @@ class ToolsTable:
                 else:
                     return None
             except Exception as e:
-                print(f"Error creating tool: {e}")
+                log.exception(f"Error creating a new tool: {e}")
                 return None
 
     def get_tool_by_id(self, id: str) -> Optional[ToolModel]:
@@ -175,7 +175,7 @@ class ToolsTable:
                 tool = db.get(Tool, id)
                 return tool.valves if tool.valves else {}
         except Exception as e:
-            print(f"An error occurred: {e}")
+            log.exception(f"Error getting tool valves by id {id}: {e}")
             return None
 
     def update_tool_valves_by_id(self, id: str, valves: dict) -> Optional[ToolValves]:
@@ -204,7 +204,9 @@ class ToolsTable:
 
             return user_settings["tools"]["valves"].get(id, {})
         except Exception as e:
-            print(f"An error occurred: {e}")
+            log.exception(
+                f"Error getting user values by id {id} and user_id {user_id}: {e}"
+            )
             return None
 
     def update_user_valves_by_id_and_user_id(
@@ -227,7 +229,9 @@ class ToolsTable:
 
             return user_settings["tools"]["valves"][id]
         except Exception as e:
-            print(f"An error occurred: {e}")
+            log.exception(
+                f"Error updating user valves by id {id} and user_id {user_id}: {e}"
+            )
             return None
 
     def update_tool_by_id(self, id: str, updated: dict) -> Optional[ToolModel]:

backend/open_webui/retrieval/loaders/main.py

@@ -4,6 +4,7 @@ import ftfy
 import sys
 
 from langchain_community.document_loaders import (
+    AzureAIDocumentIntelligenceLoader,
     BSHTMLLoader,
     CSVLoader,
     Docx2txtLoader,
@@ -76,6 +77,7 @@ known_source_ext = [
     "jsx",
     "hs",
     "lhs",
+    "json",
 ]
 
 
@@ -147,6 +149,27 @@ class Loader:
                     file_path=file_path,
                     mime_type=file_content_type,
                 )
+        elif (
+            self.engine == "document_intelligence"
+            and self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT") != ""
+            and self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY") != ""
+            and (
+                file_ext in ["pdf", "xls", "xlsx", "docx", "ppt", "pptx"]
+                or file_content_type
+                in [
+                    "application/vnd.ms-excel",
+                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+                    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+                    "application/vnd.ms-powerpoint",
+                    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+                ]
+            )
+        ):
+            loader = AzureAIDocumentIntelligenceLoader(
+                file_path=file_path,
+                api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
+                api_key=self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY"),
+            )
         else:
             if file_ext == "pdf":
                 loader = PyPDFLoader(

backend/open_webui/retrieval/models/colbert.py

@@ -1,13 +1,19 @@
 import os
+import logging
 import torch
 import numpy as np
 from colbert.infra import ColBERTConfig
 from colbert.modeling.checkpoint import Checkpoint
 
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
 
 class ColBERT:
     def __init__(self, name, **kwargs) -> None:
-        print("ColBERT: Loading model", name)
+        log.info("ColBERT: Loading model", name)
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
 
         DOCKER = kwargs.get("env") == "docker"

backend/open_webui/retrieval/utils.py

@@ -5,6 +5,7 @@ from typing import Optional, Union
 
 import asyncio
 import requests
+import hashlib
 
 from huggingface_hub import snapshot_download
 from langchain.retrievers import ContextualCompressionRetriever, EnsembleRetriever
@@ -17,6 +18,7 @@ from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
 from open_webui.utils.misc import get_last_user_message, calculate_sha256_string
 
 from open_webui.models.users import UserModel
+from open_webui.models.files import Files
 
 from open_webui.env import (
     SRC_LOG_LEVELS,
@@ -81,7 +83,7 @@ def query_doc(
 
         return result
     except Exception as e:
-        print(e)
+        log.exception(f"Error querying doc {collection_name} with limit {k}: {e}")
         raise e
 
 
@@ -94,7 +96,7 @@ def get_doc(collection_name: str, user: UserModel = None):
 
         return result
     except Exception as e:
-        print(e)
+        log.exception(f"Error getting doc {collection_name}: {e}")
         raise e
 
 
@@ -174,46 +176,41 @@ def merge_get_results(get_results: list[dict]) -> dict:
 
 def merge_and_sort_query_results(
     query_results: list[dict], k: int, reverse: bool = False
-) -> list[dict]:
+) -> dict:
     # Initialize lists to store combined data
-    combined_distances = []
+    combined = []
-    combined_documents = []
+    seen_hashes = set()  # To store unique document hashes
-    combined_metadatas = []
 
     for data in query_results:
-        combined_distances.extend(data["distances"][0])
+        distances = data["distances"][0]
-        combined_documents.extend(data["documents"][0])
+        documents = data["documents"][0]
-        combined_metadatas.extend(data["metadatas"][0])
+        metadatas = data["metadatas"][0]
 
-    # Create a list of tuples (distance, document, metadata)
+        for distance, document, metadata in zip(distances, documents, metadatas):
-    combined = list(zip(combined_distances, combined_documents, combined_metadatas))
+            if isinstance(document, str):
+                doc_hash = hashlib.md5(
+                    document.encode()
+                ).hexdigest()  # Compute a hash for uniqueness
+
+                if doc_hash not in seen_hashes:
+                    seen_hashes.add(doc_hash)
+                    combined.append((distance, document, metadata))
 
     # Sort the list based on distances
     combined.sort(key=lambda x: x[0], reverse=reverse)
 
-    # We don't have anything :-(
+    # Slice to keep only the top k elements
-    if not combined:
+    sorted_distances, sorted_documents, sorted_metadatas = (
-        sorted_distances = []
+        zip(*combined[:k]) if combined else ([], [], [])
-        sorted_documents = []
+    )
-        sorted_metadatas = []
-    else:
-        # Unzip the sorted list
-        sorted_distances, sorted_documents, sorted_metadatas = zip(*combined)
 
-        # Slicing the lists to include only k elements
+    # Create and return the output dictionary
-        sorted_distances = list(sorted_distances)[:k]
+    return {
-        sorted_documents = list(sorted_documents)[:k]
+        "distances": [list(sorted_distances)],
-        sorted_metadatas = list(sorted_metadatas)[:k]
+        "documents": [list(sorted_documents)],
-
+        "metadatas": [list(sorted_metadatas)],
-    # Create the output dictionary
-    result = {
-        "distances": [sorted_distances],
-        "documents": [sorted_documents],
-        "metadatas": [sorted_metadatas],
     }
 
-    return result
-
 
 def get_all_items_from_collections(collection_names: list[str]) -> dict:
     results = []
@@ -342,6 +339,7 @@ def get_embedding_function(
 
 
 def get_sources_from_files(
+    request,
     files,
     queries,
     embedding_function,
@@ -359,19 +357,71 @@ def get_sources_from_files(
     relevant_contexts = []
 
     for file in files:
+
+        context = None
         if file.get("docs"):
+            # BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
             context = {
                 "documents": [[doc.get("content") for doc in file.get("docs")]],
                 "metadatas": [[doc.get("metadata") for doc in file.get("docs")]],
             }
         elif file.get("context") == "full":
+            # Manual Full Mode Toggle
             context = {
                 "documents": [[file.get("file").get("data", {}).get("content")]],
                 "metadatas": [[{"file_id": file.get("id"), "name": file.get("name")}]],
             }
-        else:
+        elif (
-            context = None
+            file.get("type") != "web_search"
+            and request.app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL
+        ):
+            # BYPASS_EMBEDDING_AND_RETRIEVAL
+            if file.get("type") == "collection":
+                file_ids = file.get("data", {}).get("file_ids", [])
 
+                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,
+                            }
+                        )
+
+                context = {
+                    "documents": [documents],
+                    "metadatas": [metadatas],
+                }
+
+            elif file.get("id"):
+                file_object = Files.get_file_by_id(file.get("id"))
+                if file_object:
+                    context = {
+                        "documents": [[file_object.data.get("content", "")]],
+                        "metadatas": [
+                            [
+                                {
+                                    "file_id": file.get("id"),
+                                    "name": file_object.filename,
+                                    "source": file_object.filename,
+                                }
+                            ]
+                        ],
+                    }
+            elif file.get("file").get("data"):
+                context = {
+                    "documents": [[file.get("file").get("data", {}).get("content")]],
+                    "metadatas": [
+                        [file.get("file").get("data", {}).get("metadata", {})]
+                    ],
+                }
+        else:
             collection_names = []
             if file.get("type") == "collection":
                 if file.get("legacy"):
@@ -434,6 +484,7 @@ def get_sources_from_files(
         if context:
             if "data" in file:
                 del file["data"]
+
             relevant_contexts.append({**context, "file": file})
 
     sources = []
@@ -530,7 +581,7 @@ def generate_openai_batch_embeddings(
         else:
             raise "Something went wrong :/"
     except Exception as e:
-        print(e)
+        log.exception(f"Error generating openai batch embeddings: {e}")
         return None
 
 
@@ -564,7 +615,7 @@ def generate_ollama_batch_embeddings(
         else:
             raise "Something went wrong :/"
     except Exception as e:
-        print(e)
+        log.exception(f"Error generating ollama batch embeddings: {e}")
         return None
 
 

backend/open_webui/retrieval/vector/connector.py

@@ -16,6 +16,10 @@ elif VECTOR_DB == "pgvector":
     from open_webui.retrieval.vector.dbs.pgvector import PgvectorClient
 
     VECTOR_DB_CLIENT = PgvectorClient()
+elif VECTOR_DB == "elasticsearch":
+    from open_webui.retrieval.vector.dbs.elasticsearch import ElasticsearchClient
+
+    VECTOR_DB_CLIENT = ElasticsearchClient()
 else:
     from open_webui.retrieval.vector.dbs.chroma import ChromaClient
 

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

@@ -1,4 +1,5 @@
 import chromadb
+import logging
 from chromadb import Settings
 from chromadb.utils.batch_utils import create_batches
 
@@ -16,6 +17,10 @@ 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:
@@ -102,8 +107,7 @@ class ChromaClient:
                     }
                 )
             return None
-        except Exception as e:
+        except:
-            print(e)
             return None
 
     def get(self, collection_name: str) -> Optional[GetResult]:

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

@@ -0,0 +1,295 @@
+from elasticsearch import Elasticsearch, BadRequestError
+from typing import Optional
+import ssl
+from elasticsearch.helpers import bulk, scan
+from open_webui.retrieval.vector.main import VectorItem, SearchResult, GetResult
+from open_webui.config import (
+    ELASTICSEARCH_URL,
+    ELASTICSEARCH_CA_CERTS,
+    ELASTICSEARCH_API_KEY,
+    ELASTICSEARCH_USERNAME,
+    ELASTICSEARCH_PASSWORD,
+    ELASTICSEARCH_CLOUD_ID,
+    ELASTICSEARCH_INDEX_PREFIX,
+    SSL_ASSERT_FINGERPRINT,
+)
+
+
+class ElasticsearchClient:
+    """
+    Important:
+    in order to reduce the number of indexes and since the embedding vector length is fixed, we avoid creating
+    an index for each file but store it as a text field, while seperating to different index
+    baesd on the embedding length.
+    """
+
+    def __init__(self):
+        self.index_prefix = ELASTICSEARCH_INDEX_PREFIX
+        self.client = Elasticsearch(
+            hosts=[ELASTICSEARCH_URL],
+            ca_certs=ELASTICSEARCH_CA_CERTS,
+            api_key=ELASTICSEARCH_API_KEY,
+            cloud_id=ELASTICSEARCH_CLOUD_ID,
+            basic_auth=(
+                (ELASTICSEARCH_USERNAME, ELASTICSEARCH_PASSWORD)
+                if ELASTICSEARCH_USERNAME and ELASTICSEARCH_PASSWORD
+                else None
+            ),
+            ssl_assert_fingerprint=SSL_ASSERT_FINGERPRINT,
+        )
+
+    # Status: works
+    def _get_index_name(self, dimension: int) -> str:
+        return f"{self.index_prefix}_d{str(dimension)}"
+
+    # Status: works
+    def _scan_result_to_get_result(self, result) -> GetResult:
+        if not result:
+            return None
+        ids = []
+        documents = []
+        metadatas = []
+
+        for hit in result:
+            ids.append(hit["_id"])
+            documents.append(hit["_source"].get("text"))
+            metadatas.append(hit["_source"].get("metadata"))
+
+        return GetResult(ids=[ids], documents=[documents], metadatas=[metadatas])
+
+    # Status: works
+    def _result_to_get_result(self, result) -> GetResult:
+        if not result["hits"]["hits"]:
+            return None
+        ids = []
+        documents = []
+        metadatas = []
+
+        for hit in result["hits"]["hits"]:
+            ids.append(hit["_id"])
+            documents.append(hit["_source"].get("text"))
+            metadatas.append(hit["_source"].get("metadata"))
+
+        return GetResult(ids=[ids], documents=[documents], metadatas=[metadatas])
+
+    # Status: works
+    def _result_to_search_result(self, result) -> SearchResult:
+        ids = []
+        distances = []
+        documents = []
+        metadatas = []
+
+        for hit in result["hits"]["hits"]:
+            ids.append(hit["_id"])
+            distances.append(hit["_score"])
+            documents.append(hit["_source"].get("text"))
+            metadatas.append(hit["_source"].get("metadata"))
+
+        return SearchResult(
+            ids=[ids],
+            distances=[distances],
+            documents=[documents],
+            metadatas=[metadatas],
+        )
+
+    # Status: works
+    def _create_index(self, dimension: int):
+        body = {
+            "mappings": {
+                "dynamic_templates": [
+                    {
+                        "strings": {
+                            "match_mapping_type": "string",
+                            "mapping": {"type": "keyword"},
+                        }
+                    }
+                ],
+                "properties": {
+                    "collection": {"type": "keyword"},
+                    "id": {"type": "keyword"},
+                    "vector": {
+                        "type": "dense_vector",
+                        "dims": dimension,  # Adjust based on your vector dimensions
+                        "index": True,
+                        "similarity": "cosine",
+                    },
+                    "text": {"type": "text"},
+                    "metadata": {"type": "object"},
+                },
+            }
+        }
+        self.client.indices.create(index=self._get_index_name(dimension), body=body)
+
+    # Status: works
+
+    def _create_batches(self, items: list[VectorItem], batch_size=100):
+        for i in range(0, len(items), batch_size):
+            yield items[i : min(i + batch_size, len(items))]
+
+    # Status: works
+    def has_collection(self, collection_name) -> bool:
+        query_body = {"query": {"bool": {"filter": []}}}
+        query_body["query"]["bool"]["filter"].append(
+            {"term": {"collection": collection_name}}
+        )
+
+        try:
+            result = self.client.count(index=f"{self.index_prefix}*", body=query_body)
+
+            return result.body["count"] > 0
+        except Exception as e:
+            return None
+
+    def delete_collection(self, collection_name: str):
+        query = {"query": {"term": {"collection": collection_name}}}
+        self.client.delete_by_query(index=f"{self.index_prefix}*", body=query)
+
+    # Status: works
+    def search(
+        self, collection_name: str, vectors: list[list[float]], limit: int
+    ) -> Optional[SearchResult]:
+        query = {
+            "size": limit,
+            "_source": ["text", "metadata"],
+            "query": {
+                "script_score": {
+                    "query": {
+                        "bool": {"filter": [{"term": {"collection": collection_name}}]}
+                    },
+                    "script": {
+                        "source": "cosineSimilarity(params.vector, 'vector') + 1.0",
+                        "params": {
+                            "vector": vectors[0]
+                        },  # Assuming single query vector
+                    },
+                }
+            },
+        }
+
+        result = self.client.search(
+            index=self._get_index_name(len(vectors[0])), body=query
+        )
+
+        return self._result_to_search_result(result)
+
+    # Status: only tested halfwat
+    def query(
+        self, collection_name: str, filter: dict, limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        if not self.has_collection(collection_name):
+            return None
+
+        query_body = {
+            "query": {"bool": {"filter": []}},
+            "_source": ["text", "metadata"],
+        }
+
+        for field, value in filter.items():
+            query_body["query"]["bool"]["filter"].append({"term": {field: value}})
+        query_body["query"]["bool"]["filter"].append(
+            {"term": {"collection": collection_name}}
+        )
+        size = limit if limit else 10
+
+        try:
+            result = self.client.search(
+                index=f"{self.index_prefix}*",
+                body=query_body,
+                size=size,
+            )
+
+            return self._result_to_get_result(result)
+
+        except Exception as e:
+            return None
+
+    # Status: works
+    def _has_index(self, dimension: int):
+        return self.client.indices.exists(
+            index=self._get_index_name(dimension=dimension)
+        )
+
+    def get_or_create_index(self, dimension: int):
+        if not self._has_index(dimension=dimension):
+            self._create_index(dimension=dimension)
+
+    # Status: works
+    def get(self, collection_name: str) -> Optional[GetResult]:
+        # Get all the items in the collection.
+        query = {
+            "query": {"bool": {"filter": [{"term": {"collection": collection_name}}]}},
+            "_source": ["text", "metadata"],
+        }
+        results = list(scan(self.client, index=f"{self.index_prefix}*", query=query))
+
+        return self._scan_result_to_get_result(results)
+
+    # Status: works
+    def insert(self, collection_name: str, items: list[VectorItem]):
+        if not self._has_index(dimension=len(items[0]["vector"])):
+            self._create_index(dimension=len(items[0]["vector"]))
+
+        for batch in self._create_batches(items):
+            actions = [
+                {
+                    "_index": self._get_index_name(dimension=len(items[0]["vector"])),
+                    "_id": item["id"],
+                    "_source": {
+                        "collection": collection_name,
+                        "vector": item["vector"],
+                        "text": item["text"],
+                        "metadata": item["metadata"],
+                    },
+                }
+                for item in batch
+            ]
+            bulk(self.client, actions)
+
+    # Upsert documents using the update API with doc_as_upsert=True.
+    def upsert(self, collection_name: str, items: list[VectorItem]):
+        if not self._has_index(dimension=len(items[0]["vector"])):
+            self._create_index(dimension=len(items[0]["vector"]))
+        for batch in self._create_batches(items):
+            actions = [
+                {
+                    "_op_type": "update",
+                    "_index": self._get_index_name(dimension=len(item["vector"])),
+                    "_id": item["id"],
+                    "doc": {
+                        "collection": collection_name,
+                        "vector": item["vector"],
+                        "text": item["text"],
+                        "metadata": item["metadata"],
+                    },
+                    "doc_as_upsert": True,
+                }
+                for item in batch
+            ]
+            bulk(self.client, actions)
+
+    # Delete specific documents from a collection by filtering on both collection and document IDs.
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[list[str]] = None,
+        filter: Optional[dict] = None,
+    ):
+
+        query = {
+            "query": {"bool": {"filter": [{"term": {"collection": collection_name}}]}}
+        }
+        # logic based on chromaDB
+        if ids:
+            query["query"]["bool"]["filter"].append({"terms": {"_id": ids}})
+        elif filter:
+            for field, value in filter.items():
+                query["query"]["bool"]["filter"].append(
+                    {"term": {f"metadata.{field}": value}}
+                )
+
+        self.client.delete_by_query(index=f"{self.index_prefix}*", body=query)
+
+    def reset(self):
+        indices = self.client.indices.get(index=f"{self.index_prefix}*")
+        for index in indices:
+            self.client.indices.delete(index=index)

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

@@ -1,7 +1,7 @@
 from pymilvus import MilvusClient as Client
 from pymilvus import FieldSchema, DataType
 import json
-
+import logging
 from typing import Optional
 
 from open_webui.retrieval.vector.main import VectorItem, SearchResult, GetResult
@@ -10,15 +10,19 @@ from open_webui.config import (
     MILVUS_DB,
     MILVUS_TOKEN,
 )
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 class MilvusClient:
     def __init__(self):
         self.collection_prefix = "open_webui"
         if MILVUS_TOKEN is None:
-            self.client = Client(uri=MILVUS_URI, database=MILVUS_DB)
+            self.client = Client(uri=MILVUS_URI, db_name=MILVUS_DB)
         else:
-            self.client = Client(uri=MILVUS_URI, database=MILVUS_DB, token=MILVUS_TOKEN)
+            self.client = Client(uri=MILVUS_URI, db_name=MILVUS_DB, token=MILVUS_TOKEN)
 
     def _result_to_get_result(self, result) -> GetResult:
         ids = []
@@ -168,7 +172,7 @@ class MilvusClient:
         try:
             # Loop until there are no more items to fetch or the desired limit is reached
             while remaining > 0:
-                print("remaining", remaining)
+                log.info(f"remaining: {remaining}")
                 current_fetch = min(
                     max_limit, remaining
                 )  # Determine how many items to fetch in this iteration
@@ -195,10 +199,12 @@ class MilvusClient:
                 if results_count < current_fetch:
                     break
 
-            print(all_results)
+            log.debug(all_results)
             return self._result_to_get_result([all_results])
         except Exception as e:
-            print(e)
+            log.exception(
+                f"Error querying collection {collection_name} with limit {limit}: {e}"
+            )
             return None
 
     def get(self, collection_name: str) -> Optional[GetResult]:

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

@@ -49,7 +49,7 @@ class OpenSearchClient:
             ids=ids, distances=distances, documents=documents, metadatas=metadatas
         )
 
-    def _create_index(self, index_name: str, dimension: int):
+    def _create_index(self, collection_name: str, dimension: int):
         body = {
             "mappings": {
                 "properties": {
@@ -72,24 +72,28 @@ class OpenSearchClient:
                 }
             }
         }
-        self.client.indices.create(index=f"{self.index_prefix}_{index_name}", body=body)
+        self.client.indices.create(
+            index=f"{self.index_prefix}_{collection_name}", body=body
+        )
 
     def _create_batches(self, items: list[VectorItem], batch_size=100):
         for i in range(0, len(items), batch_size):
             yield items[i : i + batch_size]
 
-    def has_collection(self, index_name: str) -> bool:
+    def has_collection(self, collection_name: str) -> bool:
         # has_collection here means has index.
         # We are simply adapting to the norms of the other DBs.
-        return self.client.indices.exists(index=f"{self.index_prefix}_{index_name}")
+        return self.client.indices.exists(
+            index=f"{self.index_prefix}_{collection_name}"
+        )
 
-    def delete_colleciton(self, index_name: str):
+    def delete_colleciton(self, collection_name: str):
         # delete_collection here means delete index.
         # We are simply adapting to the norms of the other DBs.
-        self.client.indices.delete(index=f"{self.index_prefix}_{index_name}")
+        self.client.indices.delete(index=f"{self.index_prefix}_{collection_name}")
 
     def search(
-        self, index_name: str, vectors: list[list[float]], limit: int
+        self, collection_name: str, vectors: list[list[float]], limit: int
     ) -> Optional[SearchResult]:
         query = {
             "size": limit,
@@ -108,7 +112,7 @@ class OpenSearchClient:
         }
 
         result = self.client.search(
-            index=f"{self.index_prefix}_{index_name}", body=query
+            index=f"{self.index_prefix}_{collection_name}", body=query
         )
 
         return self._result_to_search_result(result)
@@ -141,21 +145,22 @@ class OpenSearchClient:
         except Exception as e:
             return None
 
-    def get_or_create_index(self, index_name: str, dimension: int):
+    def _create_index_if_not_exists(self, collection_name: str, dimension: int):
-        if not self.has_index(index_name):
+        if not self.has_index(collection_name):
-            self._create_index(index_name, dimension)
+            self._create_index(collection_name, dimension)
 
-    def get(self, index_name: str) -> Optional[GetResult]:
+    def get(self, collection_name: str) -> Optional[GetResult]:
         query = {"query": {"match_all": {}}, "_source": ["text", "metadata"]}
 
         result = self.client.search(
-            index=f"{self.index_prefix}_{index_name}", body=query
+            index=f"{self.index_prefix}_{collection_name}", body=query
         )
         return self._result_to_get_result(result)
 
-    def insert(self, index_name: str, items: list[VectorItem]):
+    def insert(self, collection_name: str, items: list[VectorItem]):
-        if not self.has_index(index_name):
+        self._create_index_if_not_exists(
-            self._create_index(index_name, dimension=len(items[0]["vector"]))
+            collection_name=collection_name, dimension=len(items[0]["vector"])
+        )
 
         for batch in self._create_batches(items):
             actions = [
@@ -173,15 +178,17 @@ class OpenSearchClient:
             ]
             self.client.bulk(actions)
 
-    def upsert(self, index_name: str, items: list[VectorItem]):
+    def upsert(self, collection_name: str, items: list[VectorItem]):
-        if not self.has_index(index_name):
+        self._create_index_if_not_exists(
-            self._create_index(index_name, dimension=len(items[0]["vector"]))
+            collection_name=collection_name, dimension=len(items[0]["vector"])
+        )
 
         for batch in self._create_batches(items):
             actions = [
                 {
                     "index": {
                         "_id": item["id"],
+                        "_index": f"{self.index_prefix}_{collection_name}",
                         "_source": {
                             "vector": item["vector"],
                             "text": item["text"],
@@ -193,9 +200,9 @@ class OpenSearchClient:
             ]
             self.client.bulk(actions)
 
-    def delete(self, index_name: str, ids: list[str]):
+    def delete(self, collection_name: str, ids: list[str]):
         actions = [
-            {"delete": {"_index": f"{self.index_prefix}_{index_name}", "_id": id}}
+            {"delete": {"_index": f"{self.index_prefix}_{collection_name}", "_id": id}}
             for id in ids
         ]
         self.client.bulk(body=actions)

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

@@ -1,4 +1,5 @@
 from typing import Optional, List, Dict, Any
+import logging
 from sqlalchemy import (
     cast,
     column,
@@ -24,9 +25,14 @@ from sqlalchemy.exc import NoSuchTableError
 from open_webui.retrieval.vector.main import VectorItem, SearchResult, GetResult
 from open_webui.config import PGVECTOR_DB_URL, PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH
 
+from open_webui.env import SRC_LOG_LEVELS
+
 VECTOR_LENGTH = PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH
 Base = declarative_base()
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
 
 class DocumentChunk(Base):
     __tablename__ = "document_chunk"
@@ -82,10 +88,10 @@ class PgvectorClient:
                 )
             )
             self.session.commit()
-            print("Initialization complete.")
+            log.info("Initialization complete.")
         except Exception as e:
             self.session.rollback()
-            print(f"Error during initialization: {e}")
+            log.exception(f"Error during initialization: {e}")
             raise
 
     def check_vector_length(self) -> None:
@@ -150,12 +156,12 @@ class PgvectorClient:
                 new_items.append(new_chunk)
             self.session.bulk_save_objects(new_items)
             self.session.commit()
-            print(
+            log.info(
                 f"Inserted {len(new_items)} items into collection '{collection_name}'."
             )
         except Exception as e:
             self.session.rollback()
-            print(f"Error during insert: {e}")
+            log.exception(f"Error during insert: {e}")
             raise
 
     def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
@@ -184,10 +190,12 @@ class PgvectorClient:
                     )
                     self.session.add(new_chunk)
             self.session.commit()
-            print(f"Upserted {len(items)} items into collection '{collection_name}'.")
+            log.info(
+                f"Upserted {len(items)} items into collection '{collection_name}'."
+            )
         except Exception as e:
             self.session.rollback()
-            print(f"Error during upsert: {e}")
+            log.exception(f"Error during upsert: {e}")
             raise
 
     def search(
@@ -278,7 +286,7 @@ class PgvectorClient:
                 ids=ids, distances=distances, documents=documents, metadatas=metadatas
             )
         except Exception as e:
-            print(f"Error during search: {e}")
+            log.exception(f"Error during search: {e}")
             return None
 
     def query(
@@ -310,7 +318,7 @@ class PgvectorClient:
                 metadatas=metadatas,
             )
         except Exception as e:
-            print(f"Error during query: {e}")
+            log.exception(f"Error during query: {e}")
             return None
 
     def get(
@@ -334,7 +342,7 @@ class PgvectorClient:
 
             return GetResult(ids=ids, documents=documents, metadatas=metadatas)
         except Exception as e:
-            print(f"Error during get: {e}")
+            log.exception(f"Error during get: {e}")
             return None
 
     def delete(
@@ -356,22 +364,22 @@ class PgvectorClient:
                     )
             deleted = query.delete(synchronize_session=False)
             self.session.commit()
-            print(f"Deleted {deleted} items from collection '{collection_name}'.")
+            log.info(f"Deleted {deleted} items from collection '{collection_name}'.")
         except Exception as e:
             self.session.rollback()
-            print(f"Error during delete: {e}")
+            log.exception(f"Error during delete: {e}")
             raise
 
     def reset(self) -> None:
         try:
             deleted = self.session.query(DocumentChunk).delete()
             self.session.commit()
-            print(
+            log.info(
                 f"Reset complete. Deleted {deleted} items from 'document_chunk' table."
             )
         except Exception as e:
             self.session.rollback()
-            print(f"Error during reset: {e}")
+            log.exception(f"Error during reset: {e}")
             raise
 
     def close(self) -> None:
@@ -387,9 +395,9 @@ class PgvectorClient:
             )
             return exists
         except Exception as e:
-            print(f"Error checking collection existence: {e}")
+            log.exception(f"Error checking collection existence: {e}")
             return False
 
     def delete_collection(self, collection_name: str) -> None:
         self.delete(collection_name)
-        print(f"Collection '{collection_name}' deleted.")
+        log.info(f"Collection '{collection_name}' deleted.")

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

@@ -1,4 +1,5 @@
 from typing import Optional
+import logging
 
 from qdrant_client import QdrantClient as Qclient
 from qdrant_client.http.models import PointStruct
@@ -6,9 +7,13 @@ from qdrant_client.models import models
 
 from open_webui.retrieval.vector.main import VectorItem, SearchResult, GetResult
 from open_webui.config import QDRANT_URI, QDRANT_API_KEY
+from open_webui.env import SRC_LOG_LEVELS
 
 NO_LIMIT = 999999999
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
 
 class QdrantClient:
     def __init__(self):
@@ -49,7 +54,7 @@ class QdrantClient:
             ),
         )
 
-        print(f"collection {collection_name_with_prefix} successfully created!")
+        log.info(f"collection {collection_name_with_prefix} successfully created!")
 
     def _create_collection_if_not_exists(self, collection_name, dimension):
         if not self.has_collection(collection_name=collection_name):
@@ -120,7 +125,7 @@ class QdrantClient:
             )
             return self._result_to_get_result(points.points)
         except Exception as e:
-            print(e)
+            log.exception(f"Error querying a collection '{collection_name}': {e}")
             return None
 
     def get(self, collection_name: str) -> Optional[GetResult]:

backend/open_webui/retrieval/web/perplexity.py

@@ -0,0 +1,87 @@
+import logging
+from typing import Optional, List
+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_perplexity(
+    api_key: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    """Search using Perplexity API and return the results as a list of SearchResult objects.
+
+    Args:
+      api_key (str): A Perplexity API key
+      query (str): The query to search for
+      count (int): Maximum number of results to return
+
+    """
+
+    # Handle PersistentConfig object
+    if hasattr(api_key, "__str__"):
+        api_key = str(api_key)
+
+    try:
+        url = "https://api.perplexity.ai/chat/completions"
+
+        # Create payload for the API call
+        payload = {
+            "model": "sonar",
+            "messages": [
+                {
+                    "role": "system",
+                    "content": "You are a search assistant. Provide factual information with citations.",
+                },
+                {"role": "user", "content": query},
+            ],
+            "temperature": 0.2,  # Lower temperature for more factual responses
+            "stream": False,
+        }
+
+        headers = {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+        }
+
+        # Make the API request
+        response = requests.request("POST", url, json=payload, headers=headers)
+
+        # Parse the JSON response
+        json_response = response.json()
+
+        # Extract citations from the response
+        citations = json_response.get("citations", [])
+
+        # Create search results from citations
+        results = []
+        for i, citation in enumerate(citations[:count]):
+            # Extract content from the response to use as snippet
+            content = ""
+            if "choices" in json_response and json_response["choices"]:
+                if i == 0:
+                    content = json_response["choices"][0]["message"]["content"]
+
+            result = {"link": citation, "title": f"Source {i+1}", "snippet": content}
+            results.append(result)
+
+        if filter_list:
+
+            results = get_filtered_results(results, filter_list)
+
+        return [
+            SearchResult(
+                link=result["link"], title=result["title"], snippet=result["snippet"]
+            )
+            for result in results[:count]
+        ]
+
+    except Exception as e:
+        log.error(f"Error searching with Perplexity API: {e}")
+        return []

backend/open_webui/routers/audio.py

@@ -54,7 +54,7 @@ MAX_FILE_SIZE = MAX_FILE_SIZE_MB * 1024 * 1024  # Convert MB to bytes
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["AUDIO"])
 
-SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
+SPEECH_CACHE_DIR = CACHE_DIR / "audio" / "speech"
 SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 
@@ -71,7 +71,7 @@ from pydub.utils import mediainfo
 def is_mp4_audio(file_path):
     """Check if the given file is an MP4 audio file."""
     if not os.path.isfile(file_path):
-        print(f"File not found: {file_path}")
+        log.error(f"File not found: {file_path}")
         return False
 
     info = mediainfo(file_path)
@@ -88,7 +88,7 @@ def convert_mp4_to_wav(file_path, output_path):
     """Convert MP4 audio file to WAV format."""
     audio = AudioSegment.from_file(file_path, format="mp4")
     audio.export(output_path, format="wav")
-    print(f"Converted {file_path} to {output_path}")
+    log.info(f"Converted {file_path} to {output_path}")
 
 
 def set_faster_whisper_model(model: str, auto_update: bool = False):
@@ -266,7 +266,6 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         payload["model"] = request.app.state.config.TTS_MODEL
 
         try:
-            # print(payload)
             timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
             async with aiohttp.ClientSession(
                 timeout=timeout, trust_env=True
@@ -468,7 +467,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
 
 
 def transcribe(request: Request, file_path):
-    print("transcribe", file_path)
+    log.info(f"transcribe: {file_path}")
     filename = os.path.basename(file_path)
     file_dir = os.path.dirname(file_path)
     id = filename.split(".")[0]
@@ -680,7 +679,22 @@ def transcription(
 def get_available_models(request: Request) -> list[dict]:
     available_models = []
     if request.app.state.config.TTS_ENGINE == "openai":
-        available_models = [{"id": "tts-1"}, {"id": "tts-1-hd"}]
+        # Use custom endpoint if not using the official OpenAI API URL
+        if not request.app.state.config.TTS_OPENAI_API_BASE_URL.startswith(
+            "https://api.openai.com"
+        ):
+            try:
+                response = requests.get(
+                    f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/models"
+                )
+                response.raise_for_status()
+                data = response.json()
+                available_models = data.get("models", [])
+            except Exception as e:
+                log.error(f"Error fetching models from custom endpoint: {str(e)}")
+                available_models = [{"id": "tts-1"}, {"id": "tts-1-hd"}]
+        else:
+            available_models = [{"id": "tts-1"}, {"id": "tts-1-hd"}]
     elif request.app.state.config.TTS_ENGINE == "elevenlabs":
         try:
             response = requests.get(
@@ -711,14 +725,37 @@ def get_available_voices(request) -> dict:
     """Returns {voice_id: voice_name} dict"""
     available_voices = {}
     if request.app.state.config.TTS_ENGINE == "openai":
-        available_voices = {
+        # Use custom endpoint if not using the official OpenAI API URL
-            "alloy": "alloy",
+        if not request.app.state.config.TTS_OPENAI_API_BASE_URL.startswith(
-            "echo": "echo",
+            "https://api.openai.com"
-            "fable": "fable",
+        ):
-            "onyx": "onyx",
+            try:
-            "nova": "nova",
+                response = requests.get(
-            "shimmer": "shimmer",
+                    f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/voices"
-        }
+                )
+                response.raise_for_status()
+                data = response.json()
+                voices_list = data.get("voices", [])
+                available_voices = {voice["id"]: voice["name"] for voice in voices_list}
+            except Exception as e:
+                log.error(f"Error fetching voices from custom endpoint: {str(e)}")
+                available_voices = {
+                    "alloy": "alloy",
+                    "echo": "echo",
+                    "fable": "fable",
+                    "onyx": "onyx",
+                    "nova": "nova",
+                    "shimmer": "shimmer",
+                }
+        else:
+            available_voices = {
+                "alloy": "alloy",
+                "echo": "echo",
+                "fable": "fable",
+                "onyx": "onyx",
+                "nova": "nova",
+                "shimmer": "shimmer",
+            }
     elif request.app.state.config.TTS_ENGINE == "elevenlabs":
         try:
             available_voices = get_elevenlabs_voices(

backend/open_webui/routers/auths.py

@@ -31,10 +31,7 @@ from open_webui.env import (
 )
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from fastapi.responses import RedirectResponse, Response
-from open_webui.config import (
+from open_webui.config import OPENID_PROVIDER_URL, ENABLE_OAUTH_SIGNUP, ENABLE_LDAP
-    OPENID_PROVIDER_URL,
-    ENABLE_OAUTH_SIGNUP,
-)
 from pydantic import BaseModel
 from open_webui.utils.misc import parse_duration, validate_email_format
 from open_webui.utils.auth import (
@@ -51,8 +48,10 @@ from open_webui.utils.access_control import get_permissions
 from typing import Optional, List
 
 from ssl import CERT_REQUIRED, PROTOCOL_TLS
-from ldap3 import Server, Connection, NONE, Tls
+
-from ldap3.utils.conv import escape_filter_chars
+if ENABLE_LDAP.value:
+    from ldap3 import Server, Connection, NONE, Tls
+    from ldap3.utils.conv import escape_filter_chars
 
 router = APIRouter()
 
@@ -231,9 +230,12 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
 
         entry = connection_app.entries[0]
         username = str(entry[f"{LDAP_ATTRIBUTE_FOR_USERNAME}"]).lower()
-        mail = str(entry[f"{LDAP_ATTRIBUTE_FOR_MAIL}"])
+        email = str(entry[f"{LDAP_ATTRIBUTE_FOR_MAIL}"])
-        if not mail or mail == "" or mail == "[]":
+        if not email or email == "" or email == "[]":
-            raise HTTPException(400, f"User {form_data.user} does not have mail.")
+            raise HTTPException(400, f"User {form_data.user} does not have email.")
+        else:
+            email = email.lower()
+
         cn = str(entry["cn"])
         user_dn = entry.entry_dn
 
@@ -248,18 +250,10 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
             if not connection_user.bind():
                 raise HTTPException(400, f"Authentication failed for {form_data.user}")
 
-            user = Users.get_user_by_email(mail)
+            user = Users.get_user_by_email(email)
             if not user:
                 try:
                     user_count = Users.get_num_users()
-                    if (
-                        request.app.state.USER_COUNT
-                        and user_count >= request.app.state.USER_COUNT
-                    ):
-                        raise HTTPException(
-                            status.HTTP_403_FORBIDDEN,
-                            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-                        )
 
                     role = (
                         "admin"
@@ -268,7 +262,10 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                     )
 
                     user = Auths.insert_new_auth(
-                        email=mail, password=str(uuid.uuid4()), name=cn, role=role
+                        email=email,
+                        password=str(uuid.uuid4()),
+                        name=cn,
+                        role=role,
                     )
 
                     if not user:
@@ -281,7 +278,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                 except Exception as err:
                     raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
 
-            user = Auths.authenticate_user_by_trusted_header(mail)
+            user = Auths.authenticate_user_by_trusted_header(email)
 
             if user:
                 token = create_token(
@@ -439,11 +436,6 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
             )
 
     user_count = Users.get_num_users()
-    if request.app.state.USER_COUNT and user_count >= request.app.state.USER_COUNT:
-        raise HTTPException(
-            status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
-        )
-
     if not validate_email_format(form_data.email.lower()):
         raise HTTPException(
             status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT
@@ -613,7 +605,7 @@ async def get_admin_details(request: Request, user=Depends(get_current_user)):
         admin_email = request.app.state.config.ADMIN_EMAIL
         admin_name = None
 
-        print(admin_email, admin_name)
+        log.info(f"Admin details - Email: {admin_email}, Name: {admin_name}")
 
         if admin_email:
             admin = Users.get_user_by_email(admin_email)

backend/open_webui/routers/configs.py

@@ -70,6 +70,7 @@ async def set_direct_connections_config(
 # CodeInterpreterConfig
 ############################
 class CodeInterpreterConfigForm(BaseModel):
+    ENABLE_CODE_EXECUTION: bool
     CODE_EXECUTION_ENGINE: str
     CODE_EXECUTION_JUPYTER_URL: Optional[str]
     CODE_EXECUTION_JUPYTER_AUTH: Optional[str]
@@ -89,6 +90,7 @@ class CodeInterpreterConfigForm(BaseModel):
 @router.get("/code_execution", response_model=CodeInterpreterConfigForm)
 async def get_code_execution_config(request: Request, user=Depends(get_admin_user)):
     return {
+        "ENABLE_CODE_EXECUTION": request.app.state.config.ENABLE_CODE_EXECUTION,
         "CODE_EXECUTION_ENGINE": request.app.state.config.CODE_EXECUTION_ENGINE,
         "CODE_EXECUTION_JUPYTER_URL": request.app.state.config.CODE_EXECUTION_JUPYTER_URL,
         "CODE_EXECUTION_JUPYTER_AUTH": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH,
@@ -111,6 +113,8 @@ async def set_code_execution_config(
     request: Request, form_data: CodeInterpreterConfigForm, user=Depends(get_admin_user)
 ):
 
+    request.app.state.config.ENABLE_CODE_EXECUTION = form_data.ENABLE_CODE_EXECUTION
+
     request.app.state.config.CODE_EXECUTION_ENGINE = form_data.CODE_EXECUTION_ENGINE
     request.app.state.config.CODE_EXECUTION_JUPYTER_URL = (
         form_data.CODE_EXECUTION_JUPYTER_URL
@@ -153,6 +157,7 @@ async def set_code_execution_config(
     )
 
     return {
+        "ENABLE_CODE_EXECUTION": request.app.state.config.ENABLE_CODE_EXECUTION,
         "CODE_EXECUTION_ENGINE": request.app.state.config.CODE_EXECUTION_ENGINE,
         "CODE_EXECUTION_JUPYTER_URL": request.app.state.config.CODE_EXECUTION_JUPYTER_URL,
         "CODE_EXECUTION_JUPYTER_AUTH": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH,

backend/open_webui/routers/files.py

@@ -16,6 +16,7 @@ from open_webui.models.files import (
     Files,
 )
 from open_webui.routers.retrieval import ProcessFileForm, process_file
+from open_webui.routers.audio import transcribe
 from open_webui.storage.provider import Storage
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from pydantic import BaseModel
@@ -67,7 +68,22 @@ def upload_file(
         )
 
         try:
-            process_file(request, ProcessFileForm(file_id=id), user=user)
+            if file.content_type in [
+                "audio/mpeg",
+                "audio/wav",
+                "audio/ogg",
+                "audio/x-m4a",
+            ]:
+                file_path = Storage.get_file(file_path)
+                result = transcribe(request, file_path)
+                process_file(
+                    request,
+                    ProcessFileForm(file_id=id, content=result.get("text", "")),
+                    user=user,
+                )
+            else:
+                process_file(request, ProcessFileForm(file_id=id), user=user)
+
             file_item = Files.get_file_by_id(id=id)
         except Exception as e:
             log.exception(e)
@@ -273,7 +289,7 @@ async def get_html_file_content_by_id(id: str, user=Depends(get_verified_user)):
 
             # Check if the file already exists in the cache
             if file_path.is_file():
-                print(f"file_path: {file_path}")
+                log.info(f"file_path: {file_path}")
                 return FileResponse(file_path)
             else:
                 raise HTTPException(

backend/open_webui/routers/functions.py

@@ -1,4 +1,5 @@
 import os
+import logging
 from pathlib import Path
 from typing import Optional
 
@@ -13,6 +14,11 @@ from open_webui.config import CACHE_DIR
 from open_webui.constants import ERROR_MESSAGES
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from open_webui.utils.auth import get_admin_user, get_verified_user
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
+
 
 router = APIRouter()
 
@@ -68,7 +74,7 @@ async def create_new_function(
 
             function = Functions.insert_new_function(user.id, function_type, form_data)
 
-            function_cache_dir = Path(CACHE_DIR) / "functions" / form_data.id
+            function_cache_dir = CACHE_DIR / "functions" / form_data.id
             function_cache_dir.mkdir(parents=True, exist_ok=True)
 
             if function:
@@ -79,7 +85,7 @@ async def create_new_function(
                     detail=ERROR_MESSAGES.DEFAULT("Error creating function"),
                 )
         except Exception as e:
-            print(e)
+            log.exception(f"Failed to create a new function: {e}")
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
                 detail=ERROR_MESSAGES.DEFAULT(e),
@@ -183,7 +189,7 @@ async def update_function_by_id(
         FUNCTIONS[id] = function_module
 
         updated = {**form_data.model_dump(exclude={"id"}), "type": function_type}
-        print(updated)
+        log.debug(updated)
 
         function = Functions.update_function_by_id(id, updated)
 
@@ -299,7 +305,7 @@ async def update_function_valves_by_id(
                 Functions.update_function_valves_by_id(id, valves.model_dump())
                 return valves.model_dump()
             except Exception as e:
-                print(e)
+                log.exception(f"Error updating function values by id {id}: {e}")
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
                     detail=ERROR_MESSAGES.DEFAULT(e),
@@ -388,7 +394,7 @@ async def update_function_user_valves_by_id(
                 )
                 return user_valves.model_dump()
             except Exception as e:
-                print(e)
+                log.exception(f"Error updating function user valves by id {id}: {e}")
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
                     detail=ERROR_MESSAGES.DEFAULT(e),

backend/open_webui/routers/groups.py

@@ -1,7 +1,7 @@
 import os
 from pathlib import Path
 from typing import Optional
-
+import logging
 
 from open_webui.models.users import Users
 from open_webui.models.groups import (
@@ -14,7 +14,13 @@ from open_webui.models.groups import (
 from open_webui.config import CACHE_DIR
 from open_webui.constants import ERROR_MESSAGES
 from fastapi import APIRouter, Depends, HTTPException, Request, status
+
 from open_webui.utils.auth import get_admin_user, get_verified_user
+from open_webui.env import SRC_LOG_LEVELS
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 router = APIRouter()
 
@@ -37,7 +43,7 @@ async def get_groups(user=Depends(get_verified_user)):
 
 
 @router.post("/create", response_model=Optional[GroupResponse])
-async def create_new_function(form_data: GroupForm, user=Depends(get_admin_user)):
+async def create_new_group(form_data: GroupForm, user=Depends(get_admin_user)):
     try:
         group = Groups.insert_new_group(user.id, form_data)
         if group:
@@ -48,7 +54,7 @@ async def create_new_function(form_data: GroupForm, user=Depends(get_admin_user)
                 detail=ERROR_MESSAGES.DEFAULT("Error creating group"),
             )
     except Exception as e:
-        print(e)
+        log.exception(f"Error creating a new group: {e}")
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),
@@ -94,7 +100,7 @@ async def update_group_by_id(
                 detail=ERROR_MESSAGES.DEFAULT("Error updating group"),
             )
     except Exception as e:
-        print(e)
+        log.exception(f"Error updating group {id}: {e}")
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),
@@ -118,7 +124,7 @@ async def delete_group_by_id(id: str, user=Depends(get_admin_user)):
                 detail=ERROR_MESSAGES.DEFAULT("Error deleting group"),
             )
     except Exception as e:
-        print(e)
+        log.exception(f"Error deleting group {id}: {e}")
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),

backend/open_webui/routers/images.py

@@ -25,7 +25,7 @@ from pydantic import BaseModel
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["IMAGES"])
 
-IMAGE_CACHE_DIR = Path(CACHE_DIR).joinpath("./image/generations/")
+IMAGE_CACHE_DIR = CACHE_DIR / "image" / "generations"
 IMAGE_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 
@@ -144,6 +144,8 @@ async def update_config(
     request.app.state.config.COMFYUI_BASE_URL = (
         form_data.comfyui.COMFYUI_BASE_URL.strip("/")
     )
+    request.app.state.config.COMFYUI_API_KEY = form_data.comfyui.COMFYUI_API_KEY
+
     request.app.state.config.COMFYUI_WORKFLOW = form_data.comfyui.COMFYUI_WORKFLOW
     request.app.state.config.COMFYUI_WORKFLOW_NODES = (
         form_data.comfyui.COMFYUI_WORKFLOW_NODES
@@ -203,9 +205,17 @@ async def verify_url(request: Request, user=Depends(get_admin_user)):
             request.app.state.config.ENABLE_IMAGE_GENERATION = False
             raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL)
     elif request.app.state.config.IMAGE_GENERATION_ENGINE == "comfyui":
+
+        headers = None
+        if request.app.state.config.COMFYUI_API_KEY:
+            headers = {
+                "Authorization": f"Bearer {request.app.state.config.COMFYUI_API_KEY}"
+            }
+
         try:
             r = requests.get(
-                url=f"{request.app.state.config.COMFYUI_BASE_URL}/object_info"
+                url=f"{request.app.state.config.COMFYUI_BASE_URL}/object_info",
+                headers=headers,
             )
             r.raise_for_status()
             return True
@@ -351,7 +361,7 @@ def get_models(request: Request, user=Depends(get_verified_user)):
             if model_node_id:
                 model_list_key = None
 
-                print(workflow[model_node_id]["class_type"])
+                log.info(workflow[model_node_id]["class_type"])
                 for key in info[workflow[model_node_id]["class_type"]]["input"][
                     "required"
                 ]:
@@ -507,7 +517,13 @@ async def image_generations(
             images = []
 
             for image in res["data"]:
-                image_data, content_type = load_b64_image_data(image["b64_json"])
+                if "url" in image:
+                    image_data, content_type = load_url_image_data(
+                        image["url"], headers
+                    )
+                else:
+                    image_data, content_type = load_b64_image_data(image["b64_json"])
+
                 url = upload_image(request, data, image_data, content_type, user)
                 images.append({"url": url})
             return images

backend/open_webui/routers/knowledge.py

@@ -614,7 +614,7 @@ def add_files_to_knowledge_batch(
         )
 
     # Get files content
-    print(f"files/batch/add - {len(form_data)} files")
+    log.info(f"files/batch/add - {len(form_data)} files")
     files: List[FileModel] = []
     for form in form_data:
         file = Files.get_file_by_id(form.file_id)

backend/open_webui/routers/ollama.py

@@ -14,6 +14,11 @@ from urllib.parse import urlparse
 import aiohttp
 from aiocache import cached
 import requests
+from open_webui.models.users import UserModel
+
+from open_webui.env import (
+    ENABLE_FORWARD_USER_INFO_HEADERS,
+)
 
 from fastapi import (
     Depends,
@@ -50,7 +55,7 @@ from open_webui.env import (
     ENV,
     SRC_LOG_LEVELS,
     AIOHTTP_CLIENT_TIMEOUT,
-    AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST,
+    AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST,
     BYPASS_MODEL_ACCESS_CONTROL,
 )
 from open_webui.constants import ERROR_MESSAGES
@@ -66,12 +71,26 @@ log.setLevel(SRC_LOG_LEVELS["OLLAMA"])
 ##########################################
 
 
-async def send_get_request(url, key=None):
+async def send_get_request(url, key=None, user: UserModel = None):
-    timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
+    timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST)
     try:
         async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:
             async with session.get(
-                url, headers={**({"Authorization": f"Bearer {key}"} if key else {})}
+                url,
+                headers={
+                    "Content-Type": "application/json",
+                    **({"Authorization": f"Bearer {key}"} if key else {}),
+                    **(
+                        {
+                            "X-OpenWebUI-User-Name": user.name,
+                            "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 {}
+                    ),
+                },
             ) as response:
                 return await response.json()
     except Exception as e:
@@ -96,6 +115,7 @@ async def send_post_request(
     stream: bool = True,
     key: Optional[str] = None,
     content_type: Optional[str] = None,
+    user: UserModel = None,
 ):
 
     r = None
@@ -110,6 +130,16 @@ async def send_post_request(
             headers={
                 "Content-Type": "application/json",
                 **({"Authorization": f"Bearer {key}"} if key else {}),
+                **(
+                    {
+                        "X-OpenWebUI-User-Name": user.name,
+                        "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 {}
+                ),
             },
         )
         r.raise_for_status()
@@ -186,12 +216,24 @@ async def verify_connection(
     key = form_data.key
 
     async with aiohttp.ClientSession(
-        timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
+        timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST)
     ) as session:
         try:
             async with session.get(
                 f"{url}/api/version",
-                headers={**({"Authorization": f"Bearer {key}"} if key else {})},
+                headers={
+                    **({"Authorization": f"Bearer {key}"} if key else {}),
+                    **(
+                        {
+                            "X-OpenWebUI-User-Name": user.name,
+                            "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 {}
+                    ),
+                },
             ) as r:
                 if r.status != 200:
                     detail = f"HTTP Error: {r.status}"
@@ -254,7 +296,7 @@ async def update_config(
 
 
 @cached(ttl=3)
-async def get_all_models(request: Request):
+async def get_all_models(request: Request, user: UserModel = None):
     log.info("get_all_models()")
     if request.app.state.config.ENABLE_OLLAMA_API:
         request_tasks = []
@@ -262,7 +304,7 @@ async def get_all_models(request: Request):
             if (str(idx) not in request.app.state.config.OLLAMA_API_CONFIGS) and (
                 url not in request.app.state.config.OLLAMA_API_CONFIGS  # Legacy support
             ):
-                request_tasks.append(send_get_request(f"{url}/api/tags"))
+                request_tasks.append(send_get_request(f"{url}/api/tags", user=user))
             else:
                 api_config = request.app.state.config.OLLAMA_API_CONFIGS.get(
                     str(idx),
@@ -275,7 +317,9 @@ async def get_all_models(request: Request):
                 key = api_config.get("key", None)
 
                 if enable:
-                    request_tasks.append(send_get_request(f"{url}/api/tags", key))
+                    request_tasks.append(
+                        send_get_request(f"{url}/api/tags", key, user=user)
+                    )
                 else:
                     request_tasks.append(asyncio.ensure_future(asyncio.sleep(0, None)))
 
@@ -360,7 +404,7 @@ async def get_ollama_tags(
     models = []
 
     if url_idx is None:
-        models = await get_all_models(request)
+        models = await get_all_models(request, user=user)
     else:
         url = request.app.state.config.OLLAMA_BASE_URLS[url_idx]
         key = get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS)
@@ -370,7 +414,19 @@ async def get_ollama_tags(
             r = requests.request(
                 method="GET",
                 url=f"{url}/api/tags",
-                headers={**({"Authorization": f"Bearer {key}"} if key else {})},
+                headers={
+                    **({"Authorization": f"Bearer {key}"} if key else {}),
+                    **(
+                        {
+                            "X-OpenWebUI-User-Name": user.name,
+                            "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 {}
+                    ),
+                },
             )
             r.raise_for_status()
 
@@ -477,6 +533,7 @@ async def get_ollama_loaded_models(request: Request, user=Depends(get_verified_u
                         url, {}
                     ),  # Legacy support
                 ).get("key", None),
+                user=user,
             )
             for idx, url in enumerate(request.app.state.config.OLLAMA_BASE_URLS)
         ]
@@ -509,6 +566,7 @@ async def pull_model(
         url=f"{url}/api/pull",
         payload=json.dumps(payload),
         key=get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS),
+        user=user,
     )
 
 
@@ -527,7 +585,7 @@ async def push_model(
     user=Depends(get_admin_user),
 ):
     if url_idx is None:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
         models = request.app.state.OLLAMA_MODELS
 
         if form_data.name in models:
@@ -545,6 +603,7 @@ async def push_model(
         url=f"{url}/api/push",
         payload=form_data.model_dump_json(exclude_none=True).encode(),
         key=get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS),
+        user=user,
     )
 
 
@@ -571,6 +630,7 @@ async def create_model(
         url=f"{url}/api/create",
         payload=form_data.model_dump_json(exclude_none=True).encode(),
         key=get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS),
+        user=user,
     )
 
 
@@ -588,7 +648,7 @@ async def copy_model(
     user=Depends(get_admin_user),
 ):
     if url_idx is None:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
         models = request.app.state.OLLAMA_MODELS
 
         if form_data.source in models:
@@ -609,6 +669,16 @@ async def copy_model(
             headers={
                 "Content-Type": "application/json",
                 **({"Authorization": f"Bearer {key}"} if key else {}),
+                **(
+                    {
+                        "X-OpenWebUI-User-Name": user.name,
+                        "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 {}
+                ),
             },
             data=form_data.model_dump_json(exclude_none=True).encode(),
         )
@@ -643,7 +713,7 @@ async def delete_model(
     user=Depends(get_admin_user),
 ):
     if url_idx is None:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
         models = request.app.state.OLLAMA_MODELS
 
         if form_data.name in models:
@@ -665,6 +735,16 @@ async def delete_model(
             headers={
                 "Content-Type": "application/json",
                 **({"Authorization": f"Bearer {key}"} if key else {}),
+                **(
+                    {
+                        "X-OpenWebUI-User-Name": user.name,
+                        "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 {}
+                ),
             },
         )
         r.raise_for_status()
@@ -693,7 +773,7 @@ async def delete_model(
 async def show_model_info(
     request: Request, form_data: ModelNameForm, user=Depends(get_verified_user)
 ):
-    await get_all_models(request)
+    await get_all_models(request, user=user)
     models = request.app.state.OLLAMA_MODELS
 
     if form_data.name not in models:
@@ -714,6 +794,16 @@ async def show_model_info(
             headers={
                 "Content-Type": "application/json",
                 **({"Authorization": f"Bearer {key}"} if key else {}),
+                **(
+                    {
+                        "X-OpenWebUI-User-Name": user.name,
+                        "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 {}
+                ),
             },
             data=form_data.model_dump_json(exclude_none=True).encode(),
         )
@@ -757,7 +847,7 @@ async def embed(
     log.info(f"generate_ollama_batch_embeddings {form_data}")
 
     if url_idx is None:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
         models = request.app.state.OLLAMA_MODELS
 
         model = form_data.model
@@ -783,6 +873,16 @@ async def embed(
             headers={
                 "Content-Type": "application/json",
                 **({"Authorization": f"Bearer {key}"} if key else {}),
+                **(
+                    {
+                        "X-OpenWebUI-User-Name": user.name,
+                        "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 {}
+                ),
             },
             data=form_data.model_dump_json(exclude_none=True).encode(),
         )
@@ -826,7 +926,7 @@ async def embeddings(
     log.info(f"generate_ollama_embeddings {form_data}")
 
     if url_idx is None:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
         models = request.app.state.OLLAMA_MODELS
 
         model = form_data.model
@@ -852,6 +952,16 @@ async def embeddings(
             headers={
                 "Content-Type": "application/json",
                 **({"Authorization": f"Bearer {key}"} if key else {}),
+                **(
+                    {
+                        "X-OpenWebUI-User-Name": user.name,
+                        "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 {}
+                ),
             },
             data=form_data.model_dump_json(exclude_none=True).encode(),
         )
@@ -901,7 +1011,7 @@ async def generate_completion(
     user=Depends(get_verified_user),
 ):
     if url_idx is None:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
         models = request.app.state.OLLAMA_MODELS
 
         model = form_data.model
@@ -931,6 +1041,7 @@ async def generate_completion(
         url=f"{url}/api/generate",
         payload=form_data.model_dump_json(exclude_none=True).encode(),
         key=get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS),
+        user=user,
     )
 
 
@@ -1060,6 +1171,7 @@ async def generate_chat_completion(
         stream=form_data.stream,
         key=get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS),
         content_type="application/x-ndjson",
+        user=user,
     )
 
 
@@ -1162,6 +1274,7 @@ async def generate_openai_completion(
         payload=json.dumps(payload),
         stream=payload.get("stream", False),
         key=get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS),
+        user=user,
     )
 
 
@@ -1240,6 +1353,7 @@ async def generate_openai_chat_completion(
         payload=json.dumps(payload),
         stream=payload.get("stream", False),
         key=get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS),
+        user=user,
     )
 
 
@@ -1253,7 +1367,7 @@ async def get_openai_models(
 
     models = []
     if url_idx is None:
-        model_list = await get_all_models(request)
+        model_list = await get_all_models(request, user=user)
         models = [
             {
                 "id": model["model"],

backend/open_webui/routers/openai.py

@@ -22,10 +22,11 @@ from open_webui.config import (
 )
 from open_webui.env import (
     AIOHTTP_CLIENT_TIMEOUT,
-    AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST,
+    AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST,
     ENABLE_FORWARD_USER_INFO_HEADERS,
     BYPASS_MODEL_ACCESS_CONTROL,
 )
+from open_webui.models.users import UserModel
 
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import ENV, SRC_LOG_LEVELS
@@ -51,12 +52,25 @@ log.setLevel(SRC_LOG_LEVELS["OPENAI"])
 ##########################################
 
 
-async def send_get_request(url, key=None):
+async def send_get_request(url, key=None, user: UserModel = None):
-    timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
+    timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST)
     try:
         async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:
             async with session.get(
-                url, headers={**({"Authorization": f"Bearer {key}"} if key else {})}
+                url,
+                headers={
+                    **({"Authorization": f"Bearer {key}"} if key else {}),
+                    **(
+                        {
+                            "X-OpenWebUI-User-Name": user.name,
+                            "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 {}
+                    ),
+                },
             ) as response:
                 return await response.json()
     except Exception as e:
@@ -84,9 +98,15 @@ def openai_o1_o3_handler(payload):
         payload["max_completion_tokens"] = payload["max_tokens"]
         del payload["max_tokens"]
 
-    # Fix: O1 does not support the "system" parameter, Modify "system" to "user"
+    # Fix: o1 and o3 do not support the "system" role directly.
+    # For older models like "o1-mini" or "o1-preview", use role "user".
+    # For newer o1/o3 models, replace "system" with "developer".
     if payload["messages"][0]["role"] == "system":
-        payload["messages"][0]["role"] = "user"
+        model_lower = payload["model"].lower()
+        if model_lower.startswith("o1-mini") or model_lower.startswith("o1-preview"):
+            payload["messages"][0]["role"] = "user"
+        else:
+            payload["messages"][0]["role"] = "developer"
 
     return payload
 
@@ -172,7 +192,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         body = await request.body()
         name = hashlib.sha256(body).hexdigest()
 
-        SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
+        SPEECH_CACHE_DIR = CACHE_DIR / "audio" / "speech"
         SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
         file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
         file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
@@ -247,7 +267,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND)
 
 
-async def get_all_models_responses(request: Request) -> list:
+async def get_all_models_responses(request: Request, user: UserModel) -> list:
     if not request.app.state.config.ENABLE_OPENAI_API:
         return []
 
@@ -271,7 +291,9 @@ async def get_all_models_responses(request: Request) -> list:
         ):
             request_tasks.append(
                 send_get_request(
-                    f"{url}/models", request.app.state.config.OPENAI_API_KEYS[idx]
+                    f"{url}/models",
+                    request.app.state.config.OPENAI_API_KEYS[idx],
+                    user=user,
                 )
             )
         else:
@@ -291,6 +313,7 @@ async def get_all_models_responses(request: Request) -> list:
                         send_get_request(
                             f"{url}/models",
                             request.app.state.config.OPENAI_API_KEYS[idx],
+                            user=user,
                         )
                     )
                 else:
@@ -352,13 +375,13 @@ async def get_filtered_models(models, user):
 
 
 @cached(ttl=3)
-async def get_all_models(request: Request) -> dict[str, list]:
+async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
     log.info("get_all_models()")
 
     if not request.app.state.config.ENABLE_OPENAI_API:
         return {"data": []}
 
-    responses = await get_all_models_responses(request)
+    responses = await get_all_models_responses(request, user=user)
 
     def extract_data(response):
         if response and "data" in response:
@@ -418,16 +441,14 @@ async def get_models(
     }
 
     if url_idx is None:
-        models = await get_all_models(request)
+        models = await get_all_models(request, user=user)
     else:
         url = request.app.state.config.OPENAI_API_BASE_URLS[url_idx]
         key = request.app.state.config.OPENAI_API_KEYS[url_idx]
 
         r = None
         async with aiohttp.ClientSession(
-            timeout=aiohttp.ClientTimeout(
+            timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST)
-                total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST
-            )
         ) as session:
             try:
                 async with session.get(
@@ -507,7 +528,7 @@ async def verify_connection(
     key = form_data.key
 
     async with aiohttp.ClientSession(
-        timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
+        timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST)
     ) as session:
         try:
             async with session.get(
@@ -515,6 +536,16 @@ async def verify_connection(
                 headers={
                     "Authorization": f"Bearer {key}",
                     "Content-Type": "application/json",
+                    **(
+                        {
+                            "X-OpenWebUI-User-Name": user.name,
+                            "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 {}
+                    ),
                 },
             ) as r:
                 if r.status != 200:
@@ -587,7 +618,7 @@ async def generate_chat_completion(
                 detail="Model not found",
             )
 
-    await get_all_models(request)
+    await get_all_models(request, user=user)
     model = request.app.state.OPENAI_MODELS.get(model_id)
     if model:
         idx = model["urlIdx"]
@@ -777,7 +808,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
         if r is not None:
             try:
                 res = await r.json()
-                print(res)
+                log.error(res)
                 if "error" in res:
                     detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
             except Exception:

backend/open_webui/routers/pipelines.py

@@ -101,7 +101,7 @@ async def process_pipeline_inlet_filter(request, payload, user, models):
                 if "detail" in res:
                     raise Exception(response.status, res["detail"])
             except Exception as e:
-                print(f"Connection error: {e}")
+                log.exception(f"Connection error: {e}")
 
     return payload
 
@@ -153,7 +153,7 @@ async def process_pipeline_outlet_filter(request, payload, user, models):
                 except Exception:
                     pass
             except Exception as e:
-                print(f"Connection error: {e}")
+                log.exception(f"Connection error: {e}")
 
     return payload
 
@@ -169,7 +169,7 @@ router = APIRouter()
 
 @router.get("/list")
 async def get_pipelines_list(request: Request, user=Depends(get_admin_user)):
-    responses = await get_all_models_responses(request)
+    responses = await get_all_models_responses(request, user)
     log.debug(f"get_pipelines_list: get_openai_models_responses returned {responses}")
 
     urlIdxs = [
@@ -196,7 +196,7 @@ async def upload_pipeline(
     file: UploadFile = File(...),
     user=Depends(get_admin_user),
 ):
-    print("upload_pipeline", urlIdx, file.filename)
+    log.info(f"upload_pipeline: urlIdx={urlIdx}, filename={file.filename}")
     # Check if the uploaded file is a python file
     if not (file.filename and file.filename.endswith(".py")):
         raise HTTPException(
@@ -231,7 +231,7 @@ async def upload_pipeline(
         return {**data}
     except Exception as e:
         # Handle connection error here
-        print(f"Connection error: {e}")
+        log.exception(f"Connection error: {e}")
 
         detail = None
         status_code = status.HTTP_404_NOT_FOUND
@@ -282,7 +282,7 @@ async def add_pipeline(
         return {**data}
     except Exception as e:
         # Handle connection error here
-        print(f"Connection error: {e}")
+        log.exception(f"Connection error: {e}")
 
         detail = None
         if r is not None:
@@ -327,7 +327,7 @@ async def delete_pipeline(
         return {**data}
     except Exception as e:
         # Handle connection error here
-        print(f"Connection error: {e}")
+        log.exception(f"Connection error: {e}")
 
         detail = None
         if r is not None:
@@ -361,7 +361,7 @@ async def get_pipelines(
         return {**data}
     except Exception as e:
         # Handle connection error here
-        print(f"Connection error: {e}")
+        log.exception(f"Connection error: {e}")
 
         detail = None
         if r is not None:
@@ -400,7 +400,7 @@ async def get_pipeline_valves(
         return {**data}
     except Exception as e:
         # Handle connection error here
-        print(f"Connection error: {e}")
+        log.exception(f"Connection error: {e}")
 
         detail = None
         if r is not None:
@@ -440,7 +440,7 @@ async def get_pipeline_valves_spec(
         return {**data}
     except Exception as e:
         # Handle connection error here
-        print(f"Connection error: {e}")
+        log.exception(f"Connection error: {e}")
 
         detail = None
         if r is not None:
@@ -482,7 +482,7 @@ async def update_pipeline_valves(
         return {**data}
     except Exception as e:
         # Handle connection error here
-        print(f"Connection error: {e}")
+        log.exception(f"Connection error: {e}")
 
         detail = None
 

backend/open_webui/routers/retrieval.py

@@ -59,7 +59,7 @@ from open_webui.retrieval.web.serpstack import search_serpstack
 from open_webui.retrieval.web.tavily import search_tavily
 from open_webui.retrieval.web.bing import search_bing
 from open_webui.retrieval.web.exa import search_exa
-
+from open_webui.retrieval.web.perplexity import search_perplexity
 
 from open_webui.retrieval.utils import (
     get_embedding_function,
@@ -352,10 +352,16 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         "status": True,
         "pdf_extract_images": request.app.state.config.PDF_EXTRACT_IMAGES,
         "RAG_FULL_CONTEXT": request.app.state.config.RAG_FULL_CONTEXT,
+        "BYPASS_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL,
         "enable_google_drive_integration": request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
+        "enable_onedrive_integration": request.app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
         "content_extraction": {
             "engine": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
             "tika_server_url": request.app.state.config.TIKA_SERVER_URL,
+            "document_intelligence_config": {
+                "endpoint": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
+                "key": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
+            },
         },
         "chunk": {
             "text_splitter": request.app.state.config.TEXT_SPLITTER,
@@ -373,10 +379,11 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         },
         "web": {
             "ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
-            "RAG_WEB_SEARCH_FULL_CONTEXT": request.app.state.config.RAG_WEB_SEARCH_FULL_CONTEXT,
+            "BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
             "search": {
                 "enabled": request.app.state.config.ENABLE_RAG_WEB_SEARCH,
                 "drive": request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
+                "onedrive": request.app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
                 "engine": request.app.state.config.RAG_WEB_SEARCH_ENGINE,
                 "searxng_query_url": request.app.state.config.SEARXNG_QUERY_URL,
                 "google_pse_api_key": request.app.state.config.GOOGLE_PSE_API_KEY,
@@ -398,7 +405,9 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
                 "bing_search_v7_endpoint": request.app.state.config.BING_SEARCH_V7_ENDPOINT,
                 "bing_search_v7_subscription_key": request.app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
                 "exa_api_key": request.app.state.config.EXA_API_KEY,
+                "perplexity_api_key": request.app.state.config.PERPLEXITY_API_KEY,
                 "result_count": request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
+                "trust_env": request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV,
                 "concurrent_requests": request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
                 "domain_filter_list": request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
             },
@@ -411,9 +420,15 @@ class FileConfig(BaseModel):
     max_count: Optional[int] = None
 
 
+class DocumentIntelligenceConfigForm(BaseModel):
+    endpoint: str
+    key: str
+
+
 class ContentExtractionConfig(BaseModel):
     engine: str = ""
     tika_server_url: Optional[str] = None
+    document_intelligence_config: Optional[DocumentIntelligenceConfigForm] = None
 
 
 class ChunkParamUpdateForm(BaseModel):
@@ -451,6 +466,7 @@ class WebSearchConfig(BaseModel):
     bing_search_v7_endpoint: Optional[str] = None
     bing_search_v7_subscription_key: Optional[str] = None
     exa_api_key: Optional[str] = None
+    perplexity_api_key: Optional[str] = None
     result_count: Optional[int] = None
     concurrent_requests: Optional[int] = None
     trust_env: Optional[bool] = None
@@ -460,13 +476,15 @@ class WebSearchConfig(BaseModel):
 class WebConfig(BaseModel):
     search: WebSearchConfig
     ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION: Optional[bool] = None
-    RAG_WEB_SEARCH_FULL_CONTEXT: Optional[bool] = None
+    BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL: Optional[bool] = None
 
 
 class ConfigUpdateForm(BaseModel):
     RAG_FULL_CONTEXT: Optional[bool] = None
+    BYPASS_EMBEDDING_AND_RETRIEVAL: Optional[bool] = None
     pdf_extract_images: Optional[bool] = None
     enable_google_drive_integration: Optional[bool] = None
+    enable_onedrive_integration: Optional[bool] = None
     file: Optional[FileConfig] = None
     content_extraction: Optional[ContentExtractionConfig] = None
     chunk: Optional[ChunkParamUpdateForm] = None
@@ -490,24 +508,45 @@ async def update_rag_config(
         else request.app.state.config.RAG_FULL_CONTEXT
     )
 
+    request.app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL = (
+        form_data.BYPASS_EMBEDDING_AND_RETRIEVAL
+        if form_data.BYPASS_EMBEDDING_AND_RETRIEVAL is not None
+        else request.app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL
+    )
+
     request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = (
         form_data.enable_google_drive_integration
         if form_data.enable_google_drive_integration is not None
         else request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION
     )
 
+    request.app.state.config.ENABLE_ONEDRIVE_INTEGRATION = (
+        form_data.enable_onedrive_integration
+        if form_data.enable_onedrive_integration is not None
+        else request.app.state.config.ENABLE_ONEDRIVE_INTEGRATION
+    )
+
     if form_data.file is not None:
         request.app.state.config.FILE_MAX_SIZE = form_data.file.max_size
         request.app.state.config.FILE_MAX_COUNT = form_data.file.max_count
 
     if form_data.content_extraction is not None:
-        log.info(f"Updating text settings: {form_data.content_extraction}")
+        log.info(
+            f"Updating content extraction: {request.app.state.config.CONTENT_EXTRACTION_ENGINE} to {form_data.content_extraction.engine}"
+        )
         request.app.state.config.CONTENT_EXTRACTION_ENGINE = (
             form_data.content_extraction.engine
         )
         request.app.state.config.TIKA_SERVER_URL = (
             form_data.content_extraction.tika_server_url
         )
+        if form_data.content_extraction.document_intelligence_config is not None:
+            request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = (
+                form_data.content_extraction.document_intelligence_config.endpoint
+            )
+            request.app.state.config.DOCUMENT_INTELLIGENCE_KEY = (
+                form_data.content_extraction.document_intelligence_config.key
+            )
 
     if form_data.chunk is not None:
         request.app.state.config.TEXT_SPLITTER = form_data.chunk.text_splitter
@@ -528,8 +567,8 @@ async def update_rag_config(
         request.app.state.config.ENABLE_RAG_WEB_SEARCH = form_data.web.search.enabled
         request.app.state.config.RAG_WEB_SEARCH_ENGINE = form_data.web.search.engine
 
-        request.app.state.config.RAG_WEB_SEARCH_FULL_CONTEXT = (
+        request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
-            form_data.web.RAG_WEB_SEARCH_FULL_CONTEXT
+            form_data.web.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
         )
 
         request.app.state.config.SEARXNG_QUERY_URL = (
@@ -580,6 +619,10 @@ async def update_rag_config(
 
         request.app.state.config.EXA_API_KEY = form_data.web.search.exa_api_key
 
+        request.app.state.config.PERPLEXITY_API_KEY = (
+            form_data.web.search.perplexity_api_key
+        )
+
         request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = (
             form_data.web.search.result_count
         )
@@ -597,6 +640,7 @@ async def update_rag_config(
         "status": True,
         "pdf_extract_images": request.app.state.config.PDF_EXTRACT_IMAGES,
         "RAG_FULL_CONTEXT": request.app.state.config.RAG_FULL_CONTEXT,
+        "BYPASS_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL,
         "file": {
             "max_size": request.app.state.config.FILE_MAX_SIZE,
             "max_count": request.app.state.config.FILE_MAX_COUNT,
@@ -604,6 +648,10 @@ async def update_rag_config(
         "content_extraction": {
             "engine": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
             "tika_server_url": request.app.state.config.TIKA_SERVER_URL,
+            "document_intelligence_config": {
+                "endpoint": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
+                "key": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
+            },
         },
         "chunk": {
             "text_splitter": request.app.state.config.TEXT_SPLITTER,
@@ -617,7 +665,7 @@ async def update_rag_config(
         },
         "web": {
             "ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
-            "RAG_WEB_SEARCH_FULL_CONTEXT": request.app.state.config.RAG_WEB_SEARCH_FULL_CONTEXT,
+            "BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
             "search": {
                 "enabled": request.app.state.config.ENABLE_RAG_WEB_SEARCH,
                 "engine": request.app.state.config.RAG_WEB_SEARCH_ENGINE,
@@ -641,6 +689,7 @@ async def update_rag_config(
                 "bing_search_v7_endpoint": request.app.state.config.BING_SEARCH_V7_ENDPOINT,
                 "bing_search_v7_subscription_key": request.app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
                 "exa_api_key": request.app.state.config.EXA_API_KEY,
+                "perplexity_api_key": request.app.state.config.PERPLEXITY_API_KEY,
                 "result_count": request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
                 "concurrent_requests": request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
                 "trust_env": request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV,
@@ -880,7 +929,12 @@ def process_file(
             # Update the content in the file
             # Usage: /files/{file_id}/data/content/update
 
-            VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
+            try:
+                # /files/{file_id}/data/content/update
+                VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
+            except:
+                # Audio file upload pipeline
+                pass
 
             docs = [
                 Document(
@@ -937,6 +991,8 @@ def process_file(
                     engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE,
                     TIKA_SERVER_URL=request.app.state.config.TIKA_SERVER_URL,
                     PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES,
+                    DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
+                    DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
                 )
                 docs = loader.load(
                     file.filename, file.meta.get("content_type"), file_path
@@ -979,36 +1035,45 @@ def process_file(
         hash = calculate_sha256_string(text_content)
         Files.update_file_hash_by_id(file.id, hash)
 
-        try:
+        if not request.app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL:
-            result = save_docs_to_vector_db(
+            try:
-                request,
+                result = save_docs_to_vector_db(
-                docs=docs,
+                    request,
-                collection_name=collection_name,
+                    docs=docs,
-                metadata={
+                    collection_name=collection_name,
-                    "file_id": file.id,
+                    metadata={
-                    "name": file.filename,
+                        "file_id": file.id,
-                    "hash": hash,
+                        "name": file.filename,
-                },
+                        "hash": hash,
-                add=(True if form_data.collection_name else False),
-                user=user,
-            )
-
-            if result:
-                Files.update_file_metadata_by_id(
-                    file.id,
-                    {
-                        "collection_name": collection_name,
                     },
+                    add=(True if form_data.collection_name else False),
+                    user=user,
                 )
 
-                return {
+                if result:
-                    "status": True,
+                    Files.update_file_metadata_by_id(
-                    "collection_name": collection_name,
+                        file.id,
-                    "filename": file.filename,
+                        {
-                    "content": text_content,
+                            "collection_name": collection_name,
-                }
+                        },
-        except Exception as e:
+                    )
-            raise e
+
+                    return {
+                        "status": True,
+                        "collection_name": collection_name,
+                        "filename": file.filename,
+                        "content": text_content,
+                    }
+            except Exception as e:
+                raise e
+        else:
+            return {
+                "status": True,
+                "collection_name": None,
+                "filename": file.filename,
+                "content": text_content,
+            }
+
     except Exception as e:
         log.exception(e)
         if "No pandoc was found" in str(e):
@@ -1124,9 +1189,13 @@ def process_web(
         content = " ".join([doc.page_content for doc in docs])
 
         log.debug(f"text_content: {content}")
-        save_docs_to_vector_db(
+
-            request, docs, collection_name, overwrite=True, user=user
+        if not request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL:
-        )
+            save_docs_to_vector_db(
+                request, docs, collection_name, overwrite=True, user=user
+            )
+        else:
+            collection_name = None
 
         return {
             "status": True,
@@ -1138,6 +1207,7 @@ def process_web(
                 },
                 "meta": {
                     "name": form_data.url,
+                    "source": form_data.url,
                 },
             },
         }
@@ -1163,6 +1233,7 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
     - SERPLY_API_KEY
     - TAVILY_API_KEY
     - EXA_API_KEY
+    - PERPLEXITY_API_KEY
     - SEARCHAPI_API_KEY + SEARCHAPI_ENGINE (by default `google`)
     - SERPAPI_API_KEY + SERPAPI_ENGINE (by default `google`)
     Args:
@@ -1327,6 +1398,13 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
             request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
             request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
         )
+    elif engine == "perplexity":
+        return search_perplexity(
+            request.app.state.config.PERPLEXITY_API_KEY,
+            query,
+            request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
+            request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
+        )
     else:
         raise Exception("No search engine API key found in environment variables")
 
@@ -1368,9 +1446,11 @@ async def process_web_search(
         )
         docs = await loader.aload()
 
-        if request.app.state.config.RAG_WEB_SEARCH_FULL_CONTEXT:
+        if request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL:
             return {
                 "status": True,
+                "collection_name": None,
+                "filenames": urls,
                 "docs": [
                     {
                         "content": doc.page_content,
@@ -1378,7 +1458,6 @@ async def process_web_search(
                     }
                     for doc in docs
                 ],
-                "filenames": urls,
                 "loaded_count": len(docs),
             }
         else:
@@ -1553,11 +1632,11 @@ def reset_upload_dir(user=Depends(get_admin_user)) -> bool:
                     elif os.path.isdir(file_path):
                         shutil.rmtree(file_path)  # Remove the directory
                 except Exception as e:
-                    print(f"Failed to delete {file_path}. Reason: {e}")
+                    log.exception(f"Failed to delete {file_path}. Reason: {e}")
         else:
-            print(f"The directory {folder} does not exist")
+            log.warning(f"The directory {folder} does not exist")
     except Exception as e:
-        print(f"Failed to process the directory {folder}. Reason: {e}")
+        log.exception(f"Failed to process the directory {folder}. Reason: {e}")
     return True
 
 

backend/open_webui/routers/tasks.py

@@ -20,6 +20,10 @@ from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.constants import TASKS
 
 from open_webui.routers.pipelines import process_pipeline_inlet_filter
+from open_webui.utils.filter import (
+    get_sorted_filter_ids,
+    process_filter_functions,
+)
 from open_webui.utils.task import get_task_model_id
 
 from open_webui.config import (
@@ -221,6 +225,12 @@ async def generate_title(
         },
     }
 
+    # Process the payload through the pipeline
+    try:
+        payload = await process_pipeline_inlet_filter(request, payload, user, models)
+    except Exception as e:
+        raise e
+
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
@@ -290,6 +300,12 @@ async def generate_chat_tags(
         },
     }
 
+    # Process the payload through the pipeline
+    try:
+        payload = await process_pipeline_inlet_filter(request, payload, user, models)
+    except Exception as e:
+        raise e
+
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
@@ -356,6 +372,12 @@ async def generate_image_prompt(
         },
     }
 
+    # Process the payload through the pipeline
+    try:
+        payload = await process_pipeline_inlet_filter(request, payload, user, models)
+    except Exception as e:
+        raise e
+
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
@@ -433,6 +455,12 @@ async def generate_queries(
         },
     }
 
+    # Process the payload through the pipeline
+    try:
+        payload = await process_pipeline_inlet_filter(request, payload, user, models)
+    except Exception as e:
+        raise e
+
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
@@ -514,6 +542,12 @@ async def generate_autocompletion(
         },
     }
 
+    # Process the payload through the pipeline
+    try:
+        payload = await process_pipeline_inlet_filter(request, payload, user, models)
+    except Exception as e:
+        raise e
+
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
@@ -584,6 +618,12 @@ async def generate_emoji(
         },
     }
 
+    # Process the payload through the pipeline
+    try:
+        payload = await process_pipeline_inlet_filter(request, payload, user, models)
+    except Exception as e:
+        raise e
+
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
@@ -644,6 +684,12 @@ async def generate_moa_response(
         },
     }
 
+    # Process the payload through the pipeline
+    try:
+        payload = await process_pipeline_inlet_filter(request, payload, user, models)
+    except Exception as e:
+        raise e
+
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:

backend/open_webui/routers/tools.py

@@ -1,3 +1,4 @@
+import logging
 from pathlib import Path
 from typing import Optional
 
@@ -15,6 +16,10 @@ from fastapi import APIRouter, Depends, HTTPException, Request, status
 from open_webui.utils.tools import get_tools_specs
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.utils.access_control import has_access, has_permission
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 router = APIRouter()
@@ -100,7 +105,7 @@ async def create_new_tools(
             specs = get_tools_specs(TOOLS[form_data.id])
             tools = Tools.insert_new_tool(user.id, form_data, specs)
 
-            tool_cache_dir = Path(CACHE_DIR) / "tools" / form_data.id
+            tool_cache_dir = CACHE_DIR / "tools" / form_data.id
             tool_cache_dir.mkdir(parents=True, exist_ok=True)
 
             if tools:
@@ -111,7 +116,7 @@ async def create_new_tools(
                     detail=ERROR_MESSAGES.DEFAULT("Error creating tools"),
                 )
         except Exception as e:
-            print(e)
+            log.exception(f"Failed to load the tool by id {form_data.id}: {e}")
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
                 detail=ERROR_MESSAGES.DEFAULT(str(e)),
@@ -193,7 +198,7 @@ async def update_tools_by_id(
             "specs": specs,
         }
 
-        print(updated)
+        log.debug(updated)
         tools = Tools.update_tool_by_id(id, updated)
 
         if tools:
@@ -343,7 +348,7 @@ async def update_tools_valves_by_id(
         Tools.update_tool_valves_by_id(id, valves.model_dump())
         return valves.model_dump()
     except Exception as e:
-        print(e)
+        log.exception(f"Failed to update tool valves by id {id}: {e}")
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(str(e)),
@@ -421,7 +426,7 @@ async def update_tools_user_valves_by_id(
                 )
                 return user_valves.model_dump()
             except Exception as e:
-                print(e)
+                log.exception(f"Failed to update user valves by id {id}: {e}")
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
                     detail=ERROR_MESSAGES.DEFAULT(str(e)),

backend/open_webui/routers/utils.py

@@ -1,4 +1,5 @@
 import black
+import logging
 import markdown
 
 from open_webui.models.chats import ChatTitleMessagesForm
@@ -13,8 +14,12 @@ from open_webui.utils.misc import get_gravatar_url
 from open_webui.utils.pdf_generator import PDFGenerator
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.utils.code_interpreter import execute_code_jupyter
+from open_webui.env import SRC_LOG_LEVELS
 
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
+
 router = APIRouter()
 
 
@@ -96,7 +101,7 @@ async def download_chat_as_pdf(
             headers={"Content-Disposition": "attachment;filename=chat.pdf"},
         )
     except Exception as e:
-        print(e)
+        log.exception(f"Error generating PDF: {e}")
         raise HTTPException(status_code=400, detail=str(e))
 
 

backend/open_webui/socket/main.py

@@ -12,6 +12,7 @@ from open_webui.env import (
     ENABLE_WEBSOCKET_SUPPORT,
     WEBSOCKET_MANAGER,
     WEBSOCKET_REDIS_URL,
+    WEBSOCKET_REDIS_LOCK_TIMEOUT,
 )
 from open_webui.utils.auth import decode_token
 from open_webui.socket.utils import RedisDict, RedisLock
@@ -61,7 +62,7 @@ if WEBSOCKET_MANAGER == "redis":
     clean_up_lock = RedisLock(
         redis_url=WEBSOCKET_REDIS_URL,
         lock_name="usage_cleanup_lock",
-        timeout_secs=TIMEOUT_DURATION * 2,
+        timeout_secs=WEBSOCKET_REDIS_LOCK_TIMEOUT,
     )
     aquire_func = clean_up_lock.aquire_lock
     renew_func = clean_up_lock.renew_lock

backend/open_webui/static/site.webmanifest

@@ -3,13 +3,13 @@
   "short_name": "WebUI",
   "icons": [
     {
-      "src": "/favicon/web-app-manifest-192x192.png",
+      "src": "/static/web-app-manifest-192x192.png",
       "sizes": "192x192",
       "type": "image/png",
       "purpose": "maskable"
     },
     {
-      "src": "/favicon/web-app-manifest-512x512.png",
+      "src": "/static/web-app-manifest-512x512.png",
       "sizes": "512x512",
       "type": "image/png",
       "purpose": "maskable"

backend/open_webui/storage/provider.py

@@ -1,10 +1,12 @@
 import os
 import shutil
 import json
+import logging
 from abc import ABC, abstractmethod
 from typing import BinaryIO, Tuple
 
 import boto3
+from botocore.config import Config
 from botocore.exceptions import ClientError
 from open_webui.config import (
     S3_ACCESS_KEY_ID,
@@ -13,6 +15,8 @@ from open_webui.config import (
     S3_KEY_PREFIX,
     S3_REGION_NAME,
     S3_SECRET_ACCESS_KEY,
+    S3_USE_ACCELERATE_ENDPOINT,
+    S3_ADDRESSING_STYLE,
     GCS_BUCKET_NAME,
     GOOGLE_APPLICATION_CREDENTIALS_JSON,
     AZURE_STORAGE_ENDPOINT,
@@ -27,6 +31,11 @@ from open_webui.constants import ERROR_MESSAGES
 from azure.identity import DefaultAzureCredential
 from azure.storage.blob import BlobServiceClient
 from azure.core.exceptions import ResourceNotFoundError
+from open_webui.env import SRC_LOG_LEVELS
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 class StorageProvider(ABC):
@@ -71,7 +80,7 @@ class LocalStorageProvider(StorageProvider):
         if os.path.isfile(file_path):
             os.remove(file_path)
         else:
-            print(f"File {file_path} not found in local storage.")
+            log.warning(f"File {file_path} not found in local storage.")
 
     @staticmethod
     def delete_all_files() -> None:
@@ -85,20 +94,40 @@ class LocalStorageProvider(StorageProvider):
                     elif os.path.isdir(file_path):
                         shutil.rmtree(file_path)  # Remove the directory
                 except Exception as e:
-                    print(f"Failed to delete {file_path}. Reason: {e}")
+                    log.exception(f"Failed to delete {file_path}. Reason: {e}")
         else:
-            print(f"Directory {UPLOAD_DIR} not found in local storage.")
+            log.warning(f"Directory {UPLOAD_DIR} not found in local storage.")
 
 
 class S3StorageProvider(StorageProvider):
     def __init__(self):
-        self.s3_client = boto3.client(
+        config = Config(
-            "s3",
+            s3={
-            region_name=S3_REGION_NAME,
+                "use_accelerate_endpoint": S3_USE_ACCELERATE_ENDPOINT,
-            endpoint_url=S3_ENDPOINT_URL,
+                "addressing_style": S3_ADDRESSING_STYLE,
-            aws_access_key_id=S3_ACCESS_KEY_ID,
+            },
-            aws_secret_access_key=S3_SECRET_ACCESS_KEY,
         )
+
+        # If access key and secret are provided, use them for authentication
+        if S3_ACCESS_KEY_ID and S3_SECRET_ACCESS_KEY:
+            self.s3_client = boto3.client(
+                "s3",
+                region_name=S3_REGION_NAME,
+                endpoint_url=S3_ENDPOINT_URL,
+                aws_access_key_id=S3_ACCESS_KEY_ID,
+                aws_secret_access_key=S3_SECRET_ACCESS_KEY,
+                config=config,
+            )
+        else:
+            # If no explicit credentials are provided, fall back to default AWS credentials
+            # This supports workload identity (IAM roles for EC2, EKS, etc.)
+            self.s3_client = boto3.client(
+                "s3",
+                region_name=S3_REGION_NAME,
+                endpoint_url=S3_ENDPOINT_URL,
+                config=config,
+            )
+
         self.bucket_name = S3_BUCKET_NAME
         self.key_prefix = S3_KEY_PREFIX if S3_KEY_PREFIX else ""
 

backend/open_webui/test/apps/webui/storage/test_provider.py

@@ -187,6 +187,17 @@ class TestS3StorageProvider:
         assert not (upload_dir / self.filename).exists()
         assert not (upload_dir / self.filename_extra).exists()
 
+    def test_init_without_credentials(self, monkeypatch):
+        """Test that S3StorageProvider can initialize without explicit credentials."""
+        # Temporarily unset the environment variables
+        monkeypatch.setattr(provider, "S3_ACCESS_KEY_ID", None)
+        monkeypatch.setattr(provider, "S3_SECRET_ACCESS_KEY", None)
+
+        # Should not raise an exception
+        storage = provider.S3StorageProvider()
+        assert storage.s3_client is not None
+        assert storage.bucket_name == provider.S3_BUCKET_NAME
+
 
 class TestGCSStorageProvider:
     Storage = provider.GCSStorageProvider()

backend/open_webui/utils/audit.py

@@ -0,0 +1,249 @@
+from contextlib import asynccontextmanager
+from dataclasses import asdict, dataclass
+from enum import Enum
+import re
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    AsyncGenerator,
+    Dict,
+    MutableMapping,
+    Optional,
+    cast,
+)
+import uuid
+
+from asgiref.typing import (
+    ASGI3Application,
+    ASGIReceiveCallable,
+    ASGIReceiveEvent,
+    ASGISendCallable,
+    ASGISendEvent,
+    Scope as ASGIScope,
+)
+from loguru import logger
+from starlette.requests import Request
+
+from open_webui.env import AUDIT_LOG_LEVEL, MAX_BODY_LOG_SIZE
+from open_webui.utils.auth import get_current_user, get_http_authorization_cred
+from open_webui.models.users import UserModel
+
+
+if TYPE_CHECKING:
+    from loguru import Logger
+
+
+@dataclass(frozen=True)
+class AuditLogEntry:
+    # `Metadata` audit level properties
+    id: str
+    user: dict[str, Any]
+    audit_level: str
+    verb: str
+    request_uri: str
+    user_agent: Optional[str] = None
+    source_ip: Optional[str] = None
+    # `Request` audit level properties
+    request_object: Any = None
+    # `Request Response` level
+    response_object: Any = None
+    response_status_code: Optional[int] = None
+
+
+class AuditLevel(str, Enum):
+    NONE = "NONE"
+    METADATA = "METADATA"
+    REQUEST = "REQUEST"
+    REQUEST_RESPONSE = "REQUEST_RESPONSE"
+
+
+class AuditLogger:
+    """
+    A helper class that encapsulates audit logging functionality. It uses Loguru’s logger with an auditable binding to ensure that audit log entries are filtered correctly.
+
+    Parameters:
+    logger (Logger): An instance of Loguru’s logger.
+    """
+
+    def __init__(self, logger: "Logger"):
+        self.logger = logger.bind(auditable=True)
+
+    def write(
+        self,
+        audit_entry: AuditLogEntry,
+        *,
+        log_level: str = "INFO",
+        extra: Optional[dict] = None,
+    ):
+
+        entry = asdict(audit_entry)
+
+        if extra:
+            entry["extra"] = extra
+
+        self.logger.log(
+            log_level,
+            "",
+            **entry,
+        )
+
+
+class AuditContext:
+    """
+    Captures and aggregates the HTTP request and response bodies during the processing of a request. It ensures that only a configurable maximum amount of data is stored to prevent excessive memory usage.
+
+    Attributes:
+    request_body (bytearray): Accumulated request payload.
+    response_body (bytearray): Accumulated response payload.
+    max_body_size (int): Maximum number of bytes to capture.
+    metadata (Dict[str, Any]): A dictionary to store additional audit metadata (user, http verb, user agent, etc.).
+    """
+
+    def __init__(self, max_body_size: int = MAX_BODY_LOG_SIZE):
+        self.request_body = bytearray()
+        self.response_body = bytearray()
+        self.max_body_size = max_body_size
+        self.metadata: Dict[str, Any] = {}
+
+    def add_request_chunk(self, chunk: bytes):
+        if len(self.request_body) < self.max_body_size:
+            self.request_body.extend(
+                chunk[: self.max_body_size - len(self.request_body)]
+            )
+
+    def add_response_chunk(self, chunk: bytes):
+        if len(self.response_body) < self.max_body_size:
+            self.response_body.extend(
+                chunk[: self.max_body_size - len(self.response_body)]
+            )
+
+
+class AuditLoggingMiddleware:
+    """
+    ASGI middleware that intercepts HTTP requests and responses to perform audit logging. It captures request/response bodies (depending on audit level), headers, HTTP methods, and user information, then logs a structured audit entry at the end of the request cycle.
+    """
+
+    AUDITED_METHODS = {"PUT", "PATCH", "DELETE", "POST"}
+
+    def __init__(
+        self,
+        app: ASGI3Application,
+        *,
+        excluded_paths: Optional[list[str]] = None,
+        max_body_size: int = MAX_BODY_LOG_SIZE,
+        audit_level: AuditLevel = AuditLevel.NONE,
+    ) -> None:
+        self.app = app
+        self.audit_logger = AuditLogger(logger)
+        self.excluded_paths = excluded_paths or []
+        self.max_body_size = max_body_size
+        self.audit_level = audit_level
+
+    async def __call__(
+        self,
+        scope: ASGIScope,
+        receive: ASGIReceiveCallable,
+        send: ASGISendCallable,
+    ) -> None:
+        if scope["type"] != "http":
+            return await self.app(scope, receive, send)
+
+        request = Request(scope=cast(MutableMapping, scope))
+
+        if self._should_skip_auditing(request):
+            return await self.app(scope, receive, send)
+
+        async with self._audit_context(request) as context:
+
+            async def send_wrapper(message: ASGISendEvent) -> None:
+                if self.audit_level == AuditLevel.REQUEST_RESPONSE:
+                    await self._capture_response(message, context)
+
+                await send(message)
+
+            original_receive = receive
+
+            async def receive_wrapper() -> ASGIReceiveEvent:
+                nonlocal original_receive
+                message = await original_receive()
+
+                if self.audit_level in (
+                    AuditLevel.REQUEST,
+                    AuditLevel.REQUEST_RESPONSE,
+                ):
+                    await self._capture_request(message, context)
+
+                return message
+
+            await self.app(scope, receive_wrapper, send_wrapper)
+
+    @asynccontextmanager
+    async def _audit_context(
+        self, request: Request
+    ) -> AsyncGenerator[AuditContext, None]:
+        """
+        async context manager that ensures that an audit log entry is recorded after the request is processed.
+        """
+        context = AuditContext()
+        try:
+            yield context
+        finally:
+            await self._log_audit_entry(request, context)
+
+    async def _get_authenticated_user(self, request: Request) -> UserModel:
+
+        auth_header = request.headers.get("Authorization")
+        assert auth_header
+        user = get_current_user(request, None, get_http_authorization_cred(auth_header))
+
+        return user
+
+    def _should_skip_auditing(self, request: Request) -> bool:
+        if (
+            request.method not in {"POST", "PUT", "PATCH", "DELETE"}
+            or AUDIT_LOG_LEVEL == "NONE"
+            or not request.headers.get("authorization")
+        ):
+            return True
+        # match either /api/<resource>/...(for the endpoint /api/chat case) or /api/v1/<resource>/...
+        pattern = re.compile(
+            r"^/api(?:/v1)?/(" + "|".join(self.excluded_paths) + r")\b"
+        )
+        if pattern.match(request.url.path):
+            return True
+
+        return False
+
+    async def _capture_request(self, message: ASGIReceiveEvent, context: AuditContext):
+        if message["type"] == "http.request":
+            body = message.get("body", b"")
+            context.add_request_chunk(body)
+
+    async def _capture_response(self, message: ASGISendEvent, context: AuditContext):
+        if message["type"] == "http.response.start":
+            context.metadata["response_status_code"] = message["status"]
+
+        elif message["type"] == "http.response.body":
+            body = message.get("body", b"")
+            context.add_response_chunk(body)
+
+    async def _log_audit_entry(self, request: Request, context: AuditContext):
+        try:
+            user = await self._get_authenticated_user(request)
+
+            entry = AuditLogEntry(
+                id=str(uuid.uuid4()),
+                user=user.model_dump(include={"id", "name", "email", "role"}),
+                audit_level=self.audit_level.value,
+                verb=request.method,
+                request_uri=str(request.url),
+                response_status_code=context.metadata.get("response_status_code", None),
+                source_ip=request.client.host if request.client else None,
+                user_agent=request.headers.get("user-agent"),
+                request_object=context.request_body.decode("utf-8", errors="replace"),
+                response_object=context.response_body.decode("utf-8", errors="replace"),
+            )
+
+            self.audit_logger.write(entry)
+        except Exception as e:
+            logger.error(f"Failed to log audit entry: {str(e)}")

backend/open_webui/utils/auth.py

@@ -14,14 +14,22 @@ from typing import Optional, Union, List, Dict
 from open_webui.models.users import Users
 
 from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import WEBUI_SECRET_KEY, TRUSTED_SIGNATURE_KEY, STATIC_DIR
+from open_webui.env import (
+    WEBUI_SECRET_KEY,
+    TRUSTED_SIGNATURE_KEY,
+    STATIC_DIR,
+    SRC_LOG_LEVELS,
+)
 
-from fastapi import Depends, HTTPException, Request, Response, status
+from fastapi import BackgroundTasks, Depends, HTTPException, Request, Response, status
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
 from passlib.context import CryptContext
 
+
 logging.getLogger("passlib").setLevel(logging.ERROR)
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["OAUTH"])
 
 SESSION_SECRET = WEBUI_SECRET_KEY
 ALGORITHM = "HS256"
@@ -50,7 +58,7 @@ def verify_signature(payload: str, signature: str) -> bool:
 def override_static(path: str, content: str):
     # Ensure path is safe
     if "/" in path or ".." in path:
-        print(f"Invalid path: {path}")
+        log.error(f"Invalid path: {path}")
         return
 
     file_path = os.path.join(STATIC_DIR, path)
@@ -64,7 +72,7 @@ def get_license_data(app, key):
     if key:
         try:
             res = requests.post(
-                "https://api.openwebui.com/api/v1/license",
+                "https://api.openwebui.com/api/v1/license/",
                 json={"key": key, "version": "1"},
                 timeout=5,
             )
@@ -75,18 +83,19 @@ def get_license_data(app, key):
                     if k == "resources":
                         for p, c in v.items():
                             globals().get("override_static", lambda a, b: None)(p, c)
-                    elif k == "user_count":
+                    elif k == "count":
                         setattr(app.state, "USER_COUNT", v)
-                    elif k == "webui_name":
+                    elif k == "name":
                         setattr(app.state, "WEBUI_NAME", v)
-
+                    elif k == "metadata":
+                        setattr(app.state, "LICENSE_METADATA", v)
                 return True
             else:
-                print(
+                log.error(
                     f"License: retrieval issue: {getattr(res, 'text', 'unknown error')}"
                 )
         except Exception as ex:
-            print(f"License: Uncaught Exception: {ex}")
+            log.exception(f"License: Uncaught Exception: {ex}")
     return False
 
 
@@ -142,6 +151,7 @@ def get_http_authorization_cred(auth_header: str):
 
 def get_current_user(
     request: Request,
+    background_tasks: BackgroundTasks,
     auth_token: HTTPAuthorizationCredentials = Depends(bearer_security),
 ):
     token = None
@@ -194,7 +204,10 @@ def get_current_user(
                 detail=ERROR_MESSAGES.INVALID_TOKEN,
             )
         else:
-            Users.update_user_last_active_by_id(user.id)
+            # Refresh the user's last active timestamp asynchronously
+            # to prevent blocking the request
+            if background_tasks:
+                background_tasks.add_task(Users.update_user_last_active_by_id, user.id)
         return user
     else:
         raise HTTPException(

backend/open_webui/utils/chat.py

@@ -66,7 +66,7 @@ async def generate_direct_chat_completion(
     user: Any,
     models: dict,
 ):
-    print("generate_direct_chat_completion")
+    log.info("generate_direct_chat_completion")
 
     metadata = form_data.pop("metadata", {})
 
@@ -103,7 +103,7 @@ async def generate_direct_chat_completion(
             }
         )
 
-        print("res", res)
+        log.info(f"res: {res}")
 
         if res.get("status", False):
             # Define a generator to stream responses
@@ -149,7 +149,7 @@ async def generate_direct_chat_completion(
             }
         )
 
-        if "error" in res:
+        if "error" in res and res["error"]:
             raise Exception(res["error"])
 
         return res
@@ -285,7 +285,7 @@ chat_completion = generate_chat_completion
 
 async def chat_completed(request: Request, form_data: dict, user: Any):
     if not request.app.state.MODELS:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
 
     if getattr(request.state, "direct", False) and hasattr(request.state, "model"):
         models = {
@@ -328,9 +328,14 @@ async def chat_completed(request: Request, form_data: dict, user: Any):
     }
 
     try:
+        filter_functions = [
+            Functions.get_function_by_id(filter_id)
+            for filter_id in get_sorted_filter_ids(model)
+        ]
+
         result, _ = await process_filter_functions(
             request=request,
-            filter_ids=get_sorted_filter_ids(model),
+            filter_functions=filter_functions,
             filter_type="outlet",
             form_data=data,
             extra_params=extra_params,
@@ -351,7 +356,7 @@ async def chat_action(request: Request, action_id: str, form_data: dict, user: A
         raise Exception(f"Action not found: {action_id}")
 
     if not request.app.state.MODELS:
-        await get_all_models(request)
+        await get_all_models(request, user=user)
 
     if getattr(request.state, "direct", False) and hasattr(request.state, "model"):
         models = {
@@ -432,7 +437,7 @@ async def chat_action(request: Request, action_id: str, form_data: dict, user: A
                             )
                         )
                 except Exception as e:
-                    print(e)
+                    log.exception(f"Failed to get user values: {e}")
 
                 params = {**params, "__user__": __user__}
 

backend/open_webui/utils/code_interpreter.py

@@ -1,148 +1,210 @@
 import asyncio
 import json
+import logging
 import uuid
+from typing import Optional
+
+import aiohttp
 import websockets
-import requests
+from pydantic import BaseModel
-from urllib.parse import urljoin
+
+from open_webui.env import SRC_LOG_LEVELS
+
+logger = logging.getLogger(__name__)
+logger.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
-async def execute_code_jupyter(
+class ResultModel(BaseModel):
-    jupyter_url, code, token=None, password=None, timeout=10
-):
     """
-    Executes Python code in a Jupyter kernel.
+    Execute Code Result Model
-    Supports authentication with a token or password.
-    :param jupyter_url: Jupyter server URL (e.g., "http://localhost:8888")
-    :param code: Code to execute
-    :param token: Jupyter authentication token (optional)
-    :param password: Jupyter password (optional)
-    :param timeout: WebSocket timeout in seconds (default: 10s)
-    :return: Dictionary with stdout, stderr, and result
-             - Images are prefixed with "base64:image/png," and separated by newlines if multiple.
     """
-    session = requests.Session()  # Maintain cookies
-    headers = {}  # Headers for requests
 
-    # Authenticate using password
+    stdout: Optional[str] = ""
-    if password and not token:
+    stderr: Optional[str] = ""
+    result: Optional[str] = ""
+
+
+class JupyterCodeExecuter:
+    """
+    Execute code in jupyter notebook
+    """
+
+    def __init__(
+        self,
+        base_url: str,
+        code: str,
+        token: str = "",
+        password: str = "",
+        timeout: int = 60,
+    ):
+        """
+        :param base_url: Jupyter server URL (e.g., "http://localhost:8888")
+        :param code: Code to execute
+        :param token: Jupyter authentication token (optional)
+        :param password: Jupyter password (optional)
+        :param timeout: WebSocket timeout in seconds (default: 60s)
+        """
+        self.base_url = base_url.rstrip("/")
+        self.code = code
+        self.token = token
+        self.password = password
+        self.timeout = timeout
+        self.kernel_id = ""
+        self.session = aiohttp.ClientSession(base_url=self.base_url)
+        self.params = {}
+        self.result = ResultModel()
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        if self.kernel_id:
+            try:
+                async with self.session.delete(
+                    f"/api/kernels/{self.kernel_id}", params=self.params
+                ) as response:
+                    response.raise_for_status()
+            except Exception as err:
+                logger.exception("close kernel failed, %s", err)
+        await self.session.close()
+
+    async def run(self) -> ResultModel:
         try:
-            login_url = urljoin(jupyter_url, "/login")
+            await self.sign_in()
-            response = session.get(login_url)
+            await self.init_kernel()
+            await self.execute_code()
+        except Exception as err:
+            logger.exception("execute code failed, %s", err)
+            self.result.stderr = f"Error: {err}"
+        return self.result
+
+    async def sign_in(self) -> None:
+        # password authentication
+        if self.password and not self.token:
+            async with self.session.get("/login") as response:
+                response.raise_for_status()
+                xsrf_token = response.cookies["_xsrf"].value
+                if not xsrf_token:
+                    raise ValueError("_xsrf token not found")
+                self.session.cookie_jar.update_cookies(response.cookies)
+                self.session.headers.update({"X-XSRFToken": xsrf_token})
+            async with self.session.post(
+                "/login",
+                data={"_xsrf": xsrf_token, "password": self.password},
+                allow_redirects=False,
+            ) as response:
+                response.raise_for_status()
+                self.session.cookie_jar.update_cookies(response.cookies)
+
+        # token authentication
+        if self.token:
+            self.params.update({"token": self.token})
+
+    async def init_kernel(self) -> None:
+        async with self.session.post(
+            url="/api/kernels", params=self.params
+        ) as response:
             response.raise_for_status()
-            xsrf_token = session.cookies.get("_xsrf")
+            kernel_data = await response.json()
-            if not xsrf_token:
+            self.kernel_id = kernel_data["id"]
-                raise ValueError("Failed to fetch _xsrf token")
-
-            login_data = {"_xsrf": xsrf_token, "password": password}
-            login_response = session.post(
-                login_url, data=login_data, cookies=session.cookies
-            )
-            login_response.raise_for_status()
-            headers["X-XSRFToken"] = xsrf_token
-        except Exception as e:
-            return {
-                "stdout": "",
-                "stderr": f"Authentication Error: {str(e)}",
-                "result": "",
-            }
-
-    # Construct API URLs with authentication token if provided
-    params = f"?token={token}" if token else ""
-    kernel_url = urljoin(jupyter_url, f"/api/kernels{params}")
-
-    try:
-        response = session.post(kernel_url, headers=headers, cookies=session.cookies)
-        response.raise_for_status()
-        kernel_id = response.json()["id"]
-
-        websocket_url = urljoin(
-            jupyter_url.replace("http", "ws"),
-            f"/api/kernels/{kernel_id}/channels{params}",
-        )
 
+    def init_ws(self) -> (str, dict):
+        ws_base = self.base_url.replace("http", "ws")
+        ws_params = "?" + "&".join([f"{key}={val}" for key, val in self.params.items()])
+        websocket_url = f"{ws_base}/api/kernels/{self.kernel_id}/channels{ws_params if len(ws_params) > 1 else ''}"
         ws_headers = {}
-        if password and not token:
+        if self.password and not self.token:
-            ws_headers["X-XSRFToken"] = session.cookies.get("_xsrf")
+            ws_headers = {
-            cookies = {name: value for name, value in session.cookies.items()}
+                "Cookie": "; ".join(
-            ws_headers["Cookie"] = "; ".join(
+                    [
-                [f"{name}={value}" for name, value in cookies.items()]
+                        f"{cookie.key}={cookie.value}"
-            )
+                        for cookie in self.session.cookie_jar
+                    ]
+                ),
+                **self.session.headers,
+            }
+        return websocket_url, ws_headers
 
+    async def execute_code(self) -> None:
+        # initialize ws
+        websocket_url, ws_headers = self.init_ws()
+        # execute
         async with websockets.connect(
             websocket_url, additional_headers=ws_headers
         ) as ws:
-            msg_id = str(uuid.uuid4())
+            await self.execute_in_jupyter(ws)
-            execute_request = {
-                "header": {
-                    "msg_id": msg_id,
-                    "msg_type": "execute_request",
-                    "username": "user",
-                    "session": str(uuid.uuid4()),
-                    "date": "",
-                    "version": "5.3",
-                },
-                "parent_header": {},
-                "metadata": {},
-                "content": {
-                    "code": code,
-                    "silent": False,
-                    "store_history": True,
-                    "user_expressions": {},
-                    "allow_stdin": False,
-                    "stop_on_error": True,
-                },
-                "channel": "shell",
-            }
-            await ws.send(json.dumps(execute_request))
 
-            stdout, stderr, result = "", "", []
+    async def execute_in_jupyter(self, ws) -> None:
-
+        # send message
-            while True:
+        msg_id = uuid.uuid4().hex
-                try:
+        await ws.send(
-                    message = await asyncio.wait_for(ws.recv(), timeout)
+            json.dumps(
-                    message_data = json.loads(message)
+                {
-                    if message_data.get("parent_header", {}).get("msg_id") == msg_id:
+                    "header": {
-                        msg_type = message_data.get("msg_type")
+                        "msg_id": msg_id,
-
+                        "msg_type": "execute_request",
-                        if msg_type == "stream":
+                        "username": "user",
-                            if message_data["content"]["name"] == "stdout":
+                        "session": uuid.uuid4().hex,
-                                stdout += message_data["content"]["text"]
+                        "date": "",
-                            elif message_data["content"]["name"] == "stderr":
+                        "version": "5.3",
-                                stderr += message_data["content"]["text"]
+                    },
-
+                    "parent_header": {},
-                        elif msg_type in ("execute_result", "display_data"):
+                    "metadata": {},
-                            data = message_data["content"]["data"]
+                    "content": {
-                            if "image/png" in data:
+                        "code": self.code,
-                                result.append(
+                        "silent": False,
-                                    f"data:image/png;base64,{data['image/png']}"
+                        "store_history": True,
-                                )
+                        "user_expressions": {},
-                            elif "text/plain" in data:
+                        "allow_stdin": False,
-                                result.append(data["text/plain"])
+                        "stop_on_error": True,
-
+                    },
-                        elif msg_type == "error":
+                    "channel": "shell",
-                            stderr += "\n".join(message_data["content"]["traceback"])
+                }
-
+            )
-                        elif (
+        )
-                            msg_type == "status"
+        # parse message
-                            and message_data["content"]["execution_state"] == "idle"
+        stdout, stderr, result = "", "", []
-                        ):
+        while True:
+            try:
+                # wait for message
+                message = await asyncio.wait_for(ws.recv(), self.timeout)
+                message_data = json.loads(message)
+                # msg id not match, skip
+                if message_data.get("parent_header", {}).get("msg_id") != msg_id:
+                    continue
+                # check message type
+                msg_type = message_data.get("msg_type")
+                match msg_type:
+                    case "stream":
+                        if message_data["content"]["name"] == "stdout":
+                            stdout += message_data["content"]["text"]
+                        elif message_data["content"]["name"] == "stderr":
+                            stderr += message_data["content"]["text"]
+                    case "execute_result" | "display_data":
+                        data = message_data["content"]["data"]
+                        if "image/png" in data:
+                            result.append(f"data:image/png;base64,{data['image/png']}")
+                        elif "text/plain" in data:
+                            result.append(data["text/plain"])
+                    case "error":
+                        stderr += "\n".join(message_data["content"]["traceback"])
+                    case "status":
+                        if message_data["content"]["execution_state"] == "idle":
                             break
 
-                except asyncio.TimeoutError:
+            except asyncio.TimeoutError:
-                    stderr += "\nExecution timed out."
+                stderr += "\nExecution timed out."
-                    break
+                break
+        self.result.stdout = stdout.strip()
+        self.result.stderr = stderr.strip()
+        self.result.result = "\n".join(result).strip() if result else ""
 
-    except Exception as e:
-        return {"stdout": "", "stderr": f"Error: {str(e)}", "result": ""}
 
-    finally:
+async def execute_code_jupyter(
-        if kernel_id:
+    base_url: str, code: str, token: str = "", password: str = "", timeout: int = 60
-            requests.delete(
+) -> dict:
-                f"{kernel_url}/{kernel_id}", headers=headers, cookies=session.cookies
+    async with JupyterCodeExecuter(
-            )
+        base_url, code, token, password, timeout
-
+    ) as executor:
-    return {
+        result = await executor.run()
-        "stdout": stdout.strip(),
+        return result.model_dump()
-        "stderr": stderr.strip(),
-        "result": "\n".join(result).strip() if result else "",
-    }

backend/open_webui/utils/filter.py

@@ -1,9 +1,15 @@
 import inspect
+import logging
+
 from open_webui.utils.plugin import load_function_module_by_id
 from open_webui.models.functions import Functions
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
-def get_sorted_filter_ids(model):
+def get_sorted_filter_ids(model: dict):
     def get_priority(function_id):
         function = Functions.get_function_by_id(function_id)
         if function is not None and hasattr(function, "valves"):
@@ -27,12 +33,13 @@ def get_sorted_filter_ids(model):
 
 
 async def process_filter_functions(
-    request, filter_ids, filter_type, form_data, extra_params
+    request, filter_functions, filter_type, form_data, extra_params
 ):
     skip_files = None
 
-    for filter_id in filter_ids:
+    for function in filter_functions:
-        filter = Functions.get_function_by_id(filter_id)
+        filter = function
+        filter_id = function.id
         if not filter:
             continue
 
@@ -42,6 +49,11 @@ async def process_filter_functions(
             function_module, _, _ = load_function_module_by_id(filter_id)
             request.app.state.FUNCTIONS[filter_id] = function_module
 
+        # Prepare handler function
+        handler = getattr(function_module, filter_type, None)
+        if not handler:
+            continue
+
         # Check if the function has a file_handler variable
         if filter_type == "inlet" and hasattr(function_module, "file_handler"):
             skip_files = function_module.file_handler
@@ -53,15 +65,15 @@ async def process_filter_functions(
                 **(valves if valves else {})
             )
 
-        # Prepare handler function
-        handler = getattr(function_module, filter_type, None)
-        if not handler:
-            continue
-
         try:
             # Prepare parameters
             sig = inspect.signature(handler)
-            params = {"body": form_data} | {
+
+            params = {"body": form_data}
+            if filter_type == "stream":
+                params = {"event": form_data}
+
+            params = params | {
                 k: v
                 for k, v in {
                     **extra_params,
@@ -80,7 +92,7 @@ async def process_filter_functions(
                             )
                         )
                     except Exception as e:
-                        print(e)
+                        log.exception(f"Failed to get user values: {e}")
 
             # Execute handler
             if inspect.iscoroutinefunction(handler):
@@ -89,7 +101,7 @@ async def process_filter_functions(
                 form_data = handler(**params)
 
         except Exception as e:
-            print(f"Error in {filter_type} handler {filter_id}: {e}")
+            log.exception(f"Error in {filter_type} handler {filter_id}: {e}")
             raise e
 
     # Handle file cleanup for inlet

backend/open_webui/utils/logger.py

@@ -0,0 +1,140 @@
+import json
+import logging
+import sys
+from typing import TYPE_CHECKING
+
+from loguru import logger
+
+from open_webui.env import (
+    AUDIT_LOG_FILE_ROTATION_SIZE,
+    AUDIT_LOG_LEVEL,
+    AUDIT_LOGS_FILE_PATH,
+    GLOBAL_LOG_LEVEL,
+)
+
+
+if TYPE_CHECKING:
+    from loguru import Record
+
+
+def stdout_format(record: "Record") -> str:
+    """
+    Generates a formatted string for log records that are output to the console. This format includes a timestamp, log level, source location (module, function, and line), the log message, and any extra data (serialized as JSON).
+
+    Parameters:
+    record (Record): A Loguru record that contains logging details including time, level, name, function, line, message, and any extra context.
+    Returns:
+    str: A formatted log string intended for stdout.
+    """
+    record["extra"]["extra_json"] = json.dumps(record["extra"])
+    return (
+        "<green>{time:YYYY-MM-DD HH:mm:ss.SSS}</green> | "
+        "<level>{level: <8}</level> | "
+        "<cyan>{name}</cyan>:<cyan>{function}</cyan>:<cyan>{line}</cyan> - "
+        "<level>{message}</level> - {extra[extra_json]}"
+        "\n{exception}"
+    )
+
+
+class InterceptHandler(logging.Handler):
+    """
+    Intercepts log records from Python's standard logging module
+    and redirects them to Loguru's logger.
+    """
+
+    def emit(self, record):
+        """
+        Called by the standard logging module for each log event.
+        It transforms the standard `LogRecord` into a format compatible with Loguru
+        and passes it to Loguru's logger.
+        """
+        try:
+            level = logger.level(record.levelname).name
+        except ValueError:
+            level = record.levelno
+
+        frame, depth = sys._getframe(6), 6
+        while frame and frame.f_code.co_filename == logging.__file__:
+            frame = frame.f_back
+            depth += 1
+
+        logger.opt(depth=depth, exception=record.exc_info).log(
+            level, record.getMessage()
+        )
+
+
+def file_format(record: "Record"):
+    """
+    Formats audit log records into a structured JSON string for file output.
+
+    Parameters:
+    record (Record): A Loguru record containing extra audit data.
+    Returns:
+    str: A JSON-formatted string representing the audit data.
+    """
+
+    audit_data = {
+        "id": record["extra"].get("id", ""),
+        "timestamp": int(record["time"].timestamp()),
+        "user": record["extra"].get("user", dict()),
+        "audit_level": record["extra"].get("audit_level", ""),
+        "verb": record["extra"].get("verb", ""),
+        "request_uri": record["extra"].get("request_uri", ""),
+        "response_status_code": record["extra"].get("response_status_code", 0),
+        "source_ip": record["extra"].get("source_ip", ""),
+        "user_agent": record["extra"].get("user_agent", ""),
+        "request_object": record["extra"].get("request_object", b""),
+        "response_object": record["extra"].get("response_object", b""),
+        "extra": record["extra"].get("extra", {}),
+    }
+
+    record["extra"]["file_extra"] = json.dumps(audit_data, default=str)
+    return "{extra[file_extra]}\n"
+
+
+def start_logger():
+    """
+    Initializes and configures Loguru's logger with distinct handlers:
+
+    A console (stdout) handler for general log messages (excluding those marked as auditable).
+    An optional file handler for audit logs if audit logging is enabled.
+    Additionally, this function reconfigures Python’s standard logging to route through Loguru and adjusts logging levels for Uvicorn.
+
+    Parameters:
+    enable_audit_logging (bool): Determines whether audit-specific log entries should be recorded to file.
+    """
+    logger.remove()
+
+    logger.add(
+        sys.stdout,
+        level=GLOBAL_LOG_LEVEL,
+        format=stdout_format,
+        filter=lambda record: "auditable" not in record["extra"],
+    )
+
+    if AUDIT_LOG_LEVEL != "NONE":
+        try:
+            logger.add(
+                AUDIT_LOGS_FILE_PATH,
+                level="INFO",
+                rotation=AUDIT_LOG_FILE_ROTATION_SIZE,
+                compression="zip",
+                format=file_format,
+                filter=lambda record: record["extra"].get("auditable") is True,
+            )
+        except Exception as e:
+            logger.error(f"Failed to initialize audit log file handler: {str(e)}")
+
+    logging.basicConfig(
+        handlers=[InterceptHandler()], level=GLOBAL_LOG_LEVEL, force=True
+    )
+    for uvicorn_logger_name in ["uvicorn", "uvicorn.error"]:
+        uvicorn_logger = logging.getLogger(uvicorn_logger_name)
+        uvicorn_logger.setLevel(GLOBAL_LOG_LEVEL)
+        uvicorn_logger.handlers = []
+    for uvicorn_logger_name in ["uvicorn.access"]:
+        uvicorn_logger = logging.getLogger(uvicorn_logger_name)
+        uvicorn_logger.setLevel(GLOBAL_LOG_LEVEL)
+        uvicorn_logger.handlers = [InterceptHandler()]
+
+    logger.info(f"GLOBAL_LOG_LEVEL: {GLOBAL_LOG_LEVEL}")

backend/open_webui/utils/middleware.py

@@ -68,6 +68,7 @@ from open_webui.utils.misc import (
     get_last_user_message,
     get_last_assistant_message,
     prepend_to_first_user_message_content,
+    convert_logit_bias_input_to_json,
 )
 from open_webui.utils.tools import get_tools
 from open_webui.utils.plugin import load_function_module_by_id
@@ -351,24 +352,25 @@ async def chat_web_search_handler(
                 all_results.append(results)
                 files = form_data.get("files", [])
 
-                if request.app.state.config.RAG_WEB_SEARCH_FULL_CONTEXT:
+                if results.get("collection_name"):
-                    files.append(
-                        {
-                            "docs": results.get("docs", []),
-                            "name": searchQuery,
-                            "type": "web_search_docs",
-                            "urls": results["filenames"],
-                        }
-                    )
-                else:
                     files.append(
                         {
                             "collection_name": results["collection_name"],
                             "name": searchQuery,
-                            "type": "web_search_results",
+                            "type": "web_search",
                             "urls": results["filenames"],
                         }
                     )
+                elif results.get("docs"):
+                    files.append(
+                        {
+                            "docs": results.get("docs", []),
+                            "name": searchQuery,
+                            "type": "web_search",
+                            "urls": results["filenames"],
+                        }
+                    )
+
                 form_data["files"] = files
         except Exception as e:
             log.exception(e)
@@ -518,6 +520,7 @@ async def chat_completion_files_handler(
     sources = []
 
     if files := body.get("metadata", {}).get("files", None):
+        queries = []
         try:
             queries_response = await generate_queries(
                 request,
@@ -543,8 +546,8 @@ async def chat_completion_files_handler(
                 queries_response = {"queries": [queries_response]}
 
             queries = queries_response.get("queries", [])
-        except Exception as e:
+        except:
-            queries = []
+            pass
 
         if len(queries) == 0:
             queries = [get_last_user_message(body["messages"])]
@@ -556,6 +559,7 @@ async def chat_completion_files_handler(
                 sources = await loop.run_in_executor(
                     executor,
                     lambda: get_sources_from_files(
+                        request=request,
                         files=files,
                         queries=queries,
                         embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
@@ -607,11 +611,18 @@ def apply_params_to_form_data(form_data, model):
 
         if "reasoning_effort" in params:
             form_data["reasoning_effort"] = params["reasoning_effort"]
+        if "logit_bias" in params:
+            try:
+                form_data["logit_bias"] = json.loads(
+                    convert_logit_bias_input_to_json(params["logit_bias"])
+                )
+            except Exception as e:
+                print(f"Error parsing logit_bias: {e}")
 
     return form_data
 
 
-async def process_chat_payload(request, form_data, metadata, user, model):
+async def process_chat_payload(request, form_data, user, metadata, model):
 
     form_data = apply_params_to_form_data(form_data, model)
     log.debug(f"form_data: {form_data}")
@@ -704,9 +715,14 @@ async def process_chat_payload(request, form_data, metadata, user, model):
         raise e
 
     try:
+        filter_functions = [
+            Functions.get_function_by_id(filter_id)
+            for filter_id in get_sorted_filter_ids(model)
+        ]
+
         form_data, flags = await process_filter_functions(
             request=request,
-            filter_ids=get_sorted_filter_ids(model),
+            filter_functions=filter_functions,
             filter_type="inlet",
             form_data=form_data,
             extra_params=extra_params,
@@ -738,6 +754,7 @@ async def process_chat_payload(request, form_data, metadata, user, model):
 
     tool_ids = form_data.pop("tool_ids", None)
     files = form_data.pop("files", None)
+
     # Remove files duplicates
     if files:
         files = list({json.dumps(f, sort_keys=True): f for f in files}.values())
@@ -795,8 +812,6 @@ async def process_chat_payload(request, form_data, metadata, user, model):
     if len(sources) > 0:
         context_string = ""
         for source_idx, source in enumerate(sources):
-            source_id = source.get("source", {}).get("name", "")
-
             if "document" in source:
                 for doc_idx, doc_context in enumerate(source["document"]):
                     context_string += f"<source><source_id>{source_idx}</source_id><source_context>{doc_context}</source_context></source>\n"
@@ -854,7 +869,7 @@ async def process_chat_payload(request, form_data, metadata, user, model):
 
 
 async def process_chat_response(
-    request, response, form_data, user, events, metadata, tasks
+    request, response, form_data, user, metadata, model, events, tasks
 ):
     async def background_tasks_handler():
         message_map = Chats.get_messages_by_chat_id(metadata["chat_id"])
@@ -1048,6 +1063,26 @@ async def process_chat_response(
     ):
         return response
 
+    extra_params = {
+        "__event_emitter__": event_emitter,
+        "__event_call__": event_caller,
+        "__user__": {
+            "id": user.id,
+            "email": user.email,
+            "name": user.name,
+            "role": user.role,
+        },
+        "__metadata__": metadata,
+        "__request__": request,
+        "__model__": model,
+    }
+    filter_functions = [
+        Functions.get_function_by_id(filter_id)
+        for filter_id in get_sorted_filter_ids(model)
+    ]
+
+    print(f"{filter_functions=}")
+
     # Streaming response
     if event_emitter and event_caller:
         task_id = str(uuid4())  # Create a unique task ID.
@@ -1127,12 +1162,12 @@ async def process_chat_response(
 
                         if reasoning_duration is not None:
                             if raw:
-                                content = f'{content}\n<{block["tag"]}>{block["content"]}</{block["tag"]}>\n'
+                                content = f'{content}\n<{block["start_tag"]}>{block["content"]}<{block["end_tag"]}>\n'
                             else:
                                 content = f'{content}\n<details type="reasoning" done="true" duration="{reasoning_duration}">\n<summary>Thought for {reasoning_duration} seconds</summary>\n{reasoning_display_content}\n</details>\n'
                         else:
                             if raw:
-                                content = f'{content}\n<{block["tag"]}>{block["content"]}</{block["tag"]}>\n'
+                                content = f'{content}\n<{block["start_tag"]}>{block["content"]}<{block["end_tag"]}>\n'
                             else:
                                 content = f'{content}\n<details type="reasoning" done="false">\n<summary>Thinking…</summary>\n{reasoning_display_content}\n</details>\n'
 
@@ -1228,9 +1263,9 @@ async def process_chat_response(
                     return attributes
 
                 if content_blocks[-1]["type"] == "text":
-                    for tag in tags:
+                    for start_tag, end_tag in tags:
                         # Match start tag e.g., <tag> or <tag attr="value">
-                        start_tag_pattern = rf"<{tag}(\s.*?)?>"
+                        start_tag_pattern = rf"<{re.escape(start_tag)}(\s.*?)?>"
                         match = re.search(start_tag_pattern, content)
                         if match:
                             attr_content = (
@@ -1263,7 +1298,8 @@ async def process_chat_response(
                             content_blocks.append(
                                 {
                                     "type": content_type,
-                                    "tag": tag,
+                                    "start_tag": start_tag,
+                                    "end_tag": end_tag,
                                     "attributes": attributes,
                                     "content": "",
                                     "started_at": time.time(),
@@ -1275,9 +1311,10 @@ async def process_chat_response(
 
                             break
                 elif content_blocks[-1]["type"] == content_type:
-                    tag = content_blocks[-1]["tag"]
+                    start_tag = content_blocks[-1]["start_tag"]
+                    end_tag = content_blocks[-1]["end_tag"]
                     # Match end tag e.g., </tag>
-                    end_tag_pattern = rf"</{tag}>"
+                    end_tag_pattern = rf"<{re.escape(end_tag)}>"
 
                     # Check if the content has the end tag
                     if re.search(end_tag_pattern, content):
@@ -1285,7 +1322,7 @@ async def process_chat_response(
 
                         block_content = content_blocks[-1]["content"]
                         # Strip start and end tags from the content
-                        start_tag_pattern = rf"<{tag}(.*?)>"
+                        start_tag_pattern = rf"<{re.escape(start_tag)}(.*?)>"
                         block_content = re.sub(
                             start_tag_pattern, "", block_content
                         ).strip()
@@ -1350,7 +1387,7 @@ async def process_chat_response(
 
                         # Clean processed content
                         content = re.sub(
-                            rf"<{tag}(.*?)>(.|\n)*?</{tag}>",
+                            rf"<{re.escape(start_tag)}(.*?)>(.|\n)*?<{re.escape(end_tag)}>",
                             "",
                             content,
                             flags=re.DOTALL,
@@ -1388,19 +1425,24 @@ async def process_chat_response(
 
             # We might want to disable this by default
             DETECT_REASONING = True
+            DETECT_SOLUTION = True
             DETECT_CODE_INTERPRETER = metadata.get("features", {}).get(
                 "code_interpreter", False
             )
 
             reasoning_tags = [
-                "think",
+                ("think", "/think"),
-                "thinking",
+                ("thinking", "/thinking"),
-                "reason",
+                ("reason", "/reason"),
-                "reasoning",
+                ("reasoning", "/reasoning"),
-                "thought",
+                ("thought", "/thought"),
-                "Thought",
+                ("Thought", "/Thought"),
+                ("|begin_of_thought|", "|end_of_thought|"),
             ]
-            code_interpreter_tags = ["code_interpreter"]
+
+            code_interpreter_tags = [("code_interpreter", "/code_interpreter")]
+
+            solution_tags = [("|begin_of_solution|", "|end_of_solution|")]
 
             try:
                 for event in events:
@@ -1444,119 +1486,204 @@ async def process_chat_response(
                         try:
                             data = json.loads(data)
 
-                            if "selected_model_id" in data:
+                            data, _ = await process_filter_functions(
-                                model_id = data["selected_model_id"]
+                                request=request,
-                                Chats.upsert_message_to_chat_by_id_and_message_id(
+                                filter_functions=filter_functions,
-                                    metadata["chat_id"],
+                                filter_type="stream",
-                                    metadata["message_id"],
+                                form_data=data,
-                                    {
+                                extra_params=extra_params,
-                                        "selectedModelId": model_id,
+                            )
-                                    },
-                                )
-                            else:
-                                choices = data.get("choices", [])
-                                if not choices:
-                                    continue
 
-                                delta = choices[0].get("delta", {})
+                            if data:
-                                delta_tool_calls = delta.get("tool_calls", None)
+                                if "selected_model_id" in data:
-
+                                    model_id = data["selected_model_id"]
-                                if delta_tool_calls:
+                                    Chats.upsert_message_to_chat_by_id_and_message_id(
-                                    for delta_tool_call in delta_tool_calls:
+                                        metadata["chat_id"],
-                                        tool_call_index = delta_tool_call.get("index")
+                                        metadata["message_id"],
-
+                                        {
-                                        if tool_call_index is not None:
+                                            "selectedModelId": model_id,
-                                            if (
+                                        },
-                                                len(response_tool_calls)
-                                                <= tool_call_index
-                                            ):
-                                                response_tool_calls.append(
-                                                    delta_tool_call
-                                                )
-                                            else:
-                                                delta_name = delta_tool_call.get(
-                                                    "function", {}
-                                                ).get("name")
-                                                delta_arguments = delta_tool_call.get(
-                                                    "function", {}
-                                                ).get("arguments")
-
-                                                if delta_name:
-                                                    response_tool_calls[
-                                                        tool_call_index
-                                                    ]["function"]["name"] += delta_name
-
-                                                if delta_arguments:
-                                                    response_tool_calls[
-                                                        tool_call_index
-                                                    ]["function"][
-                                                        "arguments"
-                                                    ] += delta_arguments
-
-                                value = delta.get("content")
-
-                                if value:
-                                    content = f"{content}{value}"
-
-                                    if not content_blocks:
-                                        content_blocks.append(
-                                            {
-                                                "type": "text",
-                                                "content": "",
-                                            }
-                                        )
-
-                                    content_blocks[-1]["content"] = (
-                                        content_blocks[-1]["content"] + value
                                     )
-
+                                else:
-                                    if DETECT_REASONING:
+                                    choices = data.get("choices", [])
-                                        content, content_blocks, _ = (
+                                    if not choices:
-                                            tag_content_handler(
+                                        usage = data.get("usage", {})
-                                                "reasoning",
+                                        if usage:
-                                                reasoning_tags,
+                                            await event_emitter(
-                                                content,
+                                                {
-                                                content_blocks,
+                                                    "type": "chat:completion",
+                                                    "data": {
+                                                        "usage": usage,
+                                                    },
+                                                }
                                             )
-                                        )
+                                        continue
 
-                                    if DETECT_CODE_INTERPRETER:
+                                    delta = choices[0].get("delta", {})
-                                        content, content_blocks, end = (
+                                    delta_tool_calls = delta.get("tool_calls", None)
-                                            tag_content_handler(
+
-                                                "code_interpreter",
+                                    if delta_tool_calls:
-                                                code_interpreter_tags,
+                                        for delta_tool_call in delta_tool_calls:
-                                                content,
+                                            tool_call_index = delta_tool_call.get(
-                                                content_blocks,
+                                                "index"
                                             )
-                                        )
 
-                                        if end:
+                                            if tool_call_index is not None:
-                                            break
+                                                if (
+                                                    len(response_tool_calls)
+                                                    <= tool_call_index
+                                                ):
+                                                    response_tool_calls.append(
+                                                        delta_tool_call
+                                                    )
+                                                else:
+                                                    delta_name = delta_tool_call.get(
+                                                        "function", {}
+                                                    ).get("name")
+                                                    delta_arguments = (
+                                                        delta_tool_call.get(
+                                                            "function", {}
+                                                        ).get("arguments")
+                                                    )
+
+                                                    if delta_name:
+                                                        response_tool_calls[
+                                                            tool_call_index
+                                                        ]["function"][
+                                                            "name"
+                                                        ] += delta_name
+
+                                                    if delta_arguments:
+                                                        response_tool_calls[
+                                                            tool_call_index
+                                                        ]["function"][
+                                                            "arguments"
+                                                        ] += delta_arguments
+
+                                    value = delta.get("content")
+
+                                    reasoning_content = delta.get("reasoning_content")
+                                    if reasoning_content:
+                                        if (
+                                            not content_blocks
+                                            or content_blocks[-1]["type"] != "reasoning"
+                                        ):
+                                            reasoning_block = {
+                                                "type": "reasoning",
+                                                "start_tag": "think",
+                                                "end_tag": "/think",
+                                                "attributes": {
+                                                    "type": "reasoning_content"
+                                                },
+                                                "content": "",
+                                                "started_at": time.time(),
+                                            }
+                                            content_blocks.append(reasoning_block)
+                                        else:
+                                            reasoning_block = content_blocks[-1]
+
+                                        reasoning_block["content"] += reasoning_content
 
-                                    if ENABLE_REALTIME_CHAT_SAVE:
-                                        # Save message in the database
-                                        Chats.upsert_message_to_chat_by_id_and_message_id(
-                                            metadata["chat_id"],
-                                            metadata["message_id"],
-                                            {
-                                                "content": serialize_content_blocks(
-                                                    content_blocks
-                                                ),
-                                            },
-                                        )
-                                    else:
                                         data = {
                                             "content": serialize_content_blocks(
                                                 content_blocks
-                                            ),
+                                            )
                                         }
 
-                            await event_emitter(
+                                    if value:
-                                {
+                                        if (
-                                    "type": "chat:completion",
+                                            content_blocks
-                                    "data": data,
+                                            and content_blocks[-1]["type"]
-                                }
+                                            == "reasoning"
-                            )
+                                            and content_blocks[-1]
+                                            .get("attributes", {})
+                                            .get("type")
+                                            == "reasoning_content"
+                                        ):
+                                            reasoning_block = content_blocks[-1]
+                                            reasoning_block["ended_at"] = time.time()
+                                            reasoning_block["duration"] = int(
+                                                reasoning_block["ended_at"]
+                                                - reasoning_block["started_at"]
+                                            )
+
+                                            content_blocks.append(
+                                                {
+                                                    "type": "text",
+                                                    "content": "",
+                                                }
+                                            )
+
+                                        content = f"{content}{value}"
+                                        if not content_blocks:
+                                            content_blocks.append(
+                                                {
+                                                    "type": "text",
+                                                    "content": "",
+                                                }
+                                            )
+
+                                        content_blocks[-1]["content"] = (
+                                            content_blocks[-1]["content"] + value
+                                        )
+
+                                        if DETECT_REASONING:
+                                            content, content_blocks, _ = (
+                                                tag_content_handler(
+                                                    "reasoning",
+                                                    reasoning_tags,
+                                                    content,
+                                                    content_blocks,
+                                                )
+                                            )
+
+                                        if DETECT_CODE_INTERPRETER:
+                                            content, content_blocks, end = (
+                                                tag_content_handler(
+                                                    "code_interpreter",
+                                                    code_interpreter_tags,
+                                                    content,
+                                                    content_blocks,
+                                                )
+                                            )
+
+                                            if end:
+                                                break
+
+                                        if DETECT_SOLUTION:
+                                            content, content_blocks, _ = (
+                                                tag_content_handler(
+                                                    "solution",
+                                                    solution_tags,
+                                                    content,
+                                                    content_blocks,
+                                                )
+                                            )
+
+                                        if ENABLE_REALTIME_CHAT_SAVE:
+                                            # Save message in the database
+                                            Chats.upsert_message_to_chat_by_id_and_message_id(
+                                                metadata["chat_id"],
+                                                metadata["message_id"],
+                                                {
+                                                    "content": serialize_content_blocks(
+                                                        content_blocks
+                                                    ),
+                                                },
+                                            )
+                                        else:
+                                            data = {
+                                                "content": serialize_content_blocks(
+                                                    content_blocks
+                                                ),
+                                            }
+
+                                await event_emitter(
+                                    {
+                                        "type": "chat:completion",
+                                        "data": data,
+                                    }
+                                )
                         except Exception as e:
                             done = "data: [DONE]" in line
                             if done:
@@ -1855,7 +1982,10 @@ async def process_chat_response(
                             }
                         )
 
-                        print(content_blocks, serialize_content_blocks(content_blocks))
+                        log.info(f"content_blocks={content_blocks}")
+                        log.info(
+                            f"serialize_content_blocks={serialize_content_blocks(content_blocks)}"
+                        )
 
                         try:
                             res = await generate_chat_completion(
@@ -1926,7 +2056,7 @@ async def process_chat_response(
 
                 await background_tasks_handler()
             except asyncio.CancelledError:
-                print("Task was cancelled!")
+                log.warning("Task was cancelled!")
                 await event_emitter({"type": "task-cancelled"})
 
                 if not ENABLE_REALTIME_CHAT_SAVE:
@@ -1947,17 +2077,34 @@ async def process_chat_response(
         return {"status": True, "task_id": task_id}
 
     else:
-
         # Fallback to the original response
         async def stream_wrapper(original_generator, events):
             def wrap_item(item):
                 return f"data: {item}\n\n"
 
             for event in events:
-                yield wrap_item(json.dumps(event))
+                event, _ = await process_filter_functions(
+                    request=request,
+                    filter_functions=filter_functions,
+                    filter_type="stream",
+                    form_data=event,
+                    extra_params=extra_params,
+                )
+
+                if event:
+                    yield wrap_item(json.dumps(event))
 
             async for data in original_generator:
-                yield data
+                data, _ = await process_filter_functions(
+                    request=request,
+                    filter_functions=filter_functions,
+                    filter_type="stream",
+                    form_data=data,
+                    extra_params=extra_params,
+                )
+
+                if data:
+                    yield data
 
         return StreamingResponse(
             stream_wrapper(response.body_iterator, events),

backend/open_webui/utils/misc.py

@@ -2,12 +2,18 @@ import hashlib
 import re
 import time
 import uuid
+import logging
 from datetime import timedelta
 from pathlib import Path
 from typing import Callable, Optional
+import json
 
 
 import collections.abc
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 def deep_update(d, u):
@@ -412,7 +418,7 @@ def parse_ollama_modelfile(model_text):
                 elif param_type is bool:
                     value = value.lower() == "true"
             except Exception as e:
-                print(e)
+                log.exception(f"Failed to parse parameter {param}: {e}")
                 continue
 
             data["params"][param] = value
@@ -445,3 +451,15 @@ def parse_ollama_modelfile(model_text):
         data["params"]["messages"] = messages
 
     return data
+
+
+def convert_logit_bias_input_to_json(user_input):
+    logit_bias_pairs = user_input.split(",")
+    logit_bias_json = {}
+    for pair in logit_bias_pairs:
+        token, bias = pair.split(":")
+        token = str(token.strip())
+        bias = int(bias.strip())
+        bias = 100 if bias > 100 else -100 if bias < -100 else bias
+        logit_bias_json[token] = bias
+    return json.dumps(logit_bias_json)

backend/open_webui/utils/models.py

@@ -22,6 +22,7 @@ from open_webui.config import (
 )
 
 from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.models.users import UserModel
 
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
@@ -29,17 +30,17 @@ log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
-async def get_all_base_models(request: Request):
+async def get_all_base_models(request: Request, user: UserModel = None):
     function_models = []
     openai_models = []
     ollama_models = []
 
     if request.app.state.config.ENABLE_OPENAI_API:
-        openai_models = await openai.get_all_models(request)
+        openai_models = await openai.get_all_models(request, user=user)
         openai_models = openai_models["data"]
 
     if request.app.state.config.ENABLE_OLLAMA_API:
-        ollama_models = await ollama.get_all_models(request)
+        ollama_models = await ollama.get_all_models(request, user=user)
         ollama_models = [
             {
                 "id": model["model"],
@@ -58,8 +59,8 @@ async def get_all_base_models(request: Request):
     return models
 
 
-async def get_all_models(request):
+async def get_all_models(request, user: UserModel = None):
-    models = await get_all_base_models(request)
+    models = await get_all_base_models(request, user=user)
 
     # If there are no models, return an empty list
     if len(models) == 0:

backend/open_webui/utils/oauth.py

@@ -146,7 +146,7 @@ class OAuthManager:
             nested_claims = oauth_claim.split(".")
             for nested_claim in nested_claims:
                 claim_data = claim_data.get(nested_claim, {})
-            user_oauth_groups = claim_data if isinstance(claim_data, list) else None
+            user_oauth_groups = claim_data if isinstance(claim_data, list) else []
 
         user_current_groups: list[GroupModel] = Groups.get_groups_by_member_id(user.id)
         all_available_groups: list[GroupModel] = Groups.get_groups()
@@ -234,7 +234,7 @@ class OAuthManager:
             log.warning(f"OAuth callback error: {e}")
             raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
         user_data: UserInfo = token.get("userinfo")
-        if not user_data or "email" not in user_data:
+        if not user_data or auth_manager_config.OAUTH_EMAIL_CLAIM not in user_data:
             user_data: UserInfo = await client.userinfo(token=token)
         if not user_data:
             log.warning(f"OAuth callback failed, user data is missing: {token}")
@@ -315,15 +315,6 @@ class OAuthManager:
         if not user:
             user_count = Users.get_num_users()
 
-            if (
-                request.app.state.USER_COUNT
-                and user_count >= request.app.state.USER_COUNT
-            ):
-                raise HTTPException(
-                    403,
-                    detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-                )
-
             # If the user does not exist, check if signups are enabled
             if auth_manager_config.ENABLE_OAUTH_SIGNUP:
                 # Check if an existing user with the same email already exists

backend/open_webui/utils/payload.py

@@ -62,6 +62,7 @@ def apply_model_params_to_body_openai(params: dict, form_data: dict) -> dict:
         "reasoning_effort": str,
         "seed": lambda x: x,
         "stop": lambda x: [bytes(s, "utf-8").decode("unicode_escape") for s in x],
+        "logit_bias": lambda x: x,
     }
     return apply_model_params_to_body(params, form_data, mappings)
 
@@ -124,7 +125,7 @@ def convert_messages_openai_to_ollama(messages: list[dict]) -> list[dict]:
         tool_call_id = message.get("tool_call_id", None)
 
         # Check if the content is a string (just a simple message)
-        if isinstance(content, str):
+        if isinstance(content, str) and not tool_calls:
             # If the content is a string, it's pure text
             new_message["content"] = content
 
@@ -230,6 +231,12 @@ def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
                 "system"
             ]  # To prevent Ollama warning of invalid option provided
 
+    # If there is the "stop" parameter in the openai_payload, remap it to the ollama_payload.options
+    if "stop" in openai_payload:
+        ollama_options = ollama_payload.get("options", {})
+        ollama_options["stop"] = openai_payload.get("stop")
+        ollama_payload["options"] = ollama_options
+
     if "metadata" in openai_payload:
         ollama_payload["metadata"] = openai_payload["metadata"]
 

backend/open_webui/utils/pdf_generator.py

@@ -110,7 +110,7 @@ class PDFGenerator:
             # When running using `pip install -e .` the static directory is in the site packages.
             # This path only works if `open-webui serve` is run from the root of this project.
             if not FONTS_DIR.exists():
-                FONTS_DIR = Path("./backend/static/fonts")
+                FONTS_DIR = Path(".") / "backend" / "static" / "fonts"
 
             pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
             pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")

backend/open_webui/utils/plugin.py

@@ -45,7 +45,7 @@ def extract_frontmatter(content):
                     frontmatter[key.strip()] = value.strip()
 
     except Exception as e:
-        print(f"An error occurred: {e}")
+        log.exception(f"Failed to extract frontmatter: {e}")
         return {}
 
     return frontmatter

backend/open_webui/utils/response.py

@@ -104,7 +104,7 @@ async def convert_streaming_response_ollama_to_openai(ollama_streaming_response)
         data = json.loads(data)
 
         model = data.get("model", "ollama")
-        message_content = data.get("message", {}).get("content", "")
+        message_content = data.get("message", {}).get("content", None)
         tool_calls = data.get("message", {}).get("tool_calls", None)
         openai_tool_calls = None
 
@@ -118,7 +118,7 @@ async def convert_streaming_response_ollama_to_openai(ollama_streaming_response)
             usage = convert_ollama_usage_to_openai(data)
 
         data = openai_chat_chunk_message_template(
-            model, message_content if not done else None, openai_tool_calls, usage
+            model, message_content, openai_tool_calls, usage
         )
 
         line = f"data: {json.dumps(data)}\n\n"

backend/open_webui/utils/task.py

@@ -104,7 +104,7 @@ def replace_prompt_variable(template: str, prompt: str) -> str:
 
 
 def replace_messages_variable(
-    template: str, messages: Optional[list[str]] = None
+    template: str, messages: Optional[list[dict]] = None
 ) -> str:
     def replacement_function(match):
         full_match = match.group(0)

backend/requirements.txt

@@ -1,5 +1,5 @@
 fastapi==0.115.7
-uvicorn[standard]==0.30.6
+uvicorn[standard]==0.34.0
 pydantic==2.10.6
 python-multipart==0.0.18
 
@@ -13,14 +13,14 @@ async-timeout
 aiocache
 aiofiles
 
-sqlalchemy==2.0.32
+sqlalchemy==2.0.38
 alembic==1.14.0
-peewee==3.17.8
+peewee==3.17.9
 peewee-migrate==1.12.2
 psycopg2-binary==2.9.9
 pgvector==0.3.5
 PyMySQL==1.1.1
-bcrypt==4.2.0
+bcrypt==4.3.0
 
 pymongo
 redis
@@ -31,14 +31,17 @@ APScheduler==3.10.4
 
 RestrictedPython==8.0
 
+loguru==0.7.2
+asgiref==3.8.1
+
 # AI libraries
 openai
 anthropic
 google-generativeai==0.7.2
 tiktoken
 
-langchain==0.3.7
+langchain==0.3.19
-langchain-community==0.3.7
+langchain-community==0.3.18
 
 fake-useragent==1.5.1
 chromadb==0.6.2
@@ -46,6 +49,8 @@ pymilvus==2.5.0
 qdrant-client~=1.12.0
 opensearch-py==2.8.0
 playwright==1.49.1 # Caution: version must match docker-compose.playwright.yaml
+elasticsearch==8.17.1
+
 
 transformers
 sentence-transformers==3.3.1
@@ -71,6 +76,7 @@ validators==0.34.0
 psutil
 sentencepiece
 soundfile==0.13.1
+azure-ai-documentintelligence==1.0.0
 
 opencv-python-headless==4.11.0.86
 rapidocr-onnxruntime==1.3.24
@@ -81,7 +87,7 @@ faster-whisper==1.1.1
 PyJWT[crypto]==2.10.1
 authlib==1.4.1
 
-black==24.8.0
+black==25.1.0
 langfuse==2.44.0
 youtube-transcript-api==0.6.3
 pytube==15.0.0

package-lock.json

@@ -1,13 +1,14 @@
 {
 	"name": "open-webui",
-	"version": "0.5.16",
+	"version": "0.5.20",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.5.16",
+			"version": "0.5.20",
 			"dependencies": {
+				"@azure/msal-browser": "^4.5.0",
 				"@codemirror/lang-javascript": "^6.2.2",
 				"@codemirror/lang-python": "^6.1.6",
 				"@codemirror/language-data": "^6.5.1",
@@ -41,6 +42,7 @@
 				"i18next-resources-to-backend": "^1.2.0",
 				"idb": "^7.1.1",
 				"js-sha256": "^0.10.1",
+				"jspdf": "^3.0.0",
 				"katex": "^0.16.21",
 				"kokoro-js": "^1.1.1",
 				"marked": "^9.1.0",
@@ -134,10 +136,32 @@
 				"node": ">=6.0.0"
 			}
 		},
+		"node_modules/@azure/msal-browser": {
+			"version": "4.5.0",
+			"resolved": "https://registry.npmjs.org/@azure/msal-browser/-/msal-browser-4.5.0.tgz",
+			"integrity": "sha512-H7mWmu8yI0n0XxhJobrgncXI6IU5h8DKMiWDHL5y+Dc58cdg26GbmaMUehbUkdKAQV2OTiFa4FUa6Fdu/wIxBg==",
+			"license": "MIT",
+			"dependencies": {
+				"@azure/msal-common": "15.2.0"
+			},
+			"engines": {
+				"node": ">=0.8.0"
+			}
+		},
+		"node_modules/@azure/msal-common": {
+			"version": "15.2.0",
+			"resolved": "https://registry.npmjs.org/@azure/msal-common/-/msal-common-15.2.0.tgz",
+			"integrity": "sha512-HiYfGAKthisUYqHG1nImCf/uzcyS31wng3o+CycWLIM9chnYJ9Lk6jZ30Y6YiYYpTQ9+z/FGUpiKKekd3Arc0A==",
+			"license": "MIT",
+			"engines": {
+				"node": ">=0.8.0"
+			}
+		},
 		"node_modules/@babel/runtime": {
-			"version": "7.24.1",
+			"version": "7.26.9",
-			"resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.24.1.tgz",
+			"resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.26.9.tgz",
-			"integrity": "sha512-+BIznRzyqBf+2wCTxcKE3wDjfGeCoVE61KSHGpkzqrLi8qxqFwBeUFyId2cxkTmm55fzDGnm0+yCxaxygrLUnQ==",
+			"integrity": "sha512-aA63XwOkcl4xxQa3HjPMqOP6LiK0ZDv3mUPYEFXkpHbaFjtGggE1A61FjFzJnB+p7/oy2gA8E+rcBNl/zC1tMg==",
+			"license": "MIT",
 			"dependencies": {
 				"regenerator-runtime": "^0.14.0"
 			},
@@ -3170,6 +3194,13 @@
 			"integrity": "sha512-Sk/uYFOBAB7mb74XcpizmH0KOR2Pv3D2Hmrh1Dmy5BmK3MpdSa5kqZcg6EKBdklU0bFXX9gCfzvpnyUehrPIuA==",
 			"dev": true
 		},
+		"node_modules/@types/raf": {
+			"version": "3.4.3",
+			"resolved": "https://registry.npmjs.org/@types/raf/-/raf-3.4.3.tgz",
+			"integrity": "sha512-c4YAvMedbPZ5tEyxzQdMoOhhJ4RD3rngZIdwC2/qDN3d7JpEhB6fiBRKVY1lg5B7Wk+uPBjn5f39j1/2MY1oOw==",
+			"license": "MIT",
+			"optional": true
+		},
 		"node_modules/@types/resolve": {
 			"version": "1.20.2",
 			"resolved": "https://registry.npmjs.org/@types/resolve/-/resolve-1.20.2.tgz",
@@ -3199,6 +3230,13 @@
 			"integrity": "sha512-MQ1AnmTLOncwEf9IVU+B2e4Hchrku5N67NkgcAHW0p3sdzPe0FNMANxEm6OJUzPniEQGkeT3OROLlCwZJLWFZA==",
 			"dev": true
 		},
+		"node_modules/@types/trusted-types": {
+			"version": "2.0.7",
+			"resolved": "https://registry.npmjs.org/@types/trusted-types/-/trusted-types-2.0.7.tgz",
+			"integrity": "sha512-ScaPdn1dQczgbl0QFTeTOmVHFULt394XJgOQNoyVhZ6r2vLnMLJfBPd53SB52T/3G36VI1/g2MZaX0cwDuXsfw==",
+			"license": "MIT",
+			"optional": true
+		},
 		"node_modules/@types/unist": {
 			"version": "2.0.10",
 			"resolved": "https://registry.npmjs.org/@types/unist/-/unist-2.0.10.tgz",
@@ -3794,6 +3832,18 @@
 				"node": ">= 4.0.0"
 			}
 		},
+		"node_modules/atob": {
+			"version": "2.1.2",
+			"resolved": "https://registry.npmjs.org/atob/-/atob-2.1.2.tgz",
+			"integrity": "sha512-Wm6ukoaOGJi/73p/cl2GvLjTI5JM1k/O14isD73YML8StrH/7/lRFgmg8nICZgD3bZZvjwCGxtMOD3wWNAu8cg==",
+			"license": "(MIT OR Apache-2.0)",
+			"bin": {
+				"atob": "bin/atob.js"
+			},
+			"engines": {
+				"node": ">= 4.5.0"
+			}
+		},
 		"node_modules/aws-sign2": {
 			"version": "0.7.0",
 			"resolved": "https://registry.npmjs.org/aws-sign2/-/aws-sign2-0.7.0.tgz",
@@ -3829,6 +3879,16 @@
 			"dev": true,
 			"optional": true
 		},
+		"node_modules/base64-arraybuffer": {
+			"version": "1.0.2",
+			"resolved": "https://registry.npmjs.org/base64-arraybuffer/-/base64-arraybuffer-1.0.2.tgz",
+			"integrity": "sha512-I3yl4r9QB5ZRY3XuJVEPfc2XhZO6YweFPI+UovAzn+8/hb3oJ6lnysaFcjVpkCPfVWFUDvoZ8kmVDP7WyRtYtQ==",
+			"license": "MIT",
+			"optional": true,
+			"engines": {
+				"node": ">= 0.6.0"
+			}
+		},
 		"node_modules/base64-js": {
 			"version": "1.5.1",
 			"resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
@@ -4033,6 +4093,18 @@
 				"node": "10.* || >= 12.*"
 			}
 		},
+		"node_modules/btoa": {
+			"version": "1.2.1",
+			"resolved": "https://registry.npmjs.org/btoa/-/btoa-1.2.1.tgz",
+			"integrity": "sha512-SB4/MIGlsiVkMcHmT+pSmIPoNDoHg+7cMzmt3Uxt628MTz2487DKSqK/fuhFBrkuqrYv5UCEnACpF4dTFNKc/g==",
+			"license": "(MIT OR Apache-2.0)",
+			"bin": {
+				"btoa": "bin/btoa.js"
+			},
+			"engines": {
+				"node": ">= 0.4.0"
+			}
+		},
 		"node_modules/buffer": {
 			"version": "6.0.3",
 			"resolved": "https://registry.npmjs.org/buffer/-/buffer-6.0.3.tgz",
@@ -4131,6 +4203,33 @@
 				"node": ">=6"
 			}
 		},
+		"node_modules/canvg": {
+			"version": "3.0.10",
+			"resolved": "https://registry.npmjs.org/canvg/-/canvg-3.0.10.tgz",
+			"integrity": "sha512-qwR2FRNO9NlzTeKIPIKpnTY6fqwuYSequ8Ru8c0YkYU7U0oW+hLUvWadLvAu1Rl72OMNiFhoLu4f8eUjQ7l/+Q==",
+			"license": "MIT",
+			"optional": true,
+			"dependencies": {
+				"@babel/runtime": "^7.12.5",
+				"@types/raf": "^3.4.0",
+				"core-js": "^3.8.3",
+				"raf": "^3.4.1",
+				"regenerator-runtime": "^0.13.7",
+				"rgbcolor": "^1.0.1",
+				"stackblur-canvas": "^2.0.0",
+				"svg-pathdata": "^6.0.3"
+			},
+			"engines": {
+				"node": ">=10.0.0"
+			}
+		},
+		"node_modules/canvg/node_modules/regenerator-runtime": {
+			"version": "0.13.11",
+			"resolved": "https://registry.npmjs.org/regenerator-runtime/-/regenerator-runtime-0.13.11.tgz",
+			"integrity": "sha512-kY1AZVr2Ra+t+piVaJ4gxaFaReZVH40AKNo7UCX6W+dEwBo/2oZJzqfuN1qLq1oL45o56cPaTXELwrTh8Fpggg==",
+			"license": "MIT",
+			"optional": true
+		},
 		"node_modules/caseless": {
 			"version": "0.12.0",
 			"resolved": "https://registry.npmjs.org/caseless/-/caseless-0.12.0.tgz",
@@ -4599,6 +4698,18 @@
 				"node": ">= 0.6"
 			}
 		},
+		"node_modules/core-js": {
+			"version": "3.40.0",
+			"resolved": "https://registry.npmjs.org/core-js/-/core-js-3.40.0.tgz",
+			"integrity": "sha512-7vsMc/Lty6AGnn7uFpYT56QesI5D2Y/UkgKounk87OP9Z2H9Z8kj6jzcSGAxFmUtDOS0ntK6lbQz+Nsa0Jj6mQ==",
+			"hasInstallScript": true,
+			"license": "MIT",
+			"optional": true,
+			"funding": {
+				"type": "opencollective",
+				"url": "https://opencollective.com/core-js"
+			}
+		},
 		"node_modules/core-util-is": {
 			"version": "1.0.3",
 			"resolved": "https://registry.npmjs.org/core-util-is/-/core-util-is-1.0.3.tgz",
@@ -4643,6 +4754,16 @@
 				"node": ">= 8"
 			}
 		},
+		"node_modules/css-line-break": {
+			"version": "2.1.0",
+			"resolved": "https://registry.npmjs.org/css-line-break/-/css-line-break-2.1.0.tgz",
+			"integrity": "sha512-FHcKFCZcAha3LwfVBhCQbW2nCNbkZXn7KVUJcsT5/P8YmfsVja0FMPJr0B903j/E69HUphKiV9iQArX8SDYA4w==",
+			"license": "MIT",
+			"optional": true,
+			"dependencies": {
+				"utrie": "^1.0.2"
+			}
+		},
 		"node_modules/css-select": {
 			"version": "5.1.0",
 			"resolved": "https://registry.npmjs.org/css-select/-/css-select-5.1.0.tgz",
@@ -6106,6 +6227,12 @@
 				"pend": "~1.2.0"
 			}
 		},
+		"node_modules/fflate": {
+			"version": "0.8.2",
+			"resolved": "https://registry.npmjs.org/fflate/-/fflate-0.8.2.tgz",
+			"integrity": "sha512-cPJU47OaAoCbg0pBvzsgpTPhmhqI5eJjh/JIu8tPj5q+T7iLvW/JAYUqmE7KOB4R1ZyEhzBaIQpQpardBF5z8A==",
+			"license": "MIT"
+		},
 		"node_modules/figures": {
 			"version": "3.2.0",
 			"resolved": "https://registry.npmjs.org/figures/-/figures-3.2.0.tgz",
@@ -6701,6 +6828,20 @@
 			"resolved": "https://registry.npmjs.org/html-escaper/-/html-escaper-3.0.3.tgz",
 			"integrity": "sha512-RuMffC89BOWQoY0WKGpIhn5gX3iI54O6nRA0yC124NYVtzjmFWBIiFd8M0x+ZdX0P9R4lADg1mgP8C7PxGOWuQ=="
 		},
+		"node_modules/html2canvas": {
+			"version": "1.4.1",
+			"resolved": "https://registry.npmjs.org/html2canvas/-/html2canvas-1.4.1.tgz",
+			"integrity": "sha512-fPU6BHNpsyIhr8yyMpTLLxAbkaK8ArIBcmZIRiBLiDhjeqvXolaEmDGmELFuX9I4xDcaKKcJl+TKZLqruBbmWA==",
+			"license": "MIT",
+			"optional": true,
+			"dependencies": {
+				"css-line-break": "^2.1.0",
+				"text-segmentation": "^1.0.3"
+			},
+			"engines": {
+				"node": ">=8.0.0"
+			}
+		},
 		"node_modules/htmlparser2": {
 			"version": "8.0.2",
 			"resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-8.0.2.tgz",
@@ -7213,6 +7354,34 @@
 				"graceful-fs": "^4.1.6"
 			}
 		},
+		"node_modules/jspdf": {
+			"version": "3.0.0",
+			"resolved": "https://registry.npmjs.org/jspdf/-/jspdf-3.0.0.tgz",
+			"integrity": "sha512-QvuQZvOI8CjfjVgtajdL0ihrDYif1cN5gXiF9lb9Pd9JOpmocvnNyFO9sdiJ/8RA5Bu8zyGOUjJLj5kiku16ug==",
+			"license": "MIT",
+			"dependencies": {
+				"@babel/runtime": "^7.26.0",
+				"atob": "^2.1.2",
+				"btoa": "^1.2.1",
+				"fflate": "^0.8.1"
+			},
+			"optionalDependencies": {
+				"canvg": "^3.0.6",
+				"core-js": "^3.6.0",
+				"dompurify": "^3.2.4",
+				"html2canvas": "^1.0.0-rc.5"
+			}
+		},
+		"node_modules/jspdf/node_modules/dompurify": {
+			"version": "3.2.4",
+			"resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.2.4.tgz",
+			"integrity": "sha512-ysFSFEDVduQpyhzAob/kkuJjf5zWkZD8/A9ywSp1byueyuCfHamrCBa14/Oc2iiB0e51B+NpxSl5gmzn+Ms/mg==",
+			"license": "(MPL-2.0 OR Apache-2.0)",
+			"optional": true,
+			"optionalDependencies": {
+				"@types/trusted-types": "^2.0.7"
+			}
+		},
 		"node_modules/jsprim": {
 			"version": "2.0.2",
 			"resolved": "https://registry.npmjs.org/jsprim/-/jsprim-2.0.2.tgz",
@@ -9029,7 +9198,7 @@
 			"version": "2.1.0",
 			"resolved": "https://registry.npmjs.org/performance-now/-/performance-now-2.1.0.tgz",
 			"integrity": "sha512-7EAHlyLHI56VEIdK57uwHdHKIaAGbnXPiw0yWbarQZOKaKpvUIgW0jWRVLiatnM+XXlSwsanIBH/hzGMJulMow==",
-			"dev": true
+			"devOptional": true
 		},
 		"node_modules/periscopic": {
 			"version": "3.1.0",
@@ -9755,6 +9924,16 @@
 				"rimraf": "bin.js"
 			}
 		},
+		"node_modules/raf": {
+			"version": "3.4.1",
+			"resolved": "https://registry.npmjs.org/raf/-/raf-3.4.1.tgz",
+			"integrity": "sha512-Sq4CW4QhwOHE8ucn6J34MqtZCeWFP2aQSmrlroYgqAV1PjStIhJXxYuTgUIfkEk7zTLjmIjLmU5q+fbD1NnOJA==",
+			"license": "MIT",
+			"optional": true,
+			"dependencies": {
+				"performance-now": "^2.1.0"
+			}
+		},
 		"node_modules/react-is": {
 			"version": "18.3.1",
 			"resolved": "https://registry.npmjs.org/react-is/-/react-is-18.3.1.tgz",
@@ -9894,6 +10073,16 @@
 			"integrity": "sha512-r5a3l5HzYlIC68TpmYKlxWjmOP6wiPJ1vWv2HeLhNsRZMrCkxeqxiHlQ21oXmQ4F3SiryXBHhAD7JZqvOJjFmg==",
 			"dev": true
 		},
+		"node_modules/rgbcolor": {
+			"version": "1.0.1",
+			"resolved": "https://registry.npmjs.org/rgbcolor/-/rgbcolor-1.0.1.tgz",
+			"integrity": "sha512-9aZLIrhRaD97sgVhtJOW6ckOEh6/GnvQtdVNfdZ6s67+3/XwLS9lBcQYzEEhYVeUowN7pRzMLsyGhK2i/xvWbw==",
+			"license": "MIT OR SEE LICENSE IN FEEL-FREE.md",
+			"optional": true,
+			"engines": {
+				"node": ">= 0.8.15"
+			}
+		},
 		"node_modules/rimraf": {
 			"version": "3.0.2",
 			"resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz",
@@ -10785,6 +10974,16 @@
 			"integrity": "sha512-1XMJE5fQo1jGH6Y/7ebnwPOBEkIEnT4QF32d5R1+VXdXveM0IBMJt8zfaxX1P3QhVwrYe+576+jkANtSS2mBbw==",
 			"dev": true
 		},
+		"node_modules/stackblur-canvas": {
+			"version": "2.7.0",
+			"resolved": "https://registry.npmjs.org/stackblur-canvas/-/stackblur-canvas-2.7.0.tgz",
+			"integrity": "sha512-yf7OENo23AGJhBriGx0QivY5JP6Y1HbrrDI6WLt6C5auYZXlQrheoY8hD4ibekFKz1HOfE48Ww8kMWMnJD/zcQ==",
+			"license": "MIT",
+			"optional": true,
+			"engines": {
+				"node": ">=0.1.14"
+			}
+		},
 		"node_modules/std-env": {
 			"version": "3.7.0",
 			"resolved": "https://registry.npmjs.org/std-env/-/std-env-3.7.0.tgz",
@@ -11166,6 +11365,16 @@
 				"@types/estree": "*"
 			}
 		},
+		"node_modules/svg-pathdata": {
+			"version": "6.0.3",
+			"resolved": "https://registry.npmjs.org/svg-pathdata/-/svg-pathdata-6.0.3.tgz",
+			"integrity": "sha512-qsjeeq5YjBZ5eMdFuUa4ZosMLxgr5RZ+F+Y1OrDhuOCEInRMA3x74XdBtggJcj9kOeInz0WE+LgCPDkZFlBYJw==",
+			"license": "MIT",
+			"optional": true,
+			"engines": {
+				"node": ">=12.0.0"
+			}
+		},
 		"node_modules/symlink-or-copy": {
 			"version": "1.3.1",
 			"resolved": "https://registry.npmjs.org/symlink-or-copy/-/symlink-or-copy-1.3.1.tgz",
@@ -11258,6 +11467,16 @@
 				"streamx": "^2.12.5"
 			}
 		},
+		"node_modules/text-segmentation": {
+			"version": "1.0.3",
+			"resolved": "https://registry.npmjs.org/text-segmentation/-/text-segmentation-1.0.3.tgz",
+			"integrity": "sha512-iOiPUo/BGnZ6+54OsWxZidGCsdU8YbE4PSpdPinp7DeMtUJNJBoJ/ouUSTJjHkh1KntHaltHl/gDs2FC4i5+Nw==",
+			"license": "MIT",
+			"optional": true,
+			"dependencies": {
+				"utrie": "^1.0.2"
+			}
+		},
 		"node_modules/text-table": {
 			"version": "0.2.0",
 			"resolved": "https://registry.npmjs.org/text-table/-/text-table-0.2.0.tgz",
@@ -11597,6 +11816,16 @@
 			"integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==",
 			"dev": true
 		},
+		"node_modules/utrie": {
+			"version": "1.0.2",
+			"resolved": "https://registry.npmjs.org/utrie/-/utrie-1.0.2.tgz",
+			"integrity": "sha512-1MLa5ouZiOmQzUbjbu9VmjLzn1QLXBhwpUa7kdLUQK+KQ5KA9I1vk5U4YHe/X2Ch7PYnJfWuWT+VbuxbGwljhw==",
+			"license": "MIT",
+			"optional": true,
+			"dependencies": {
+				"base64-arraybuffer": "^1.0.2"
+			}
+		},
 		"node_modules/uuid": {
 			"version": "9.0.1",
 			"resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.1.tgz",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.5.16",
+	"version": "0.5.20",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -51,6 +51,7 @@
 	},
 	"type": "module",
 	"dependencies": {
+		"@azure/msal-browser": "^4.5.0",
 		"@codemirror/lang-javascript": "^6.2.2",
 		"@codemirror/lang-python": "^6.1.6",
 		"@codemirror/language-data": "^6.5.1",
@@ -84,6 +85,7 @@
 		"i18next-resources-to-backend": "^1.2.0",
 		"idb": "^7.1.1",
 		"js-sha256": "^0.10.1",
+		"jspdf": "^3.0.0",
 		"katex": "^0.16.21",
 		"kokoro-js": "^1.1.1",
 		"marked": "^9.1.0",

pyproject.toml

@@ -7,7 +7,7 @@ authors = [
 license = { file = "LICENSE" }
 dependencies = [
     "fastapi==0.115.7",
-    "uvicorn[standard]==0.30.6",
+    "uvicorn[standard]==0.34.0",
     "pydantic==2.10.6",
     "python-multipart==0.0.18",
 
@@ -21,14 +21,14 @@ dependencies = [
     "aiocache",
     "aiofiles",
 
-    "sqlalchemy==2.0.32",
+    "sqlalchemy==2.0.38",
     "alembic==1.14.0",
-    "peewee==3.17.8",
+    "peewee==3.17.9",
     "peewee-migrate==1.12.2",
     "psycopg2-binary==2.9.9",
     "pgvector==0.3.5",
     "PyMySQL==1.1.1",
-    "bcrypt==4.2.0",
+    "bcrypt==4.3.0",
 
     "pymongo",
     "redis",
@@ -40,13 +40,16 @@ dependencies = [
 
     "RestrictedPython==8.0",
 
+    "loguru==0.7.2",
+    "asgiref==3.8.1",
+
     "openai",
     "anthropic",
     "google-generativeai==0.7.2",
     "tiktoken",
 
-    "langchain==0.3.7",
+    "langchain==0.3.19",
-    "langchain-community==0.3.7",
+    "langchain-community==0.3.18",
 
     "fake-useragent==1.5.1",
     "chromadb==0.6.2",
@@ -54,6 +57,7 @@ dependencies = [
     "qdrant-client~=1.12.0",
     "opensearch-py==2.8.0",
     "playwright==1.49.1",
+    "elasticsearch==8.17.1",
 
     "transformers",
     "sentence-transformers==3.3.1",
@@ -78,6 +82,7 @@ dependencies = [
     "psutil",
     "sentencepiece",
     "soundfile==0.13.1",
+    "azure-ai-documentintelligence==1.0.0",
 
     "opencv-python-headless==4.11.0.86",
     "rapidocr-onnxruntime==1.3.24",
@@ -88,7 +93,7 @@ dependencies = [
     "PyJWT[crypto]==2.10.1",
     "authlib==1.4.1",
 
-    "black==24.8.0",
+    "black==25.1.0",
     "langfuse==2.44.0",
     "youtube-transcript-api==0.6.3",
     "pytube==15.0.0",

src/app.html

@@ -2,12 +2,14 @@
 <html lang="en">
 	<head>
 		<meta charset="utf-8" />
-		<link rel="icon" type="image/png" href="/favicon/favicon-96x96.png" sizes="96x96" />
+		<link rel="icon" type="image/png" href="/static/favicon.png" />
-		<link rel="icon" type="image/svg+xml" href="/favicon/favicon.svg" />
+		<link rel="icon" type="image/png" href="/static/favicon-96x96.png" sizes="96x96" />
-		<link rel="shortcut icon" href="/favicon/favicon.ico" />
+		<link rel="icon" type="image/svg+xml" href="/static/favicon.svg" />
-		<link rel="apple-touch-icon" sizes="180x180" href="/favicon/apple-touch-icon.png" />
+		<link rel="shortcut icon" href="/static/favicon.ico" />
+		<link rel="apple-touch-icon" sizes="180x180" href="/static/apple-touch-icon.png" />
 		<meta name="apple-mobile-web-app-title" content="Open WebUI" />
-		<link rel="manifest" href="/favicon/site.webmanifest" />
+
+		<link rel="manifest" href="/manifest.json" />
 		<meta
 			name="viewport"
 			content="width=device-width, initial-scale=1, maximum-scale=1, viewport-fit=cover"
@@ -74,6 +76,28 @@
 						}
 					}
 				});
+
+				function setSplashImage() {
+					const logo = document.getElementById('logo');
+					const isDarkMode = document.documentElement.classList.contains('dark');
+
+					if (isDarkMode) {
+						const darkImage = new Image();
+						darkImage.src = '/static/splash-dark.png';
+
+						darkImage.onload = () => {
+							logo.src = '/static/splash-dark.png';
+							logo.style.filter = ''; // Ensure no inversion is applied if splash-dark.png exists
+						};
+
+						darkImage.onerror = () => {
+							logo.style.filter = 'invert(1)'; // Invert image if splash-dark.png is missing
+						};
+					}
+				}
+
+				// Runs after classes are assigned
+				window.onload = setSplashImage;
 			})();
 		</script>
 
@@ -176,10 +200,6 @@
 		background: #000;
 	}
 
-	html.dark #splash-screen img {
-		filter: invert(1);
-	}
-
 	html.her #splash-screen {
 		background: #983724;
 	}

src/lib/apis/retrieval/index.ts

@@ -32,9 +32,15 @@ type ChunkConfigForm = {
 	chunk_overlap: number;
 };
 
+type DocumentIntelligenceConfigForm = {
+	key: string;
+	endpoint: string;
+};
+
 type ContentExtractConfigForm = {
 	engine: string;
 	tika_server_url: string | null;
+	document_intelligence_config: DocumentIntelligenceConfigForm | null;
 };
 
 type YoutubeConfigForm = {
@@ -46,6 +52,7 @@ type YoutubeConfigForm = {
 type RAGConfigForm = {
 	pdf_extract_images?: boolean;
 	enable_google_drive_integration?: boolean;
+	enable_onedrive_integration?: boolean;
 	chunk?: ChunkConfigForm;
 	content_extraction?: ContentExtractConfigForm;
 	web_loader_ssl_verification?: boolean;

src/lib/components/OnBoarding.svelte

@@ -1,5 +1,5 @@
 <script>
-	import { getContext } from 'svelte';
+	import { getContext, onMount } from 'svelte';
 	const i18n = getContext('i18n');
 
 	import { WEBUI_BASE_URL } from '$lib/constants';
@@ -10,6 +10,32 @@
 
 	export let show = true;
 	export let getStartedHandler = () => {};
+
+	function setLogoImage() {
+		const logo = document.getElementById('logo');
+
+		if (logo) {
+			const isDarkMode = document.documentElement.classList.contains('dark');
+
+			if (isDarkMode) {
+				const darkImage = new Image();
+				darkImage.src = '/static/favicon-dark.png';
+
+				darkImage.onload = () => {
+					logo.src = '/static/favicon-dark.png';
+					logo.style.filter = ''; // Ensure no inversion is applied if splash-dark.png exists
+				};
+
+				darkImage.onerror = () => {
+					logo.style.filter = 'invert(1)'; // Invert image if splash-dark.png is missing
+				};
+			}
+		}
+	}
+
+	$: if (show) {
+		setLogoImage();
+	}
 </script>
 
 {#if show}
@@ -18,6 +44,7 @@
 			<div class="flex space-x-2">
 				<div class=" self-center">
 					<img
+						id="logo"
 						crossorigin="anonymous"
 						src="{WEBUI_BASE_URL}/static/favicon.png"
 						class=" w-6 rounded-full"

src/lib/components/admin/Functions/FunctionEditor.svelte

@@ -1,8 +1,7 @@
 <script>
-	import { getContext, createEventDispatcher, onMount, tick } from 'svelte';
+	import { getContext, onMount, tick } from 'svelte';
 	import { goto } from '$app/navigation';
 
-	const dispatch = createEventDispatcher();
 	const i18n = getContext('i18n');
 
 	import CodeEditor from '$lib/components/common/CodeEditor.svelte';
@@ -15,6 +14,8 @@
 	let loading = false;
 	let showConfirm = false;
 
+	export let onSave = () => {};
+
 	export let edit = false;
 	export let clone = false;
 
@@ -256,7 +257,7 @@ class Pipe:
 
 	const saveHandler = async () => {
 		loading = true;
-		dispatch('save', {
+		onSave({
 			id,
 			name,
 			meta,
@@ -371,10 +372,10 @@ class Pipe:
 						value={content}
 						lang="python"
 						{boilerplate}
-						on:change={(e) => {
+						onChange={(e) => {
-							_content = e.detail.value;
+							_content = e;
 						}}
-						on:save={async () => {
+						onSave={async () => {
 							if (formElement) {
 								formElement.requestSubmit();
 							}

src/lib/components/admin/Settings/CodeExecution.svelte

@@ -45,6 +45,16 @@
 
 					<hr class=" border-gray-100 dark:border-gray-850 my-2" />
 
+					<div class="mb-2.5">
+						<div class=" flex w-full justify-between">
+							<div class=" self-center text-xs font-medium">
+								{$i18n.t('Enable Code Execution')}
+							</div>
+
+							<Switch bind:state={config.ENABLE_CODE_EXECUTION} />
+						</div>
+					</div>
+
 					<div class="mb-2.5">
 						<div class="flex w-full justify-between">
 							<div class=" self-center text-xs font-medium">{$i18n.t('Code Execution Engine')}</div>

src/lib/components/admin/Settings/Connections.svelte

@@ -274,6 +274,7 @@
 												newConfig[newIdx] = OPENAI_API_CONFIGS[newIdx < idx ? newIdx : newIdx + 1];
 											});
 											OPENAI_API_CONFIGS = newConfig;
+											updateOpenAIHandler();
 										}}
 									/>
 								{/each}

src/lib/components/admin/Settings/Evaluations.svelte

@@ -103,10 +103,12 @@
 	<div class="overflow-y-scroll scrollbar-hidden h-full">
 		{#if evaluationConfig !== null}
 			<div class="">
-				<div class="text-sm font-medium mb-2">{$i18n.t('General Settings')}</div>
+				<div class="mb-3">
+					<div class=" mb-2.5 text-base font-medium">{$i18n.t('General')}</div>
 
-				<div class=" mb-2">
+					<hr class=" border-gray-100 dark:border-gray-850 my-2" />
-					<div class="flex justify-between items-center text-xs">
+
+					<div class="mb-2.5 flex w-full justify-between">
 						<div class=" text-xs font-medium">{$i18n.t('Arena Models')}</div>
 
 						<Tooltip content={$i18n.t(`Message rating should be enabled to use this feature`)}>
@@ -116,46 +118,50 @@
 				</div>
 
 				{#if evaluationConfig.ENABLE_EVALUATION_ARENA_MODELS}
-					<hr class=" border-gray-50 dark:border-gray-700/10 my-2" />
+					<div class="mb-3">
-
+						<div class=" mb-2.5 text-base font-medium flex justify-between items-center">
-					<div class="flex justify-between items-center mb-2">
+							<div>
-						<div class="text-sm font-medium">{$i18n.t('Manage Arena Models')}</div>
+								{$i18n.t('Manage')}
-
-						<div>
-							<Tooltip content={$i18n.t('Add Arena Model')}>
-								<button
-									class="p-1"
-									type="button"
-									on:click={() => {
-										showAddModel = true;
-									}}
-								>
-									<Plus />
-								</button>
-							</Tooltip>
-						</div>
-					</div>
-
-					<div class="flex flex-col gap-2">
-						{#if (evaluationConfig?.EVALUATION_ARENA_MODELS ?? []).length > 0}
-							{#each evaluationConfig.EVALUATION_ARENA_MODELS as model, index}
-								<Model
-									{model}
-									on:edit={(e) => {
-										editModelHandler(e.detail, index);
-									}}
-									on:delete={(e) => {
-										deleteModelHandler(index);
-									}}
-								/>
-							{/each}
-						{:else}
-							<div class=" text-center text-xs text-gray-500">
-								{$i18n.t(
-									`Using the default arena model with all models. Click the plus button to add custom models.`
-								)}
 							</div>
-						{/if}
+
+							<div>
+								<Tooltip content={$i18n.t('Add Arena Model')}>
+									<button
+										class="p-1"
+										type="button"
+										on:click={() => {
+											showAddModel = true;
+										}}
+									>
+										<Plus />
+									</button>
+								</Tooltip>
+							</div>
+						</div>
+
+						<hr class=" border-gray-100 dark:border-gray-850 my-2" />
+
+						<div class="flex flex-col gap-2">
+							{#if (evaluationConfig?.EVALUATION_ARENA_MODELS ?? []).length > 0}
+								{#each evaluationConfig.EVALUATION_ARENA_MODELS as model, index}
+									<Model
+										{model}
+										on:edit={(e) => {
+											editModelHandler(e.detail, index);
+										}}
+										on:delete={(e) => {
+											deleteModelHandler(index);
+										}}
+									/>
+								{/each}
+							{:else}
+								<div class=" text-center text-xs text-gray-500">
+									{$i18n.t(
+										`Using the default arena model with all models. Click the plus button to add custom models.`
+									)}
+								</div>
+							{/if}
+						</div>
 					</div>
 				{/if}
 			</div>

src/lib/components/admin/Settings/General.svelte

@@ -1,4 +1,6 @@
 <script lang="ts">
+	import DOMPurify from 'dompurify';
+
 	import { getBackendConfig, getVersionUpdates, getWebhookUrl, updateWebhookUrl } from '$lib/apis';
 	import {
 		getAdminConfig,
@@ -220,15 +222,44 @@
 								<div class="">
 									{$i18n.t('License')}
 								</div>
-								<a
+
-									class=" text-xs text-gray-500 hover:underline"
+								{#if $config?.license_metadata}
-									href="https://docs.openwebui.com/enterprise"
+									<a
-									target="_blank"
+										href="https://docs.openwebui.com/enterprise"
-								>
+										target="_blank"
-									{$i18n.t(
+										class="text-gray-500 mt-0.5"
-										'Upgrade to a licensed plan for enhanced capabilities, including custom theming and branding, and dedicated support.'
+									>
-									)}
+										<span class=" capitalize text-black dark:text-white"
-								</a>
+											>{$config?.license_metadata?.type}
+											license</span
+										>
+										registered to
+										<span class=" capitalize text-black dark:text-white"
+											>{$config?.license_metadata?.organization_name}</span
+										>
+										for
+										<span class=" font-medium text-black dark:text-white"
+											>{$config?.license_metadata?.seats ?? 'Unlimited'} users.</span
+										>
+									</a>
+									{#if $config?.license_metadata?.html}
+										<div class="mt-0.5">
+											{@html DOMPurify.sanitize($config?.license_metadata?.html)}
+										</div>
+									{/if}
+								{:else}
+									<a
+										class=" text-xs hover:underline"
+										href="https://docs.openwebui.com/enterprise"
+										target="_blank"
+									>
+										<span class="text-gray-500">
+											{$i18n.t(
+												'Upgrade to a licensed plan for enhanced capabilities, including custom theming and branding, and dedicated support.'
+											)}
+										</span>
+									</a>
+								{/if}
 							</div>
 
 							<!-- <button

src/lib/components/admin/Settings/Models/ConfigureModelsModal.svelte

@@ -16,6 +16,8 @@
 	import Spinner from '$lib/components/common/Spinner.svelte';
 	import Minus from '$lib/components/icons/Minus.svelte';
 	import Plus from '$lib/components/icons/Plus.svelte';
+	import ChevronUp from '$lib/components/icons/ChevronUp.svelte';
+	import ChevronDown from '$lib/components/icons/ChevronDown.svelte';
 
 	export let show = false;
 	export let initHandler = () => {};
@@ -26,6 +28,9 @@
 	let defaultModelIds = [];
 	let modelIds = [];
 
+	let sortKey = '';
+	let sortOrder = '';
+
 	let loading = false;
 	let showResetModal = false;
 
@@ -71,6 +76,9 @@
 			// Add remaining IDs not in MODEL_ORDER_LIST, sorted alphabetically
 			...allModelIds.filter((id) => !orderedSet.has(id)).sort((a, b) => a.localeCompare(b))
 		];
+
+		sortKey = '';
+		sortOrder = '';
 	};
 	const submitHandler = async () => {
 		loading = true;
@@ -145,9 +153,45 @@
 					>
 						<div>
 							<div class="flex flex-col w-full">
-								<div class="mb-1 flex justify-between">
+								<button
+									class="mb-1 flex gap-2"
+									type="button"
+									on:click={() => {
+										sortKey = 'model';
+
+										if (sortOrder === 'asc') {
+											sortOrder = 'desc';
+										} else {
+											sortOrder = 'asc';
+										}
+
+										modelIds = modelIds
+											.filter((id) => id !== '')
+											.sort((a, b) => {
+												const nameA = $models.find((model) => model.id === a)?.name || a;
+												const nameB = $models.find((model) => model.id === b)?.name || b;
+												return sortOrder === 'desc'
+													? nameA.localeCompare(nameB)
+													: nameB.localeCompare(nameA);
+											});
+									}}
+								>
 									<div class="text-xs text-gray-500">{$i18n.t('Reorder Models')}</div>
-								</div>
+
+									{#if sortKey === 'model'}
+										<span class="font-normal self-center">
+											{#if sortOrder === 'asc'}
+												<ChevronUp className="size-3" />
+											{:else}
+												<ChevronDown className="size-3" />
+											{/if}
+										</span>
+									{:else}
+										<span class="invisible">
+											<ChevronUp className="size-3" />
+										</span>
+									{/if}
+								</button>
 
 								<ModelList bind:modelIds />
 							</div>

src/lib/components/admin/Settings/Models/ModelList.svelte

@@ -21,14 +21,24 @@
 		modelIds = modelList;
 	};
 
-	onMount(() => {
+	$: if (modelIds) {
-		sortable = Sortable.create(modelListElement, {
+		init();
-			animation: 150,
+	}
-			onUpdate: async (event) => {
+
-				positionChangeHandler();
+	const init = () => {
-			}
+		if (sortable) {
-		});
+			sortable.destroy();
-	});
+		}
+
+		if (modelListElement) {
+			sortable = Sortable.create(modelListElement, {
+				animation: 150,
+				onUpdate: async (event) => {
+					positionChangeHandler();
+				}
+			});
+		}
+	};
 </script>
 
 {#if modelIds.length > 0}

src/lib/components/admin/Settings/WebSearch.svelte

@@ -29,7 +29,8 @@
 		'tavily',
 		'jina',
 		'bing',
-		'exa'
+		'exa',
+		'perplexity'
 	];
 
 	let youtubeLanguage = 'en';
@@ -85,384 +86,427 @@
 >
 	<div class=" space-y-3 overflow-y-scroll scrollbar-hidden h-full">
 		{#if webConfig}
-			<div>
+			<div class="">
-				<div class=" mb-1 text-sm font-medium">
+				<div class="mb-3">
-					{$i18n.t('Web Search')}
+					<div class=" mb-2.5 text-base font-medium">{$i18n.t('General')}</div>
-				</div>
 
-				<div>
+					<hr class=" border-gray-100 dark:border-gray-850 my-2" />
-					<div class=" py-0.5 flex w-full justify-between">
+
+					<div class="  mb-2.5 flex w-full justify-between">
 						<div class=" self-center text-xs font-medium">
-							{$i18n.t('Enable Web Search')}
+							{$i18n.t('Web Search')}
+						</div>
+						<div class="flex items-center relative">
+							<Switch bind:state={webConfig.search.enabled} />
 						</div>
-
-						<Switch bind:state={webConfig.search.enabled} />
 					</div>
-				</div>
 
-				<div class=" py-0.5 flex w-full justify-between">
+					<div class="  mb-2.5 flex w-full justify-between">
-					<div class=" self-center text-xs font-medium">{$i18n.t('Web Search Engine')}</div>
+						<div class=" self-center text-xs font-medium">
-					<div class="flex items-center relative">
+							{$i18n.t('Web Search Engine')}
-						<select
+						</div>
-							class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-right"
+						<div class="flex items-center relative">
-							bind:value={webConfig.search.engine}
+							<select
-							placeholder={$i18n.t('Select a engine')}
+								class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-right"
-							required
+								bind:value={webConfig.search.engine}
-						>
+								placeholder={$i18n.t('Select a engine')}
-							<option disabled selected value="">{$i18n.t('Select a engine')}</option>
+								required
-							{#each webSearchEngines as engine}
+							>
-								<option value={engine}>{engine}</option>
+								<option disabled selected value="">{$i18n.t('Select a engine')}</option>
-							{/each}
+								{#each webSearchEngines as engine}
-						</select>
+									<option value={engine}>{engine}</option>
+								{/each}
+							</select>
+						</div>
 					</div>
-				</div>
 
-				<div class=" py-0.5 flex w-full justify-between">
+					{#if webConfig.search.engine !== ''}
-					<div class=" self-center text-xs font-medium">{$i18n.t('Full Context Mode')}</div>
-					<div class="flex items-center relative">
-						<Tooltip
-							content={webConfig.RAG_WEB_SEARCH_FULL_CONTEXT
-								? 'Inject the entire web results as context for comprehensive processing, this is recommended for complex queries.'
-								: 'Default to segmented retrieval for focused and relevant content extraction, this is recommended for most cases.'}
-						>
-							<Switch bind:state={webConfig.RAG_WEB_SEARCH_FULL_CONTEXT} />
-						</Tooltip>
-					</div>
-				</div>
-
-				{#if webConfig.search.engine !== ''}
-					<div class="mt-1.5">
 						{#if webConfig.search.engine === 'searxng'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Searxng Query URL')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Searxng Query URL')}
+									</div>
 
-								<div class="flex w-full">
+									<div class="flex w-full">
-									<div class="flex-1">
+										<div class="flex-1">
-										<input
+											<input
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+												class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
-											type="text"
+												type="text"
-											placeholder={$i18n.t('Enter Searxng Query URL')}
+												placeholder={$i18n.t('Enter Searxng Query URL')}
-											bind:value={webConfig.search.searxng_query_url}
+												bind:value={webConfig.search.searxng_query_url}
-											autocomplete="off"
+												autocomplete="off"
-										/>
+											/>
+										</div>
 									</div>
 								</div>
 							</div>
 						{:else if webConfig.search.engine === 'google_pse'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Google PSE API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Google PSE API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Google PSE API Key')}
+										placeholder={$i18n.t('Enter Google PSE API Key')}
-									bind:value={webConfig.search.google_pse_api_key}
+										bind:value={webConfig.search.google_pse_api_key}
-								/>
+									/>
-							</div>
-							<div class="mt-1.5">
-								<div class=" self-center text-xs font-medium mb-1">
-									{$i18n.t('Google PSE Engine Id')}
 								</div>
+								<div class="mt-1.5">
+									<div class=" self-center text-xs font-medium mb-1">
+										{$i18n.t('Google PSE Engine Id')}
+									</div>
 
-								<div class="flex w-full">
+									<div class="flex w-full">
-									<div class="flex-1">
+										<div class="flex-1">
-										<input
+											<input
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+												class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
-											type="text"
+												type="text"
-											placeholder={$i18n.t('Enter Google PSE Engine Id')}
+												placeholder={$i18n.t('Enter Google PSE Engine Id')}
-											bind:value={webConfig.search.google_pse_engine_id}
+												bind:value={webConfig.search.google_pse_engine_id}
-											autocomplete="off"
+												autocomplete="off"
-										/>
+											/>
+										</div>
 									</div>
 								</div>
 							</div>
 						{:else if webConfig.search.engine === 'brave'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Brave Search API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Brave Search API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Brave Search API Key')}
+										placeholder={$i18n.t('Enter Brave Search API Key')}
-									bind:value={webConfig.search.brave_search_api_key}
+										bind:value={webConfig.search.brave_search_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'kagi'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Kagi Search API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Kagi Search API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Kagi Search API Key')}
+										placeholder={$i18n.t('Enter Kagi Search API Key')}
-									bind:value={webConfig.search.kagi_search_api_key}
+										bind:value={webConfig.search.kagi_search_api_key}
-								/>
+									/>
+								</div>
+								.
 							</div>
 						{:else if webConfig.search.engine === 'mojeek'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Mojeek Search API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Mojeek Search API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Mojeek Search API Key')}
+										placeholder={$i18n.t('Enter Mojeek Search API Key')}
-									bind:value={webConfig.search.mojeek_search_api_key}
+										bind:value={webConfig.search.mojeek_search_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'bocha'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Bocha Search API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Bocha Search API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Bocha Search API Key')}
+										placeholder={$i18n.t('Enter Bocha Search API Key')}
-									bind:value={webConfig.search.bocha_search_api_key}
+										bind:value={webConfig.search.bocha_search_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'serpstack'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Serpstack API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Serpstack API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Serpstack API Key')}
+										placeholder={$i18n.t('Enter Serpstack API Key')}
-									bind:value={webConfig.search.serpstack_api_key}
+										bind:value={webConfig.search.serpstack_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'serper'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Serper API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Serper API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Serper API Key')}
+										placeholder={$i18n.t('Enter Serper API Key')}
-									bind:value={webConfig.search.serper_api_key}
+										bind:value={webConfig.search.serper_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'serply'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Serply API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Serply API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Serply API Key')}
+										placeholder={$i18n.t('Enter Serply API Key')}
-									bind:value={webConfig.search.serply_api_key}
+										bind:value={webConfig.search.serply_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'searchapi'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('SearchApi API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('SearchApi API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter SearchApi API Key')}
+										placeholder={$i18n.t('Enter SearchApi API Key')}
-									bind:value={webConfig.search.searchapi_api_key}
+										bind:value={webConfig.search.searchapi_api_key}
-								/>
+									/>
-							</div>
-							<div class="mt-1.5">
-								<div class=" self-center text-xs font-medium mb-1">
-									{$i18n.t('SearchApi Engine')}
 								</div>
+								<div class="mt-1.5">
+									<div class=" self-center text-xs font-medium mb-1">
+										{$i18n.t('SearchApi Engine')}
+									</div>
 
-								<div class="flex w-full">
+									<div class="flex w-full">
-									<div class="flex-1">
+										<div class="flex-1">
-										<input
+											<input
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+												class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
-											type="text"
+												type="text"
-											placeholder={$i18n.t('Enter SearchApi Engine')}
+												placeholder={$i18n.t('Enter SearchApi Engine')}
-											bind:value={webConfig.search.searchapi_engine}
+												bind:value={webConfig.search.searchapi_engine}
-											autocomplete="off"
+												autocomplete="off"
-										/>
+											/>
+										</div>
 									</div>
 								</div>
 							</div>
 						{:else if webConfig.search.engine === 'serpapi'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('SerpApi API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('SerpApi API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter SerpApi API Key')}
+										placeholder={$i18n.t('Enter SerpApi API Key')}
-									bind:value={webConfig.search.serpapi_api_key}
+										bind:value={webConfig.search.serpapi_api_key}
-								/>
+									/>
-							</div>
-							<div class="mt-1.5">
-								<div class=" self-center text-xs font-medium mb-1">
-									{$i18n.t('SerpApi Engine')}
 								</div>
+								<div class="mt-1.5">
+									<div class=" self-center text-xs font-medium mb-1">
+										{$i18n.t('SerpApi Engine')}
+									</div>
 
-								<div class="flex w-full">
+									<div class="flex w-full">
-									<div class="flex-1">
+										<div class="flex-1">
-										<input
+											<input
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+												class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
-											type="text"
+												type="text"
-											placeholder={$i18n.t('Enter SerpApi Engine')}
+												placeholder={$i18n.t('Enter SerpApi Engine')}
-											bind:value={webConfig.search.serpapi_engine}
+												bind:value={webConfig.search.serpapi_engine}
-											autocomplete="off"
+												autocomplete="off"
-										/>
+											/>
+										</div>
 									</div>
 								</div>
 							</div>
 						{:else if webConfig.search.engine === 'tavily'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Tavily API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Tavily API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Tavily API Key')}
+										placeholder={$i18n.t('Enter Tavily API Key')}
-									bind:value={webConfig.search.tavily_api_key}
+										bind:value={webConfig.search.tavily_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'jina'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Jina API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Jina API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Jina API Key')}
+										placeholder={$i18n.t('Enter Jina API Key')}
-									bind:value={webConfig.search.jina_api_key}
+										bind:value={webConfig.search.jina_api_key}
-								/>
+									/>
+								</div>
 							</div>
 						{:else if webConfig.search.engine === 'exa'}
+							<div class="mb-2.5 flex w-full flex-col">
+								<div>
+									<div class=" self-center text-xs font-medium mb-1">
+										{$i18n.t('Exa API Key')}
+									</div>
+
+									<SensitiveInput
+										placeholder={$i18n.t('Enter Exa API Key')}
+										bind:value={webConfig.search.exa_api_key}
+									/>
+								</div>
+							</div>
+						{:else if webConfig.search.engine === 'perplexity'}
 							<div>
 								<div class=" self-center text-xs font-medium mb-1">
-									{$i18n.t('Exa API Key')}
+									{$i18n.t('Perplexity API Key')}
 								</div>
 
 								<SensitiveInput
-									placeholder={$i18n.t('Enter Exa API Key')}
+									placeholder={$i18n.t('Enter Perplexity API Key')}
-									bind:value={webConfig.search.exa_api_key}
+									bind:value={webConfig.search.perplexity_api_key}
 								/>
 							</div>
 						{:else if webConfig.search.engine === 'bing'}
-							<div>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Bing Search V7 Endpoint')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Bing Search V7 Endpoint')}
+									</div>
 
-								<div class="flex w-full">
+									<div class="flex w-full">
-									<div class="flex-1">
+										<div class="flex-1">
-										<input
+											<input
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+												class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
-											type="text"
+												type="text"
-											placeholder={$i18n.t('Enter Bing Search V7 Endpoint')}
+												placeholder={$i18n.t('Enter Bing Search V7 Endpoint')}
-											bind:value={webConfig.search.bing_search_v7_endpoint}
+												bind:value={webConfig.search.bing_search_v7_endpoint}
-											autocomplete="off"
+												autocomplete="off"
-										/>
+											/>
+										</div>
 									</div>
 								</div>
-							</div>
 
-							<div class="mt-2">
+								<div class="mt-2">
-								<div class=" self-center text-xs font-medium mb-1">
+									<div class=" self-center text-xs font-medium mb-1">
-									{$i18n.t('Bing Search V7 Subscription Key')}
+										{$i18n.t('Bing Search V7 Subscription Key')}
+									</div>
+
+									<SensitiveInput
+										placeholder={$i18n.t('Enter Bing Search V7 Subscription Key')}
+										bind:value={webConfig.search.bing_search_v7_subscription_key}
+									/>
 								</div>
-
-								<SensitiveInput
-									placeholder={$i18n.t('Enter Bing Search V7 Subscription Key')}
-									bind:value={webConfig.search.bing_search_v7_subscription_key}
-								/>
 							</div>
 						{/if}
-					</div>
+					{/if}
-				{/if}
 
-				{#if webConfig.search.enabled}
+					{#if webConfig.search.enabled}
-					<div class="mt-2 flex gap-2 mb-1">
+						<div class="mb-2.5 flex w-full flex-col">
-						<div class="w-full">
+							<div class="flex gap-2">
-							<div class=" self-center text-xs font-medium mb-1">
+								<div class="w-full">
-								{$i18n.t('Search Result Count')}
+									<div class=" self-center text-xs font-medium mb-1">
+										{$i18n.t('Search Result Count')}
+									</div>
+
+									<input
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+										placeholder={$i18n.t('Search Result Count')}
+										bind:value={webConfig.search.result_count}
+										required
+									/>
+								</div>
+
+								<div class="w-full">
+									<div class=" self-center text-xs font-medium mb-1">
+										{$i18n.t('Concurrent Requests')}
+									</div>
+
+									<input
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+										placeholder={$i18n.t('Concurrent Requests')}
+										bind:value={webConfig.search.concurrent_requests}
+										required
+									/>
+								</div>
+							</div>
+						</div>
+
+						<div class="mb-2.5 flex w-full flex-col">
+							<div class="  text-xs font-medium mb-1">
+								{$i18n.t('Domain Filter List')}
 							</div>
 
 							<input
 								class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
-								placeholder={$i18n.t('Search Result Count')}
+								placeholder={$i18n.t(
-								bind:value={webConfig.search.result_count}
+									'Enter domains separated by commas (e.g., example.com,site.org)'
-								required
+								)}
+								bind:value={webConfig.search.domain_filter_list}
 							/>
 						</div>
+					{/if}
 
-						<div class="w-full">
+					<div class="  mb-2.5 flex w-full justify-between">
-							<div class=" self-center text-xs font-medium mb-1">
+						<div class=" self-center text-xs font-medium">
-								{$i18n.t('Concurrent Requests')}
+							<Tooltip content={$i18n.t('Full Context Mode')} placement="top-start">
-							</div>
+								{$i18n.t('Bypass Embedding and Retrieval')}
-
+							</Tooltip>
-							<input
+						</div>
-								class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+						<div class="flex items-center relative">
-								placeholder={$i18n.t('Concurrent Requests')}
+							<Tooltip
-								bind:value={webConfig.search.concurrent_requests}
+								content={webConfig.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
-								required
+									? 'Inject the entire content as context for comprehensive processing, this is recommended for complex queries.'
-							/>
+									: 'Default to segmented retrieval for focused and relevant content extraction, this is recommended for most cases.'}
+							>
+								<Switch bind:state={webConfig.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL} />
+							</Tooltip>
 						</div>
 					</div>
 
-					<div class="mt-2">
+					<div class="  mb-2.5 flex w-full justify-between">
-						<div class=" self-center text-xs font-medium mb-1">
+						<div class=" self-center text-xs font-medium">
-							{$i18n.t('Domain Filter List')}
+							{$i18n.t('Trust Proxy Environment')}
+						</div>
+						<div class="flex items-center relative">
+							<Tooltip
+								content={webConfig.search.trust_env
+									? 'Use proxy designated by http_proxy and https_proxy environment variables to fetch page contents'
+									: 'Use no proxy to fetch page contents.'}
+							>
+								<Switch bind:state={webConfig.search.trust_env} />
+							</Tooltip>
 						</div>
-
-						<input
-							class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
-							placeholder={$i18n.t(
-								'Enter domains separated by commas (e.g., example.com,site.org)'
-							)}
-							bind:value={webConfig.search.domain_filter_list}
-						/>
 					</div>
-				{/if}
-			</div>
-
-			<hr class="border-gray-100 dark:border-gray-850 my-2" />
-
-			<div>
-				<div class=" mb-1 text-sm font-medium">
-					{$i18n.t('Web Loader Settings')}
 				</div>
 
-				<div>
+				<div class="mb-3">
-					<div class=" py-0.5 flex w-full justify-between">
+					<div class=" mb-2.5 text-base font-medium">{$i18n.t('Loader')}</div>
+
+					<hr class=" border-gray-100 dark:border-gray-850 my-2" />
+
+					<div class="  mb-2.5 flex w-full justify-between">
 						<div class=" self-center text-xs font-medium">
 							{$i18n.t('Bypass SSL verification for Websites')}
 						</div>
-
+						<div class="flex items-center relative">
-						<button
+							<Switch bind:state={webConfig.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION} />
-							class="p-1 px-3 text-xs flex rounded-sm transition"
+						</div>
-							on:click={() => {
-								webConfig.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION =
-									!webConfig.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION;
-								submitHandler();
-							}}
-							type="button"
-						>
-							{#if webConfig.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION === false}
-								<span class="ml-2 self-center">{$i18n.t('On')}</span>
-							{:else}
-								<span class="ml-2 self-center">{$i18n.t('Off')}</span>
-							{/if}
-						</button>
 					</div>
-				</div>
 
-				<div class=" mt-2 mb-1 text-sm font-medium">
+					<div class="  mb-2.5 flex w-full justify-between">
-					{$i18n.t('Youtube Loader Settings')}
+						<div class=" self-center text-xs font-medium">
-				</div>
+							{$i18n.t('Youtube Language')}
-
+						</div>
-				<div>
+						<div class="flex items-center relative">
-					<div class=" py-0.5 flex w-full justify-between">
-						<div class=" w-20 text-xs font-medium self-center">{$i18n.t('Language')}</div>
-						<div class=" flex-1 self-center">
 							<input
-								class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+								class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
 								type="text"
 								placeholder={$i18n.t('Enter language codes')}
 								bind:value={youtubeLanguage}
@@ -470,14 +514,14 @@
 							/>
 						</div>
 					</div>
-				</div>
 
-				<div>
+					<div class="  mb-2.5 flex flex-col w-full justify-between">
-					<div class=" py-0.5 flex w-full justify-between">
+						<div class=" mb-1 text-xs font-medium">
-						<div class=" w-20 text-xs font-medium self-center">{$i18n.t('Proxy URL')}</div>
+							{$i18n.t('Youtube Proxy URL')}
-						<div class=" flex-1 self-center">
+						</div>
+						<div class="flex items-center relative">
 							<input
-								class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+								class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
 								type="text"
 								placeholder={$i18n.t('Enter proxy URL (e.g. https://user:password@host:port)')}
 								bind:value={youtubeProxyUrl}

src/lib/components/admin/Users/UserList.svelte

@@ -28,6 +28,7 @@
 	import ChevronUp from '$lib/components/icons/ChevronUp.svelte';
 	import ChevronDown from '$lib/components/icons/ChevronDown.svelte';
 	import About from '$lib/components/chat/Settings/About.svelte';
+	import Banner from '$lib/components/common/Banner.svelte';
 
 	const i18n = getContext('i18n');
 
@@ -124,12 +125,43 @@
 />
 <UserChatsModal bind:show={showUserChatsModal} user={selectedUser} />
 
+{#if ($config?.license_metadata?.seats ?? null) !== null && users.length > $config?.license_metadata?.seats}
+	<div class=" mt-1 mb-2 text-xs text-red-500">
+		<Banner
+			className="mx-0"
+			banner={{
+				type: 'error',
+				title: 'License Error',
+				content:
+					'Exceeded the number of seats in your license. Please contact support to increase the number of seats.',
+				dismissable: true
+			}}
+		/>
+	</div>
+{/if}
+
 <div class="mt-0.5 mb-2 gap-1 flex flex-col md:flex-row justify-between">
 	<div class="flex md:self-center text-lg font-medium px-0.5">
-		{$i18n.t('Users')}
+		<div class="flex-shrink-0">
+			{$i18n.t('Users')}
+		</div>
 		<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-50 dark:bg-gray-850" />
 
-		<span class="text-lg font-medium text-gray-500 dark:text-gray-300">{users.length}</span>
+		{#if ($config?.license_metadata?.seats ?? null) !== null}
+			{#if users.length > $config?.license_metadata?.seats}
+				<span class="text-lg font-medium text-red-500"
+					>{users.length} of {$config?.license_metadata?.seats}
+					<span class="text-sm font-normal">available users</span></span
+				>
+			{:else}
+				<span class="text-lg font-medium text-gray-500 dark:text-gray-300"
+					>{users.length} of {$config?.license_metadata?.seats}
+					<span class="text-sm font-normal">available users</span></span
+				>
+			{/if}
+		{:else}
+			<span class="text-lg font-medium text-gray-500 dark:text-gray-300">{users.length}</span>
+		{/if}
 	</div>
 
 	<div class="flex gap-1">

src/lib/components/channel/MessageInput.svelte

@@ -157,22 +157,6 @@
 		}
 
 		files = [...files, fileItem];
-		// Check if the file is an audio file and transcribe/convert it to text file
-		if (['audio/mpeg', 'audio/wav', 'audio/ogg', 'audio/x-m4a'].includes(file['type'])) {
-			const res = await transcribeAudio(localStorage.token, file).catch((error) => {
-				toast.error(`${error}`);
-				return null;
-			});
-
-			if (res) {
-				console.log(res);
-				const blob = new Blob([res.text], { type: 'text/plain' });
-				file = blobToFile(blob, `${file.name}.txt`);
-
-				fileItem.name = file.name;
-				fileItem.size = file.size;
-			}
-		}
 
 		try {
 			// During the file upload, file content is automatically extracted.

src/lib/components/chat/Chat.svelte

@@ -187,15 +187,20 @@
 		setToolIds();
 	}
 
+	$: if (atSelectedModel || selectedModels) {
+		setToolIds();
+	}
+
 	const setToolIds = async () => {
 		if (!$tools) {
 			tools.set(await getTools(localStorage.token));
 		}
 
-		if (selectedModels.length !== 1) {
+		if (selectedModels.length !== 1 && !atSelectedModel) {
 			return;
 		}
-		const model = $models.find((m) => m.id === selectedModels[0]);
+
+		const model = atSelectedModel ?? $models.find((m) => m.id === selectedModels[0]);
 		if (model) {
 			selectedToolIds = (model?.info?.meta?.toolIds ?? []).filter((id) =>
 				$tools.find((t) => t.id === id)
@@ -836,6 +841,7 @@
 				content: m.content,
 				info: m.info ? m.info : undefined,
 				timestamp: m.timestamp,
+				...(m.usage ? { usage: m.usage } : {}),
 				...(m.sources ? { sources: m.sources } : {})
 			})),
 			model_item: $models.find((m) => m.id === modelId),
@@ -1273,7 +1279,9 @@
 		const chatInputElement = document.getElementById('chat-input');
 
 		if (chatInputElement) {
+			await tick();
 			chatInputElement.style.height = '';
+			chatInputElement.style.height = Math.min(chatInputElement.scrollHeight, 320) + 'px';
 		}
 
 		const _files = JSON.parse(JSON.stringify(files));
@@ -1488,7 +1496,10 @@
 							params?.system ?? $settings?.system ?? '',
 							$user.name,
 							$settings?.userLocation
-								? await getAndUpdateUserLocation(localStorage.token)
+								? await getAndUpdateUserLocation(localStorage.token).catch((err) => {
+										console.error(err);
+										return undefined;
+									})
 								: undefined
 						)}${
 							(responseMessage?.userContext ?? null)
@@ -1573,7 +1584,12 @@
 				variables: {
 					...getPromptVariables(
 						$user.name,
-						$settings?.userLocation ? await getAndUpdateUserLocation(localStorage.token) : undefined
+						$settings?.userLocation
+							? await getAndUpdateUserLocation(localStorage.token).catch((err) => {
+									console.error(err);
+									return undefined;
+								})
+							: undefined
 					)
 				},
 				model_item: $models.find((m) => m.id === model.id),
@@ -1921,9 +1937,33 @@
 
 		<PaneGroup direction="horizontal" class="w-full h-full">
 			<Pane defaultSize={50} class="h-full flex w-full relative">
-				{#if $banners.length > 0 && !history.currentId && !$chatId && selectedModels.length <= 1}
+				{#if !history.currentId && !$chatId && selectedModels.length <= 1 && ($banners.length > 0 || ($config?.license_metadata?.type ?? null) === 'trial' || (($config?.license_metadata?.seats ?? null) !== null && $config?.user_count > $config?.license_metadata?.seats))}
 					<div class="absolute top-12 left-0 right-0 w-full z-30">
 						<div class=" flex flex-col gap-1 w-full">
+							{#if ($config?.license_metadata?.type ?? null) === 'trial'}
+								<Banner
+									banner={{
+										type: 'info',
+										title: 'Trial License',
+										content: $i18n.t(
+											'You are currently using a trial license. Please contact support to upgrade your license.'
+										)
+									}}
+								/>
+							{/if}
+
+							{#if ($config?.license_metadata?.seats ?? null) !== null && $config?.user_count > $config?.license_metadata?.seats}
+								<Banner
+									banner={{
+										type: 'error',
+										title: 'License Error',
+										content: $i18n.t(
+											'Exceeded the number of seats in your license. Please contact support to increase the number of seats.'
+										)
+									}}
+								/>
+							{/if}
+
 							{#each $banners.filter( (b) => (b.dismissible ? !JSON.parse(localStorage.getItem('dismissedBannerIds') ?? '[]').includes(b.id) : true) ) as banner}
 								<Banner
 									{banner}
@@ -1965,6 +2005,7 @@
 									bind:autoScroll
 									bind:prompt
 									{selectedModels}
+									{atSelectedModel}
 									{sendPrompt}
 									{showMessage}
 									{submitMessage}

src/lib/components/chat/ChatPlaceholder.svelte

@@ -16,6 +16,7 @@
 
 	export let modelIds = [];
 	export let models = [];
+	export let atSelectedModel;
 
 	export let submitPrompt;
 
@@ -126,7 +127,8 @@
 		<div class=" w-full font-primary" in:fade={{ duration: 200, delay: 300 }}>
 			<Suggestions
 				className="grid grid-cols-2"
-				suggestionPrompts={models[selectedModelIdx]?.info?.meta?.suggestion_prompts ??
+				suggestionPrompts={atSelectedModel?.info?.meta?.suggestion_prompts ??
+					models[selectedModelIdx]?.info?.meta?.suggestion_prompts ??
 					$config?.default_prompt_suggestions ??
 					[]}
 				on:select={(e) => {

src/lib/components/chat/ContentRenderer/FloatingButtons.svelte

@@ -121,7 +121,8 @@
 			toast.error('Model not selected');
 			return;
 		}
-		prompt = `Explain this section to me in more detail\n\n\`\`\`\n${selectedText}\n\`\`\``;
+		const explainText = $i18n.t('Explain this section to me in more detail');
+		prompt = `${explainText}\n\n\`\`\`\n${selectedText}\n\`\`\``;
 
 		responseContent = '';
 		const [res, controller] = await chatCompletion(localStorage.token, {
@@ -246,7 +247,7 @@
 				>
 					<ChatBubble className="size-3 shrink-0" />
 
-					<div class="shrink-0">Ask</div>
+					<div class="shrink-0">{$i18n.t('Ask')}</div>
 				</button>
 				<button
 					class="px-1 hover:bg-gray-50 dark:hover:bg-gray-800 rounded-sm flex items-center gap-1 min-w-fit"
@@ -257,7 +258,7 @@
 				>
 					<LightBlub className="size-3 shrink-0" />
 
-					<div class="shrink-0">Explain</div>
+					<div class="shrink-0">{$i18n.t('Explain')}</div>
 				</button>
 			</div>
 		{:else}

src/lib/components/chat/MessageInput.svelte

@@ -2,6 +2,7 @@
 	import { toast } from 'svelte-sonner';
 	import { v4 as uuidv4 } from 'uuid';
 	import { createPicker, getAuthToken } from '$lib/utils/google-drive-picker';
+	import { pickAndDownloadFile } from '$lib/utils/onedrive-file-picker';
 
 	import { onMount, tick, getContext, createEventDispatcher, onDestroy } from 'svelte';
 	const dispatch = createEventDispatcher();
@@ -84,6 +85,8 @@
 	let loaded = false;
 	let recording = false;
 
+	let isComposing = false;
+
 	let chatInputContainerElement;
 	let chatInputElement;
 
@@ -173,22 +176,6 @@
 		}
 
 		files = [...files, fileItem];
-		// Check if the file is an audio file and transcribe/convert it to text file
-		if (['audio/mpeg', 'audio/wav', 'audio/ogg', 'audio/x-m4a'].includes(file['type'])) {
-			const res = await transcribeAudio(localStorage.token, file).catch((error) => {
-				toast.error(`${error}`);
-				return null;
-			});
-
-			if (res) {
-				console.log(res);
-				const blob = new Blob([res.text], { type: 'text/plain' });
-				file = blobToFile(blob, `${file.name}.txt`);
-
-				fileItem.name = file.name;
-				fileItem.size = file.size;
-			}
-		}
 
 		try {
 			// During the file upload, file content is automatically extracted.
@@ -691,12 +678,13 @@
 												bind:value={prompt}
 												id="chat-input"
 												messageInput={true}
-												shiftEnter={!$mobile ||
+												shiftEnter={!($settings?.ctrlEnterToSend ?? false) &&
-													!(
+													(!$mobile ||
-														'ontouchstart' in window ||
+														!(
-														navigator.maxTouchPoints > 0 ||
+															'ontouchstart' in window ||
-														navigator.msMaxTouchPoints > 0
+															navigator.maxTouchPoints > 0 ||
-													)}
+															navigator.msMaxTouchPoints > 0
+														))}
 												placeholder={placeholder ? placeholder : $i18n.t('Send a Message')}
 												largeTextAsFile={$settings?.largeTextAsFile ?? false}
 												autocomplete={$config?.features.enable_autocomplete_generation}
@@ -721,6 +709,8 @@
 													console.log(res);
 													return res;
 												}}
+												oncompositionstart={() => (isComposing = true)}
+												oncompositionend={() => (isComposing = false)}
 												on:keydown={async (e) => {
 													e = e.detail.event;
 
@@ -820,15 +810,24 @@
 																navigator.msMaxTouchPoints > 0
 															)
 														) {
-															// Prevent Enter key from creating a new line
+															if (isComposing) {
-															// Uses keyCode '13' for Enter key for chinese/japanese keyboards
+																return;
-															if (e.keyCode === 13 && !e.shiftKey) {
-																e.preventDefault();
 															}
 
-															// Submit the prompt when Enter key is pressed
+															// Uses keyCode '13' for Enter key for chinese/japanese keyboards.
-															if (prompt !== '' && e.keyCode === 13 && !e.shiftKey) {
+															//
-																dispatch('submit', prompt);
+															// Depending on the user's settings, it will send the message
+															// either when Enter is pressed or when Ctrl+Enter is pressed.
+															const enterPressed =
+																($settings?.ctrlEnterToSend ?? false)
+																	? (e.key === 'Enter' || e.keyCode === 13) && isCtrlPressed
+																	: (e.key === 'Enter' || e.keyCode === 13) && !e.shiftKey;
+
+															if (enterPressed) {
+																e.preventDefault();
+																if (prompt !== '' || files.length > 0) {
+																	dispatch('submit', prompt);
+																}
 															}
 														}
 													}
@@ -891,34 +890,19 @@
 											class="scrollbar-hidden bg-transparent dark:text-gray-100 outline-hidden w-full pt-3 px-1 resize-none"
 											placeholder={placeholder ? placeholder : $i18n.t('Send a Message')}
 											bind:value={prompt}
-											on:keypress={(e) => {
+											on:compositionstart={() => (isComposing = true)}
-												if (
+											on:compositionend={() => (isComposing = false)}
-													!$mobile ||
-													!(
-														'ontouchstart' in window ||
-														navigator.maxTouchPoints > 0 ||
-														navigator.msMaxTouchPoints > 0
-													)
-												) {
-													// Prevent Enter key from creating a new line
-													if (e.key === 'Enter' && !e.shiftKey) {
-														e.preventDefault();
-													}
-
-													// Submit the prompt when Enter key is pressed
-													if (prompt !== '' && e.key === 'Enter' && !e.shiftKey) {
-														dispatch('submit', prompt);
-													}
-												}
-											}}
 											on:keydown={async (e) => {
 												const isCtrlPressed = e.ctrlKey || e.metaKey; // metaKey is for Cmd key on Mac
+
+												console.log('keydown', e);
 												const commandsContainerElement =
 													document.getElementById('commands-container');
 
 												if (e.key === 'Escape') {
 													stopResponse();
 												}
+
 												// Command/Ctrl + Shift + Enter to submit a message pair
 												if (isCtrlPressed && e.key === 'Enter' && e.shiftKey) {
 													e.preventDefault();
@@ -954,51 +938,87 @@
 													editButton?.click();
 												}
 
-												if (commandsContainerElement && e.key === 'ArrowUp') {
+												if (commandsContainerElement) {
-													e.preventDefault();
+													if (commandsContainerElement && e.key === 'ArrowUp') {
-													commandsElement.selectUp();
+														e.preventDefault();
+														commandsElement.selectUp();
 
-													const commandOptionButton = [
+														const commandOptionButton = [
-														...document.getElementsByClassName('selected-command-option-button')
+															...document.getElementsByClassName('selected-command-option-button')
-													]?.at(-1);
+														]?.at(-1);
-													commandOptionButton.scrollIntoView({ block: 'center' });
+														commandOptionButton.scrollIntoView({ block: 'center' });
-												}
+													}
 
-												if (commandsContainerElement && e.key === 'ArrowDown') {
+													if (commandsContainerElement && e.key === 'ArrowDown') {
-													e.preventDefault();
+														e.preventDefault();
-													commandsElement.selectDown();
+														commandsElement.selectDown();
 
-													const commandOptionButton = [
+														const commandOptionButton = [
-														...document.getElementsByClassName('selected-command-option-button')
+															...document.getElementsByClassName('selected-command-option-button')
-													]?.at(-1);
+														]?.at(-1);
-													commandOptionButton.scrollIntoView({ block: 'center' });
+														commandOptionButton.scrollIntoView({ block: 'center' });
-												}
+													}
 
-												if (commandsContainerElement && e.key === 'Enter') {
+													if (commandsContainerElement && e.key === 'Enter') {
-													e.preventDefault();
+														e.preventDefault();
 
-													const commandOptionButton = [
+														const commandOptionButton = [
-														...document.getElementsByClassName('selected-command-option-button')
+															...document.getElementsByClassName('selected-command-option-button')
-													]?.at(-1);
+														]?.at(-1);
+
+														if (e.shiftKey) {
+															prompt = `${prompt}\n`;
+														} else if (commandOptionButton) {
+															commandOptionButton?.click();
+														} else {
+															document.getElementById('send-message-button')?.click();
+														}
+													}
+
+													if (commandsContainerElement && e.key === 'Tab') {
+														e.preventDefault();
+
+														const commandOptionButton = [
+															...document.getElementsByClassName('selected-command-option-button')
+														]?.at(-1);
 
-													if (e.shiftKey) {
-														prompt = `${prompt}\n`;
-													} else if (commandOptionButton) {
 														commandOptionButton?.click();
-													} else {
+													}
-														document.getElementById('send-message-button')?.click();
+												} else {
+													if (
+														!$mobile ||
+														!(
+															'ontouchstart' in window ||
+															navigator.maxTouchPoints > 0 ||
+															navigator.msMaxTouchPoints > 0
+														)
+													) {
+														if (isComposing) {
+															return;
+														}
+
+														console.log('keypress', e);
+														// Prevent Enter key from creating a new line
+														const isCtrlPressed = e.ctrlKey || e.metaKey;
+														const enterPressed =
+															($settings?.ctrlEnterToSend ?? false)
+																? (e.key === 'Enter' || e.keyCode === 13) && isCtrlPressed
+																: (e.key === 'Enter' || e.keyCode === 13) && !e.shiftKey;
+
+														console.log('Enter pressed:', enterPressed);
+
+														if (enterPressed) {
+															e.preventDefault();
+														}
+
+														// Submit the prompt when Enter key is pressed
+														if ((prompt !== '' || files.length > 0) && enterPressed) {
+															dispatch('submit', prompt);
+														}
 													}
 												}
 
-												if (commandsContainerElement && e.key === 'Tab') {
+												if (e.key === 'Tab') {
-													e.preventDefault();
-
-													const commandOptionButton = [
-														...document.getElementsByClassName('selected-command-option-button')
-													]?.at(-1);
-
-													commandOptionButton?.click();
-												} else if (e.key === 'Tab') {
 													const words = findWordIndices(prompt);
 
 													if (words.length > 0) {
@@ -1108,6 +1128,21 @@
 													);
 												}
 											}}
+											uploadOneDriveHandler={async () => {
+												try {
+													const fileData = await pickAndDownloadFile();
+													if (fileData) {
+														const file = new File([fileData.blob], fileData.name, {
+															type: fileData.blob.type || 'application/octet-stream'
+														});
+														await uploadFileHandler(file);
+													} else {
+														console.log('No file was selected from OneDrive');
+													}
+												} catch (error) {
+													console.error('OneDrive Error:', error);
+												}
+											}}
 											onClose={async () => {
 												await tick();
 
@@ -1285,14 +1320,17 @@
 
 																	stream = null;
 
-																	if (!$TTSWorker) {
+																	if ($settings.audio?.tts?.engine === 'browser-kokoro') {
-																		await TTSWorker.set(
+																		// If the user has not initialized the TTS worker, initialize it
-																			new KokoroWorker({
+																		if (!$TTSWorker) {
-																				dtype: $settings.audio?.tts?.engineConfig?.dtype ?? 'fp32'
+																			await TTSWorker.set(
-																			})
+																				new KokoroWorker({
-																		);
+																					dtype: $settings.audio?.tts?.engineConfig?.dtype ?? 'fp32'
+																				})
+																			);
 
-																		await $TTSWorker.init();
+																			await $TTSWorker.init();
+																		}
 																	}
 
 																	showCallOverlay.set(true);

src/lib/components/chat/MessageInput/CallOverlay.svelte

@@ -231,7 +231,6 @@
 			mediaRecorder.onstart = () => {
 				console.log('Recording started');
 				audioChunks = [];
-				analyseAudio(audioStream);
 			};
 
 			mediaRecorder.ondataavailable = (event) => {
@@ -245,7 +244,7 @@
 				stopRecordingCallback();
 			};
 
-			mediaRecorder.start();
+			analyseAudio(audioStream);
 		}
 	};
 
@@ -321,6 +320,9 @@
 				if (hasSound) {
 					// BIG RED TEXT
 					console.log('%c%s', 'color: red; font-size: 20px;', '🔊 Sound detected');
+					if (mediaRecorder && mediaRecorder.state !== 'recording') {
+						mediaRecorder.start();
+					}
 
 					if (!hasStartedSpeaking) {
 						hasStartedSpeaking = true;

src/lib/components/chat/MessageInput/Commands/Prompts.svelte

@@ -74,7 +74,13 @@
 		}
 
 		if (command.content.includes('{{USER_LOCATION}}')) {
-			const location = await getUserPosition();
+			let location;
+			try {
+				location = await getUserPosition();
+			} catch (error) {
+				toast.error($i18n.t('Location access not allowed'));
+				location = 'LOCATION_UNKNOWN';
+			}
 			text = text.replaceAll('{{USER_LOCATION}}', String(location));
 		}
 

src/lib/components/chat/MessageInput/InputMenu.svelte

@@ -5,6 +5,7 @@
 
 	import { config, user, tools as _tools, mobile } from '$lib/stores';
 	import { createPicker } from '$lib/utils/google-drive-picker';
+
 	import { getTools } from '$lib/apis/tools';
 
 	import Dropdown from '$lib/components/common/Dropdown.svelte';
@@ -24,6 +25,7 @@
 	export let inputFilesHandler: Function;
 
 	export let uploadGoogleDriveHandler: Function;
+	export let uploadOneDriveHandler: Function;
 
 	export let selectedToolIds: string[] = [];
 
@@ -225,6 +227,97 @@
 					<div class="line-clamp-1">{$i18n.t('Google Drive')}</div>
 				</DropdownMenu.Item>
 			{/if}
+
+			{#if $config?.features?.enable_onedrive_integration}
+				<DropdownMenu.Item
+					class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl"
+					on:click={() => {
+						uploadOneDriveHandler();
+					}}
+				>
+					<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32" class="w-5 h-5" fill="none">
+						<mask
+							id="mask0_87_7796"
+							style="mask-type:alpha"
+							maskUnits="userSpaceOnUse"
+							x="0"
+							y="6"
+							width="32"
+							height="20"
+						>
+							<path
+								d="M7.82979 26C3.50549 26 0 22.5675 0 18.3333C0 14.1921 3.35322 10.8179 7.54613 10.6716C9.27535 7.87166 12.4144 6 16 6C20.6308 6 24.5169 9.12183 25.5829 13.3335C29.1316 13.3603 32 16.1855 32 19.6667C32 23.0527 29 26 25.8723 25.9914L7.82979 26Z"
+								fill="#C4C4C4"
+							/>
+						</mask>
+						<g mask="url(#mask0_87_7796)">
+							<path
+								d="M7.83017 26.0001C5.37824 26.0001 3.18957 24.8966 1.75391 23.1691L18.0429 16.3335L30.7089 23.4647C29.5926 24.9211 27.9066 26.0001 26.0004 25.9915C23.1254 26.0001 12.0629 26.0001 7.83017 26.0001Z"
+								fill="url(#paint0_linear_87_7796)"
+							/>
+							<path
+								d="M25.5785 13.3149L18.043 16.3334L30.709 23.4647C31.5199 22.4065 32.0004 21.0916 32.0004 19.6669C32.0004 16.1857 29.1321 13.3605 25.5833 13.3337C25.5817 13.3274 25.5801 13.3212 25.5785 13.3149Z"
+								fill="url(#paint1_linear_87_7796)"
+							/>
+							<path
+								d="M7.06445 10.7028L18.0423 16.3333L25.5779 13.3148C24.5051 9.11261 20.6237 6 15.9997 6C12.4141 6 9.27508 7.87166 7.54586 10.6716C7.3841 10.6773 7.22358 10.6877 7.06445 10.7028Z"
+								fill="url(#paint2_linear_87_7796)"
+							/>
+							<path
+								d="M1.7535 23.1687L18.0425 16.3331L7.06471 10.7026C3.09947 11.0792 0 14.3517 0 18.3331C0 20.1665 0.657197 21.8495 1.7535 23.1687Z"
+								fill="url(#paint3_linear_87_7796)"
+							/>
+						</g>
+						<defs>
+							<linearGradient
+								id="paint0_linear_87_7796"
+								x1="4.42591"
+								y1="24.6668"
+								x2="27.2309"
+								y2="23.2764"
+								gradientUnits="userSpaceOnUse"
+							>
+								<stop stop-color="#2086B8" />
+								<stop offset="1" stop-color="#46D3F6" />
+							</linearGradient>
+							<linearGradient
+								id="paint1_linear_87_7796"
+								x1="23.8302"
+								y1="19.6668"
+								x2="30.2108"
+								y2="15.2082"
+								gradientUnits="userSpaceOnUse"
+							>
+								<stop stop-color="#1694DB" />
+								<stop offset="1" stop-color="#62C3FE" />
+							</linearGradient>
+							<linearGradient
+								id="paint2_linear_87_7796"
+								x1="8.51037"
+								y1="7.33333"
+								x2="23.3335"
+								y2="15.9348"
+								gradientUnits="userSpaceOnUse"
+							>
+								<stop stop-color="#0D3D78" />
+								<stop offset="1" stop-color="#063B83" />
+							</linearGradient>
+							<linearGradient
+								id="paint3_linear_87_7796"
+								x1="-0.340429"
+								y1="19.9998"
+								x2="14.5634"
+								y2="14.4649"
+								gradientUnits="userSpaceOnUse"
+							>
+								<stop stop-color="#16589B" />
+								<stop offset="1" stop-color="#1464B7" />
+							</linearGradient>
+						</defs>
+					</svg>
+					<div class="line-clamp-1">{$i18n.t('OneDrive')}</div>
+				</DropdownMenu.Item>
+			{/if}
 		</DropdownMenu.Content>
 	</div>
 </Dropdown>

src/lib/components/chat/Messages.svelte

@@ -32,6 +32,7 @@
 	export let prompt;
 	export let history = {};
 	export let selectedModels;
+	export let atSelectedModel;
 
 	let messages = [];
 
@@ -227,7 +228,8 @@
 					role: 'user',
 					content: userPrompt,
 					...(history.messages[messageId].files && { files: history.messages[messageId].files }),
-					models: selectedModels
+					models: selectedModels,
+					timestamp: Math.floor(Date.now() / 1000) // Unix epoch
 				};
 
 				let messageParentId = history.messages[messageId].parentId;
@@ -349,6 +351,7 @@
 	{#if Object.keys(history?.messages ?? {}).length == 0}
 		<ChatPlaceholder
 			modelIds={selectedModels}
+			{atSelectedModel}
 			submitPrompt={async (p) => {
 				let text = p;
 

src/lib/components/chat/Messages/Citations.svelte

@@ -43,6 +43,7 @@
 	}
 
 	$: {
+		console.log('sources', sources);
 		citations = sources.reduce((acc, source) => {
 			if (Object.keys(source).length === 0) {
 				return acc;
@@ -53,7 +54,7 @@
 				const distance = source.distances?.[index];
 
 				// Within the same citation there could be multiple documents
-				const id = metadata?.source ?? 'N/A';
+				const id = metadata?.source ?? source?.source?.id ?? 'N/A';
 				let _source = source?.source;
 
 				if (metadata?.name) {

src/lib/components/chat/Messages/CodeBlock.svelte

@@ -1,18 +1,9 @@
 <script lang="ts">
-	import hljs from 'highlight.js';
-	import { loadPyodide } from 'pyodide';
 	import mermaid from 'mermaid';
 
 	import { v4 as uuidv4 } from 'uuid';
 
-	import {
+	import { getContext, onMount, tick, onDestroy } from 'svelte';
-		getContext,
-		getAllContexts,
-		onMount,
-		tick,
-		createEventDispatcher,
-		onDestroy
-	} from 'svelte';
 	import { copyToClipboard } from '$lib/utils';
 
 	import 'highlight.js/styles/github-dark.min.css';
@@ -23,12 +14,17 @@
 	import { config } from '$lib/stores';
 	import { executeCode } from '$lib/apis/utils';
 	import { toast } from 'svelte-sonner';
+	import ChevronUp from '$lib/components/icons/ChevronUp.svelte';
+	import ChevronUpDown from '$lib/components/icons/ChevronUpDown.svelte';
+	import CommandLine from '$lib/components/icons/CommandLine.svelte';
 
 	const i18n = getContext('i18n');
-	const dispatch = createEventDispatcher();
 
 	export let id = '';
 
+	export let onSave = (e) => {};
+	export let onCode = (e) => {};
+
 	export let save = false;
 	export let run = true;
 
@@ -64,14 +60,19 @@
 	let result = null;
 	let files = null;
 
+	let collapsed = false;
 	let copied = false;
 	let saved = false;
 
+	const collapseCodeBlock = () => {
+		collapsed = !collapsed;
+	};
+
 	const saveCode = () => {
 		saved = true;
 
 		code = _code;
-		dispatch('save', code);
+		onSave(code);
 
 		setTimeout(() => {
 			saved = false;
@@ -344,7 +345,7 @@
 		render();
 	}
 
-	$: dispatch('code', { lang, code });
+	$: onCode({ lang, code });
 
 	$: if (attributes) {
 		onAttributesUpdate();
@@ -380,7 +381,7 @@
 		console.log('codeblock', lang, code);
 
 		if (lang) {
-			dispatch('code', { lang, code });
+			onCode({ lang, code });
 		}
 		if (document.documentElement.classList.contains('dark')) {
 			mermaid.initialize({
@@ -425,18 +426,39 @@
 				class="sticky {stickyButtonsClassName} mb-1 py-1 pr-2.5 flex items-center justify-end z-10 text-xs text-black dark:text-white"
 			>
 				<div class="flex items-center gap-0.5 translate-y-[1px]">
-					{#if lang.toLowerCase() === 'python' || lang.toLowerCase() === 'py' || (lang === '' && checkPythonCode(code))}
+					<button
+						class="flex gap-1 items-center bg-none border-none bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition rounded-md px-1.5 py-0.5"
+						on:click={collapseCodeBlock}
+					>
+						<div>
+							<ChevronUpDown className="size-3" />
+						</div>
+
+						<div>
+							{collapsed ? $i18n.t('Expand') : $i18n.t('Collapse')}
+						</div>
+					</button>
+
+					{#if ($config?.features?.enable_code_execution ?? true) && (lang.toLowerCase() === 'python' || lang.toLowerCase() === 'py' || (lang === '' && checkPythonCode(code)))}
 						{#if executing}
 							<div class="run-code-button bg-none border-none p-1 cursor-not-allowed">Running</div>
 						{:else if run}
 							<button
-								class="run-code-button bg-none border-none bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition rounded-md px-1.5 py-0.5"
+								class="flex gap-1 items-center run-code-button bg-none border-none bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition rounded-md px-1.5 py-0.5"
 								on:click={async () => {
 									code = _code;
 									await tick();
 									executePython(code);
-								}}>{$i18n.t('Run')}</button
+								}}
 							>
+								<div>
+									<CommandLine className="size-3" />
+								</div>
+
+								<div>
+									{$i18n.t('Run')}
+								</div>
+							</button>
 						{/if}
 					{/if}
 
@@ -464,65 +486,80 @@
 						: 'rounded-b-lg'} overflow-hidden"
 			>
 				<div class=" pt-7 bg-gray-50 dark:bg-gray-850"></div>
-				<CodeEditor
+
-					value={code}
+				{#if !collapsed}
-					{id}
+					<CodeEditor
-					{lang}
+						value={code}
-					on:save={() => {
+						{id}
-						saveCode();
+						{lang}
-					}}
+						onSave={() => {
-					on:change={(e) => {
+							saveCode();
-						_code = e.detail.value;
+						}}
-					}}
+						onChange={(value) => {
-				/>
+							_code = value;
+						}}
+					/>
+				{:else}
+					<div
+						class="bg-gray-50 dark:bg-black dark:text-white rounded-b-lg! pt-2 pb-2 px-4 flex flex-col gap-2 text-xs"
+					>
+						<span class="text-gray-500 italic">
+							{$i18n.t('{{COUNT}} hidden lines', {
+								COUNT: code.split('\n').length
+							})}
+						</span>
+					</div>
+				{/if}
 			</div>
 
-			<div
+			{#if !collapsed}
-				id="plt-canvas-{id}"
-				class="bg-gray-50 dark:bg-[#202123] dark:text-white max-w-full overflow-x-auto scrollbar-hidden"
-			/>
-
-			{#if executing || stdout || stderr || result || files}
 				<div
-					class="bg-gray-50 dark:bg-[#202123] dark:text-white rounded-b-lg! py-4 px-4 flex flex-col gap-2"
+					id="plt-canvas-{id}"
-				>
+					class="bg-gray-50 dark:bg-[#202123] dark:text-white max-w-full overflow-x-auto scrollbar-hidden"
-					{#if executing}
+				/>
-						<div class=" ">
+
-							<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
+				{#if executing || stdout || stderr || result || files}
-							<div class="text-sm">Running...</div>
+					<div
-						</div>
+						class="bg-gray-50 dark:bg-[#202123] dark:text-white rounded-b-lg! py-4 px-4 flex flex-col gap-2"
-					{:else}
+					>
-						{#if stdout || stderr}
+						{#if executing}
 							<div class=" ">
 								<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
-								<div
+								<div class="text-sm">Running...</div>
-									class="text-sm {stdout?.split('\n')?.length > 100
-										? `max-h-96`
-										: ''}  overflow-y-auto"
-								>
-									{stdout || stderr}
-								</div>
 							</div>
-						{/if}
+						{:else}
-						{#if result || files}
+							{#if stdout || stderr}
-							<div class=" ">
+								<div class=" ">
-								<div class=" text-gray-500 text-xs mb-1">RESULT</div>
+									<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
-								{#if result}
+									<div
-									<div class="text-sm">{`${JSON.stringify(result)}`}</div>
+										class="text-sm {stdout?.split('\n')?.length > 100
-								{/if}
+											? `max-h-96`
-								{#if files}
+											: ''}  overflow-y-auto"
-									<div class="flex flex-col gap-2">
+									>
-										{#each files as file}
+										{stdout || stderr}
-											{#if file.type.startsWith('image')}
-												<img src={file.data} alt="Output" />
-											{/if}
-										{/each}
 									</div>
-								{/if}
+								</div>
-							</div>
+							{/if}
+							{#if result || files}
+								<div class=" ">
+									<div class=" text-gray-500 text-xs mb-1">RESULT</div>
+									{#if result}
+										<div class="text-sm">{`${JSON.stringify(result)}`}</div>
+									{/if}
+									{#if files}
+										<div class="flex flex-col gap-2">
+											{#each files as file}
+												{#if file.type.startsWith('image')}
+													<img src={file.data} alt="Output" class=" w-full max-w-[36rem]" />
+												{/if}
+											{/each}
+										</div>
+									{/if}
+								</div>
+							{/if}
 						{/if}
-					{/if}
+					</div>
-				</div>
+				{/if}
 			{/if}
 		{/if}
 	</div>

src/lib/components/chat/Messages/Markdown/MarkdownTokens.svelte

@@ -17,6 +17,7 @@
 	import Collapsible from '$lib/components/common/Collapsible.svelte';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
 	import ArrowDownTray from '$lib/components/icons/ArrowDownTray.svelte';
+	import Source from './Source.svelte';
 
 	const dispatch = createEventDispatcher();
 
@@ -88,14 +89,14 @@
 				code={token?.text ?? ''}
 				{attributes}
 				{save}
-				on:code={(e) => {
+				onCode={(value) => {
-					dispatch('code', e.detail);
+					dispatch('code', value);
 				}}
-				on:save={(e) => {
+				onSave={(value) => {
 					dispatch('update', {
 						raw: token.raw,
 						oldContent: token.text,
-						newContent: e.detail
+						newContent: value
 					});
 				}}
 			/>
@@ -261,6 +262,8 @@
 			{@html html}
 		{:else if token.text.includes(`<iframe src="${WEBUI_BASE_URL}/api/v1/files/`)}
 			{@html `${token.text}`}
+		{:else if token.text.includes(`<source_id`)}
+			<Source {id} {token} onClick={onSourceClick} />
 		{:else}
 			{token.text}
 		{/if}