Merge pull request #10933 from open-webui/dev

0.5.18

.github/workflows/release-pypi.yml

@@ -19,7 +19,7 @@ jobs:
         uses: actions/checkout@v4
       - uses: actions/setup-node@v4
         with:
-          node-version: 18
+          node-version: 22
       - uses: actions/setup-python@v5
         with:
           python-version: 3.11

CHANGELOG.md

@@ -5,6 +5,66 @@ 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).
 
+## [0.5.18] - 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
+
+- **🔍 Web Search Retrieval Restored**: Resolved a critical issue that broke web search retrieval by reverting deduplication changes, ensuring complete and accurate search results once again.
+
+## [0.5.15] - 2025-02-20
+
+### Added
+
+- **📄 Full Context Mode for Local Document Search (RAG)**: Toggle full context mode from Admin Settings > Documents to inject entire document content into context, improving accuracy for models with large context windows—ideal for deep context understanding.
+- **🌍 Smarter Web Search with Agentic Workflows**: Web searches now intelligently gather and refine multiple relevant terms, similar to RAG handling, delivering significantly better search results for more accurate information retrieval.
+- **🔎 Experimental Playwright Support for Web Loader**: Web content retrieval is taken to the next level with Playwright-powered scraping for enhanced accuracy in extracted web data.
+- **☁️ Experimental Azure Storage Provider**: Early-stage support for Azure Storage allows more cloud storage flexibility directly within Open WebUI.
+- **📊 Improved Jupyter Code Execution with Plots**: Interactive coding now properly displays inline plots, making data visualization more seamless inside chat interactions.
+- **⏳ Adjustable Execution Timeout for Jupyter Interpreter**: Customize execution timeout (default: 60s) for Jupyter-based code execution, allowing longer or more constrained execution based on your needs.
+- **▶️ "Running..." Indicator for Jupyter Code Execution**: A visual indicator now appears while code execution is in progress, providing real-time status updates on ongoing computations.
+- **⚙️ General Backend & Frontend Stability Enhancements**: Extensive refactoring improves reliability, performance, and overall user experience for a more seamless Open WebUI.
+- **🌍 Translation Updates**: Various international translation refinements ensure better localization and a more natural user interface experience.
+
+### Fixed
+
+- **📱 Mobile Hover Issue Resolved**: Users can now edit responses smoothly on mobile without interference, fixing a longstanding hover issue.
+- **🔄 Temporary Chat Message Duplication Fixed**: Eliminated buggy behavior where messages were being unnecessarily repeated in temporary chat mode, ensuring a smooth and consistent conversation flow.
+
+## [0.5.14] - 2025-02-17
+
+### Fixed
+
+- **🔧 Critical Import Error Resolved**: Fixed a circular import issue preventing 'override_static' from being correctly imported in 'open_webui.config', ensuring smooth system initialization and stability.
+
 ## [0.5.13] - 2025-02-17
 
 ### Added

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()
@@ -588,20 +587,6 @@ load_oauth_providers()
 
 STATIC_DIR = Path(os.getenv("STATIC_DIR", OPEN_WEBUI_DIR / "static")).resolve()
 
-
-def override_static(path: str, content: str):
-    # Ensure path is safe
-    if "/" in path or ".." in path:
-        log.error(f"Invalid path: {path}")
-        return
-
-    file_path = os.path.join(STATIC_DIR, path)
-    os.makedirs(os.path.dirname(file_path), exist_ok=True)
-
-    with open(file_path, "wb") as f:
-        f.write(base64.b64decode(content))  # Convert Base64 back to raw binary
-
-
 frontend_favicon = FRONTEND_BUILD_DIR / "static" / "favicon.png"
 
 if frontend_favicon.exists():
@@ -692,12 +677,20 @@ 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(
     "GOOGLE_APPLICATION_CREDENTIALS_JSON", None
 )
 
+AZURE_STORAGE_ENDPOINT = os.environ.get("AZURE_STORAGE_ENDPOINT", None)
+AZURE_STORAGE_CONTAINER_NAME = os.environ.get("AZURE_STORAGE_CONTAINER_NAME", None)
+AZURE_STORAGE_KEY = os.environ.get("AZURE_STORAGE_KEY", None)
+
 ####################################
 # File Upload DIR
 ####################################
@@ -797,6 +790,9 @@ ENABLE_OPENAI_API = PersistentConfig(
 OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "")
 OPENAI_API_BASE_URL = os.environ.get("OPENAI_API_BASE_URL", "")
 
+GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY", "")
+GEMINI_API_BASE_URL = os.environ.get("GEMINI_API_BASE_URL", "")
+
 
 if OPENAI_API_BASE_URL == "":
     OPENAI_API_BASE_URL = "https://api.openai.com/v1"
@@ -1101,7 +1097,7 @@ 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)
@@ -1409,6 +1405,11 @@ CODE_EXECUTION_JUPYTER_AUTH_PASSWORD = PersistentConfig(
     os.environ.get("CODE_EXECUTION_JUPYTER_AUTH_PASSWORD", ""),
 )
 
+CODE_EXECUTION_JUPYTER_TIMEOUT = PersistentConfig(
+    "CODE_EXECUTION_JUPYTER_TIMEOUT",
+    "code_execution.jupyter.timeout",
+    int(os.environ.get("CODE_EXECUTION_JUPYTER_TIMEOUT", "60")),
+)
 
 ENABLE_CODE_INTERPRETER = PersistentConfig(
     "ENABLE_CODE_INTERPRETER",
@@ -1464,6 +1465,17 @@ CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD = PersistentConfig(
     ),
 )
 
+CODE_INTERPRETER_JUPYTER_TIMEOUT = PersistentConfig(
+    "CODE_INTERPRETER_JUPYTER_TIMEOUT",
+    "code_interpreter.jupyter.timeout",
+    int(
+        os.environ.get(
+            "CODE_INTERPRETER_JUPYTER_TIMEOUT",
+            os.environ.get("CODE_EXECUTION_JUPYTER_TIMEOUT", "60"),
+        )
+    ),
+)
+
 
 DEFAULT_CODE_INTERPRETER_PROMPT = """
 #### Tools Available
@@ -1489,21 +1501,27 @@ 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
@@ -1557,6 +1575,18 @@ 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",
@@ -1570,6 +1600,26 @@ 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"))
 )
@@ -1585,6 +1635,12 @@ ENABLE_RAG_HYBRID_SEARCH = PersistentConfig(
     os.environ.get("ENABLE_RAG_HYBRID_SEARCH", "").lower() == "true",
 )
 
+RAG_FULL_CONTEXT = PersistentConfig(
+    "RAG_FULL_CONTEXT",
+    "rag.full_context",
+    os.getenv("RAG_FULL_CONTEXT", "False").lower() == "true",
+)
+
 RAG_FILE_MAX_COUNT = PersistentConfig(
     "RAG_FILE_MAX_COUNT",
     "rag.file.max_count",
@@ -1699,7 +1755,7 @@ Respond to the user query using the provided context, incorporating inline citat
 - Respond in the same language as the user's query.
 - If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
 - If the answer isn't present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
-- **Only include inline citations using [source_id] when a <source_id> tag is explicitly provided in the context.**  
+- **Only include inline citations using [source_id] (e.g., [1], [2]) when a `<source_id>` tag is explicitly provided in the context.**
 - Do not cite if the <source_id> tag is not provided in the context.  
 - Do not use XML tags in your response.
 - Ensure citations are concise and directly related to the information provided.
@@ -1780,10 +1836,10 @@ 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.
@@ -1933,10 +1989,34 @@ RAG_WEB_SEARCH_CONCURRENT_REQUESTS = PersistentConfig(
     int(os.getenv("RAG_WEB_SEARCH_CONCURRENT_REQUESTS", "10")),
 )
 
+RAG_WEB_LOADER_ENGINE = PersistentConfig(
+    "RAG_WEB_LOADER_ENGINE",
+    "rag.web.loader.engine",
+    os.environ.get("RAG_WEB_LOADER_ENGINE", "safe_web"),
+)
+
 RAG_WEB_SEARCH_TRUST_ENV = PersistentConfig(
     "RAG_WEB_SEARCH_TRUST_ENV",
     "rag.web.search.trust_env",
-    os.getenv("RAG_WEB_SEARCH_TRUST_ENV", False),
+    os.getenv("RAG_WEB_SEARCH_TRUST_ENV", "False").lower() == "true",
+)
+
+PLAYWRIGHT_WS_URI = PersistentConfig(
+    "PLAYWRIGHT_WS_URI",
+    "rag.web.loader.engine.playwright.ws.uri",
+    os.environ.get("PLAYWRIGHT_WS_URI", None),
+)
+
+FIRECRAWL_API_KEY = PersistentConfig(
+    "FIRECRAWL_API_KEY",
+    "firecrawl.api_key",
+    os.environ.get("FIRECRAWL_API_KEY", ""),
+)
+
+FIRECRAWL_API_BASE_URL = PersistentConfig(
+    "FIRECRAWL_API_BASE_URL",
+    "firecrawl.api_url",
+    os.environ.get("FIRECRAWL_API_BASE_URL", "https://api.firecrawl.dev"),
 )
 
 ####################################
@@ -2149,6 +2229,17 @@ IMAGES_OPENAI_API_KEY = PersistentConfig(
     os.getenv("IMAGES_OPENAI_API_KEY", OPENAI_API_KEY),
 )
 
+IMAGES_GEMINI_API_BASE_URL = PersistentConfig(
+    "IMAGES_GEMINI_API_BASE_URL",
+    "image_generation.gemini.api_base_url",
+    os.getenv("IMAGES_GEMINI_API_BASE_URL", GEMINI_API_BASE_URL),
+)
+IMAGES_GEMINI_API_KEY = PersistentConfig(
+    "IMAGES_GEMINI_API_KEY",
+    "image_generation.gemini.api_key",
+    os.getenv("IMAGES_GEMINI_API_KEY", GEMINI_API_KEY),
+)
+
 IMAGE_SIZE = PersistentConfig(
     "IMAGE_SIZE", "image_generation.size", os.getenv("IMAGE_SIZE", "512x512")
 )
@@ -2325,7 +2416,7 @@ 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

@@ -419,3 +419,25 @@ 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,
@@ -95,6 +98,7 @@ 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,
@@ -106,6 +110,7 @@ from open_webui.config import (
     CODE_EXECUTION_JUPYTER_AUTH,
     CODE_EXECUTION_JUPYTER_AUTH_TOKEN,
     CODE_EXECUTION_JUPYTER_AUTH_PASSWORD,
+    CODE_EXECUTION_JUPYTER_TIMEOUT,
     ENABLE_CODE_INTERPRETER,
     CODE_INTERPRETER_ENGINE,
     CODE_INTERPRETER_PROMPT_TEMPLATE,
@@ -113,6 +118,7 @@ from open_webui.config import (
     CODE_INTERPRETER_JUPYTER_AUTH,
     CODE_INTERPRETER_JUPYTER_AUTH_TOKEN,
     CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD,
+    CODE_INTERPRETER_JUPYTER_TIMEOUT,
     # Image
     AUTOMATIC1111_API_AUTH,
     AUTOMATIC1111_BASE_URL,
@@ -131,6 +137,8 @@ from open_webui.config import (
     IMAGE_STEPS,
     IMAGES_OPENAI_API_BASE_URL,
     IMAGES_OPENAI_API_KEY,
+    IMAGES_GEMINI_API_BASE_URL,
+    IMAGES_GEMINI_API_KEY,
     # Audio
     AUDIO_STT_ENGINE,
     AUDIO_STT_MODEL,
@@ -145,6 +153,10 @@ from open_webui.config import (
     AUDIO_TTS_VOICE,
     AUDIO_TTS_AZURE_SPEECH_REGION,
     AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT,
+    PLAYWRIGHT_WS_URI,
+    FIRECRAWL_API_BASE_URL,
+    FIRECRAWL_API_KEY,
+    RAG_WEB_LOADER_ENGINE,
     WHISPER_MODEL,
     DEEPGRAM_API_KEY,
     WHISPER_MODEL_AUTO_UPDATE,
@@ -152,6 +164,8 @@ from open_webui.config import (
     # Retrieval
     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,
@@ -171,6 +185,8 @@ 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,
@@ -179,7 +195,7 @@ 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,
@@ -206,11 +222,13 @@ 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,
@@ -289,8 +307,11 @@ 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,
@@ -375,6 +396,7 @@ https://github.com/open-webui/open-webui
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
+    start_logger()
     if RESET_CONFIG_ON_START:
         reset_config()
 
@@ -515,6 +537,9 @@ app.state.config.RELEVANCE_THRESHOLD = RAG_RELEVANCE_THRESHOLD
 app.state.config.FILE_MAX_SIZE = RAG_FILE_MAX_SIZE
 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
@@ -522,6 +547,8 @@ 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
@@ -549,10 +576,13 @@ 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
@@ -576,7 +606,11 @@ app.state.config.EXA_API_KEY = EXA_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
+app.state.config.RAG_WEB_LOADER_ENGINE = RAG_WEB_LOADER_ENGINE
 app.state.config.RAG_WEB_SEARCH_TRUST_ENV = RAG_WEB_SEARCH_TRUST_ENV
+app.state.config.PLAYWRIGHT_WS_URI = PLAYWRIGHT_WS_URI
+app.state.config.FIRECRAWL_API_BASE_URL = FIRECRAWL_API_BASE_URL
+app.state.config.FIRECRAWL_API_KEY = FIRECRAWL_API_KEY
 
 app.state.EMBEDDING_FUNCTION = None
 app.state.ef = None
@@ -631,6 +665,7 @@ app.state.config.CODE_EXECUTION_JUPYTER_AUTH_TOKEN = CODE_EXECUTION_JUPYTER_AUTH
 app.state.config.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD = (
     CODE_EXECUTION_JUPYTER_AUTH_PASSWORD
 )
+app.state.config.CODE_EXECUTION_JUPYTER_TIMEOUT = CODE_EXECUTION_JUPYTER_TIMEOUT
 
 app.state.config.ENABLE_CODE_INTERPRETER = ENABLE_CODE_INTERPRETER
 app.state.config.CODE_INTERPRETER_ENGINE = CODE_INTERPRETER_ENGINE
@@ -644,6 +679,7 @@ app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_TOKEN = (
 app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD = (
     CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD
 )
+app.state.config.CODE_INTERPRETER_JUPYTER_TIMEOUT = CODE_INTERPRETER_JUPYTER_TIMEOUT
 
 ########################################
 #
@@ -658,6 +694,9 @@ app.state.config.ENABLE_IMAGE_PROMPT_GENERATION = ENABLE_IMAGE_PROMPT_GENERATION
 app.state.config.IMAGES_OPENAI_API_BASE_URL = IMAGES_OPENAI_API_BASE_URL
 app.state.config.IMAGES_OPENAI_API_KEY = IMAGES_OPENAI_API_KEY
 
+app.state.config.IMAGES_GEMINI_API_BASE_URL = IMAGES_GEMINI_API_BASE_URL
+app.state.config.IMAGES_GEMINI_API_KEY = IMAGES_GEMINI_API_KEY
+
 app.state.config.IMAGE_GENERATION_MODEL = IMAGE_GENERATION_MODEL
 
 app.state.config.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
@@ -859,6 +898,19 @@ 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
@@ -891,7 +943,7 @@ 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 = [
@@ -920,7 +972,7 @@ 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}
 
 
@@ -931,7 +983,7 @@ 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)
@@ -967,7 +1019,7 @@ 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": model_info.model_dump() if model_info else model,
             "direct": model_item.get("direct", False),
             **(
                 {"function_calling": "native"}
@@ -1126,6 +1178,7 @@ 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 {}
@@ -1157,6 +1210,7 @@ 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},
             }
             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
@@ -14,8 +15,10 @@ from langchain_core.documents import Document
 
 from open_webui.config import VECTOR_DB
 from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
-from open_webui.utils.misc import get_last_user_message
+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,
@@ -80,7 +83,20 @@ 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
+
+
+def get_doc(collection_name: str, user: UserModel = None):
+    try:
+        result = VECTOR_DB_CLIENT.get(collection_name=collection_name)
+
+        if result:
+            log.info(f"query_doc:result {result.ids} {result.metadatas}")
+
+        return result
+    except Exception as e:
+        log.exception(f"Error getting doc {collection_name}: {e}")
         raise e
 
 
@@ -137,47 +153,80 @@ def query_doc_with_hybrid_search(
         raise e
 
 
-def merge_and_sort_query_results(
+def merge_get_results(get_results: list[dict]) -> dict:
-    query_results: list[dict], k: int, reverse: bool = False
-) -> list[dict]:
     # Initialize lists to store combined data
-    combined_distances = []
     combined_documents = []
     combined_metadatas = []
+    combined_ids = []
 
-    for data in query_results:
+    for data in get_results:
-        combined_distances.extend(data["distances"][0])
         combined_documents.extend(data["documents"][0])
         combined_metadatas.extend(data["metadatas"][0])
+        combined_ids.extend(data["ids"][0])
 
-    # Create a list of tuples (distance, document, metadata)
+    # Create the output dictionary
-    combined = list(zip(combined_distances, combined_documents, combined_metadatas))
+    result = {
+        "documents": [combined_documents],
+        "metadatas": [combined_metadatas],
+        "ids": [combined_ids],
+    }
+
+    return result
+
+
+def merge_and_sort_query_results(
+    query_results: list[dict], k: int, reverse: bool = False
+) -> dict:
+    # Initialize lists to store combined data
+    combined = []
+    seen_hashes = set()  # To store unique document hashes
+
+    for data in query_results:
+        distances = data["distances"][0]
+        documents = data["documents"][0]
+        metadatas = data["metadatas"][0]
+
+        for distance, document, metadata in zip(distances, documents, 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 = []
+
+    for collection_name in collection_names:
+        if collection_name:
+            try:
+                result = get_doc(collection_name=collection_name)
+                if result is not None:
+                    results.append(result.model_dump())
+            except Exception as e:
+                log.exception(f"Error when querying the collection: {e}")
+        else:
+            pass
+
+    return merge_get_results(results)
 
 
 def query_collection(
@@ -290,6 +339,7 @@ def get_embedding_function(
 
 
 def get_sources_from_files(
+    request,
     files,
     queries,
     embedding_function,
@@ -297,26 +347,74 @@ def get_sources_from_files(
     reranking_function,
     r,
     hybrid_search,
+    full_context=False,
 ):
-    log.debug(f"files: {files} {queries} {embedding_function} {reranking_function}")
+    log.debug(
+        f"files: {files} {queries} {embedding_function} {reranking_function} {full_context}"
+    )
 
     extracted_collections = []
     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,
+                                }
+                            ]
+                        ],
+                    }
+        else:
             collection_names = []
             if file.get("type") == "collection":
                 if file.get("legacy"):
@@ -336,42 +434,50 @@ def get_sources_from_files(
                 log.debug(f"skipping {file} as it has already been extracted")
                 continue
 
-            try:
+            if full_context:
-                context = None
+                try:
-                if file.get("type") == "text":
+                    context = get_all_items_from_collections(collection_names)
-                    context = file["content"]
+                except Exception as e:
-                else:
+                    log.exception(e)
-                    if hybrid_search:
+
-                        try:
+            else:
-                            context = query_collection_with_hybrid_search(
+                try:
+                    context = None
+                    if file.get("type") == "text":
+                        context = file["content"]
+                    else:
+                        if hybrid_search:
+                            try:
+                                context = query_collection_with_hybrid_search(
+                                    collection_names=collection_names,
+                                    queries=queries,
+                                    embedding_function=embedding_function,
+                                    k=k,
+                                    reranking_function=reranking_function,
+                                    r=r,
+                                )
+                            except Exception as e:
+                                log.debug(
+                                    "Error when using hybrid search, using"
+                                    " non hybrid search as fallback."
+                                )
+
+                        if (not hybrid_search) or (context is None):
+                            context = query_collection(
                                 collection_names=collection_names,
                                 queries=queries,
                                 embedding_function=embedding_function,
                                 k=k,
-                                reranking_function=reranking_function,
-                                r=r,
                             )
-                        except Exception as e:
+                except Exception as e:
-                            log.debug(
+                    log.exception(e)
-                                "Error when using hybrid search, using"
-                                " non hybrid search as fallback."
-                            )
-
-                    if (not hybrid_search) or (context is None):
-                        context = query_collection(
-                            collection_names=collection_names,
-                            queries=queries,
-                            embedding_function=embedding_function,
-                            k=k,
-                        )
-            except Exception as e:
-                log.exception(e)
 
             extracted_collections.extend(collection_names)
 
         if context:
             if "data" in file:
                 del file["data"]
+
             relevant_contexts.append({**context, "file": file})
 
     sources = []
@@ -468,7 +574,7 @@ 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
 
 
@@ -502,7 +608,7 @@ 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/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/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
@@ -10,6 +10,10 @@ 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:
@@ -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/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/utils.py

@@ -1,22 +1,38 @@
-import socket
-import aiohttp
 import asyncio
-import urllib.parse
-import validators
-from typing import Any, AsyncIterator, Dict, Iterator, List, Sequence, Union
-
-
-from langchain_community.document_loaders import (
-    WebBaseLoader,
-)
-from langchain_core.documents import Document
-
-
-from open_webui.constants import ERROR_MESSAGES
-from open_webui.config import ENABLE_RAG_LOCAL_WEB_FETCH
-from open_webui.env import SRC_LOG_LEVELS
-
 import logging
+import socket
+import ssl
+import urllib.parse
+import urllib.request
+from collections import defaultdict
+from datetime import datetime, time, timedelta
+from typing import (
+    Any,
+    AsyncIterator,
+    Dict,
+    Iterator,
+    List,
+    Optional,
+    Sequence,
+    Union,
+    Literal,
+)
+import aiohttp
+import certifi
+import validators
+from langchain_community.document_loaders import PlaywrightURLLoader, WebBaseLoader
+from langchain_community.document_loaders.firecrawl import FireCrawlLoader
+from langchain_community.document_loaders.base import BaseLoader
+from langchain_core.documents import Document
+from open_webui.constants import ERROR_MESSAGES
+from open_webui.config import (
+    ENABLE_RAG_LOCAL_WEB_FETCH,
+    PLAYWRIGHT_WS_URI,
+    RAG_WEB_LOADER_ENGINE,
+    FIRECRAWL_API_BASE_URL,
+    FIRECRAWL_API_KEY,
+)
+from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
@@ -68,6 +84,314 @@ def resolve_hostname(hostname):
     return ipv4_addresses, ipv6_addresses
 
 
+def extract_metadata(soup, url):
+    metadata = {"source": url}
+    if title := soup.find("title"):
+        metadata["title"] = title.get_text()
+    if description := soup.find("meta", attrs={"name": "description"}):
+        metadata["description"] = description.get("content", "No description found.")
+    if html := soup.find("html"):
+        metadata["language"] = html.get("lang", "No language found.")
+    return metadata
+
+
+def verify_ssl_cert(url: str) -> bool:
+    """Verify SSL certificate for the given URL."""
+    if not url.startswith("https://"):
+        return True
+
+    try:
+        hostname = url.split("://")[-1].split("/")[0]
+        context = ssl.create_default_context(cafile=certifi.where())
+        with context.wrap_socket(ssl.socket(), server_hostname=hostname) as s:
+            s.connect((hostname, 443))
+        return True
+    except ssl.SSLError:
+        return False
+    except Exception as e:
+        log.warning(f"SSL verification failed for {url}: {str(e)}")
+        return False
+
+
+class SafeFireCrawlLoader(BaseLoader):
+    def __init__(
+        self,
+        web_paths,
+        verify_ssl: bool = True,
+        trust_env: bool = False,
+        requests_per_second: Optional[float] = None,
+        continue_on_failure: bool = True,
+        api_key: Optional[str] = None,
+        api_url: Optional[str] = None,
+        mode: Literal["crawl", "scrape", "map"] = "crawl",
+        proxy: Optional[Dict[str, str]] = None,
+        params: Optional[Dict] = None,
+    ):
+        """Concurrent document loader for FireCrawl operations.
+
+        Executes multiple FireCrawlLoader instances concurrently using thread pooling
+        to improve bulk processing efficiency.
+        Args:
+            web_paths: List of URLs/paths to process.
+            verify_ssl: If True, verify SSL certificates.
+            trust_env: If True, use proxy settings from environment variables.
+            requests_per_second: Number of requests per second to limit to.
+            continue_on_failure (bool): If True, continue loading other URLs on failure.
+            api_key: API key for FireCrawl service. Defaults to None
+                (uses FIRE_CRAWL_API_KEY environment variable if not provided).
+            api_url: Base URL for FireCrawl API. Defaults to official API endpoint.
+            mode: Operation mode selection:
+                - 'crawl': Website crawling mode (default)
+                - 'scrape': Direct page scraping
+                - 'map': Site map generation
+            proxy: Proxy override settings for the FireCrawl API.
+            params: The parameters to pass to the Firecrawl API.
+                Examples include crawlerOptions.
+                For more details, visit: https://github.com/mendableai/firecrawl-py
+        """
+        proxy_server = proxy.get("server") if proxy else None
+        if trust_env and not proxy_server:
+            env_proxies = urllib.request.getproxies()
+            env_proxy_server = env_proxies.get("https") or env_proxies.get("http")
+            if env_proxy_server:
+                if proxy:
+                    proxy["server"] = env_proxy_server
+                else:
+                    proxy = {"server": env_proxy_server}
+        self.web_paths = web_paths
+        self.verify_ssl = verify_ssl
+        self.requests_per_second = requests_per_second
+        self.last_request_time = None
+        self.trust_env = trust_env
+        self.continue_on_failure = continue_on_failure
+        self.api_key = api_key
+        self.api_url = api_url
+        self.mode = mode
+        self.params = params
+
+    def lazy_load(self) -> Iterator[Document]:
+        """Load documents concurrently using FireCrawl."""
+        for url in self.web_paths:
+            try:
+                self._safe_process_url_sync(url)
+                loader = FireCrawlLoader(
+                    url=url,
+                    api_key=self.api_key,
+                    api_url=self.api_url,
+                    mode=self.mode,
+                    params=self.params,
+                )
+                yield from loader.lazy_load()
+            except Exception as e:
+                if self.continue_on_failure:
+                    log.exception(e, "Error loading %s", url)
+                    continue
+                raise e
+
+    async def alazy_load(self):
+        """Async version of lazy_load."""
+        for url in self.web_paths:
+            try:
+                await self._safe_process_url(url)
+                loader = FireCrawlLoader(
+                    url=url,
+                    api_key=self.api_key,
+                    api_url=self.api_url,
+                    mode=self.mode,
+                    params=self.params,
+                )
+                async for document in loader.alazy_load():
+                    yield document
+            except Exception as e:
+                if self.continue_on_failure:
+                    log.exception(e, "Error loading %s", url)
+                    continue
+                raise e
+
+    def _verify_ssl_cert(self, url: str) -> bool:
+        return verify_ssl_cert(url)
+
+    async def _wait_for_rate_limit(self):
+        """Wait to respect the rate limit if specified."""
+        if self.requests_per_second and self.last_request_time:
+            min_interval = timedelta(seconds=1.0 / self.requests_per_second)
+            time_since_last = datetime.now() - self.last_request_time
+            if time_since_last < min_interval:
+                await asyncio.sleep((min_interval - time_since_last).total_seconds())
+        self.last_request_time = datetime.now()
+
+    def _sync_wait_for_rate_limit(self):
+        """Synchronous version of rate limit wait."""
+        if self.requests_per_second and self.last_request_time:
+            min_interval = timedelta(seconds=1.0 / self.requests_per_second)
+            time_since_last = datetime.now() - self.last_request_time
+            if time_since_last < min_interval:
+                time.sleep((min_interval - time_since_last).total_seconds())
+        self.last_request_time = datetime.now()
+
+    async def _safe_process_url(self, url: str) -> bool:
+        """Perform safety checks before processing a URL."""
+        if self.verify_ssl and not self._verify_ssl_cert(url):
+            raise ValueError(f"SSL certificate verification failed for {url}")
+        await self._wait_for_rate_limit()
+        return True
+
+    def _safe_process_url_sync(self, url: str) -> bool:
+        """Synchronous version of safety checks."""
+        if self.verify_ssl and not self._verify_ssl_cert(url):
+            raise ValueError(f"SSL certificate verification failed for {url}")
+        self._sync_wait_for_rate_limit()
+        return True
+
+
+class SafePlaywrightURLLoader(PlaywrightURLLoader):
+    """Load HTML pages safely with Playwright, supporting SSL verification, rate limiting, and remote browser connection.
+
+    Attributes:
+        web_paths (List[str]): List of URLs to load.
+        verify_ssl (bool): If True, verify SSL certificates.
+        trust_env (bool): If True, use proxy settings from environment variables.
+        requests_per_second (Optional[float]): Number of requests per second to limit to.
+        continue_on_failure (bool): If True, continue loading other URLs on failure.
+        headless (bool): If True, the browser will run in headless mode.
+        proxy (dict): Proxy override settings for the Playwright session.
+        playwright_ws_url (Optional[str]): WebSocket endpoint URI for remote browser connection.
+    """
+
+    def __init__(
+        self,
+        web_paths: List[str],
+        verify_ssl: bool = True,
+        trust_env: bool = False,
+        requests_per_second: Optional[float] = None,
+        continue_on_failure: bool = True,
+        headless: bool = True,
+        remove_selectors: Optional[List[str]] = None,
+        proxy: Optional[Dict[str, str]] = None,
+        playwright_ws_url: Optional[str] = None,
+    ):
+        """Initialize with additional safety parameters and remote browser support."""
+
+        proxy_server = proxy.get("server") if proxy else None
+        if trust_env and not proxy_server:
+            env_proxies = urllib.request.getproxies()
+            env_proxy_server = env_proxies.get("https") or env_proxies.get("http")
+            if env_proxy_server:
+                if proxy:
+                    proxy["server"] = env_proxy_server
+                else:
+                    proxy = {"server": env_proxy_server}
+
+        # We'll set headless to False if using playwright_ws_url since it's handled by the remote browser
+        super().__init__(
+            urls=web_paths,
+            continue_on_failure=continue_on_failure,
+            headless=headless if playwright_ws_url is None else False,
+            remove_selectors=remove_selectors,
+            proxy=proxy,
+        )
+        self.verify_ssl = verify_ssl
+        self.requests_per_second = requests_per_second
+        self.last_request_time = None
+        self.playwright_ws_url = playwright_ws_url
+        self.trust_env = trust_env
+
+    def lazy_load(self) -> Iterator[Document]:
+        """Safely load URLs synchronously with support for remote browser."""
+        from playwright.sync_api import sync_playwright
+
+        with sync_playwright() as p:
+            # Use remote browser if ws_endpoint is provided, otherwise use local browser
+            if self.playwright_ws_url:
+                browser = p.chromium.connect(self.playwright_ws_url)
+            else:
+                browser = p.chromium.launch(headless=self.headless, proxy=self.proxy)
+
+            for url in self.urls:
+                try:
+                    self._safe_process_url_sync(url)
+                    page = browser.new_page()
+                    response = page.goto(url)
+                    if response is None:
+                        raise ValueError(f"page.goto() returned None for url {url}")
+
+                    text = self.evaluator.evaluate(page, browser, response)
+                    metadata = {"source": url}
+                    yield Document(page_content=text, metadata=metadata)
+                except Exception as e:
+                    if self.continue_on_failure:
+                        log.exception(e, "Error loading %s", url)
+                        continue
+                    raise e
+            browser.close()
+
+    async def alazy_load(self) -> AsyncIterator[Document]:
+        """Safely load URLs asynchronously with support for remote browser."""
+        from playwright.async_api import async_playwright
+
+        async with async_playwright() as p:
+            # Use remote browser if ws_endpoint is provided, otherwise use local browser
+            if self.playwright_ws_url:
+                browser = await p.chromium.connect(self.playwright_ws_url)
+            else:
+                browser = await p.chromium.launch(
+                    headless=self.headless, proxy=self.proxy
+                )
+
+            for url in self.urls:
+                try:
+                    await self._safe_process_url(url)
+                    page = await browser.new_page()
+                    response = await page.goto(url)
+                    if response is None:
+                        raise ValueError(f"page.goto() returned None for url {url}")
+
+                    text = await self.evaluator.evaluate_async(page, browser, response)
+                    metadata = {"source": url}
+                    yield Document(page_content=text, metadata=metadata)
+                except Exception as e:
+                    if self.continue_on_failure:
+                        log.exception(e, "Error loading %s", url)
+                        continue
+                    raise e
+            await browser.close()
+
+    def _verify_ssl_cert(self, url: str) -> bool:
+        return verify_ssl_cert(url)
+
+    async def _wait_for_rate_limit(self):
+        """Wait to respect the rate limit if specified."""
+        if self.requests_per_second and self.last_request_time:
+            min_interval = timedelta(seconds=1.0 / self.requests_per_second)
+            time_since_last = datetime.now() - self.last_request_time
+            if time_since_last < min_interval:
+                await asyncio.sleep((min_interval - time_since_last).total_seconds())
+        self.last_request_time = datetime.now()
+
+    def _sync_wait_for_rate_limit(self):
+        """Synchronous version of rate limit wait."""
+        if self.requests_per_second and self.last_request_time:
+            min_interval = timedelta(seconds=1.0 / self.requests_per_second)
+            time_since_last = datetime.now() - self.last_request_time
+            if time_since_last < min_interval:
+                time.sleep((min_interval - time_since_last).total_seconds())
+        self.last_request_time = datetime.now()
+
+    async def _safe_process_url(self, url: str) -> bool:
+        """Perform safety checks before processing a URL."""
+        if self.verify_ssl and not self._verify_ssl_cert(url):
+            raise ValueError(f"SSL certificate verification failed for {url}")
+        await self._wait_for_rate_limit()
+        return True
+
+    def _safe_process_url_sync(self, url: str) -> bool:
+        """Synchronous version of safety checks."""
+        if self.verify_ssl and not self._verify_ssl_cert(url):
+            raise ValueError(f"SSL certificate verification failed for {url}")
+        self._sync_wait_for_rate_limit()
+        return True
+
+
 class SafeWebBaseLoader(WebBaseLoader):
     """WebBaseLoader with enhanced error handling for URLs."""
 
@@ -143,20 +467,12 @@ class SafeWebBaseLoader(WebBaseLoader):
                 text = soup.get_text(**self.bs_get_text_kwargs)
 
                 # Build metadata
-                metadata = {"source": path}
+                metadata = extract_metadata(soup, path)
-                if title := soup.find("title"):
-                    metadata["title"] = title.get_text()
-                if description := soup.find("meta", attrs={"name": "description"}):
-                    metadata["description"] = description.get(
-                        "content", "No description found."
-                    )
-                if html := soup.find("html"):
-                    metadata["language"] = html.get("lang", "No language found.")
 
                 yield Document(page_content=text, metadata=metadata)
             except Exception as e:
                 # Log the error and continue with the next URL
-                log.error(f"Error loading {path}: {e}")
+                log.exception(e, "Error loading %s", path)
 
     async def alazy_load(self) -> AsyncIterator[Document]:
         """Async lazy load text from the url(s) in web_path."""
@@ -179,6 +495,12 @@ class SafeWebBaseLoader(WebBaseLoader):
         return [document async for document in self.alazy_load()]
 
 
+RAG_WEB_LOADER_ENGINES = defaultdict(lambda: SafeWebBaseLoader)
+RAG_WEB_LOADER_ENGINES["playwright"] = SafePlaywrightURLLoader
+RAG_WEB_LOADER_ENGINES["safe_web"] = SafeWebBaseLoader
+RAG_WEB_LOADER_ENGINES["firecrawl"] = SafeFireCrawlLoader
+
+
 def get_web_loader(
     urls: Union[str, Sequence[str]],
     verify_ssl: bool = True,
@@ -188,10 +510,29 @@ def get_web_loader(
     # Check if the URLs are valid
     safe_urls = safe_validate_urls([urls] if isinstance(urls, str) else urls)
 
-    return SafeWebBaseLoader(
+    web_loader_args = {
-        web_path=safe_urls,
+        "web_paths": safe_urls,
-        verify_ssl=verify_ssl,
+        "verify_ssl": verify_ssl,
-        requests_per_second=requests_per_second,
+        "requests_per_second": requests_per_second,
-        continue_on_failure=True,
+        "continue_on_failure": True,
-        trust_env=trust_env,
+        "trust_env": trust_env,
+    }
+
+    if PLAYWRIGHT_WS_URI.value:
+        web_loader_args["playwright_ws_url"] = PLAYWRIGHT_WS_URI.value
+
+    if RAG_WEB_LOADER_ENGINE.value == "firecrawl":
+        web_loader_args["api_key"] = FIRECRAWL_API_KEY.value
+        web_loader_args["api_url"] = FIRECRAWL_API_BASE_URL.value
+
+    # Create the appropriate WebLoader based on the configuration
+    WebLoaderClass = RAG_WEB_LOADER_ENGINES[RAG_WEB_LOADER_ENGINE.value]
+    web_loader = WebLoaderClass(**web_loader_args)
+
+    log.debug(
+        "Using RAG_WEB_LOADER_ENGINE %s for %s URLs",
+        web_loader.__class__.__name__,
+        len(safe_urls),
     )
+
+    return web_loader

backend/open_webui/routers/audio.py

@@ -37,6 +37,7 @@ from open_webui.config import (
 
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import (
+    AIOHTTP_CLIENT_TIMEOUT,
     ENV,
     SRC_LOG_LEVELS,
     DEVICE_TYPE,
@@ -70,7 +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)
@@ -87,7 +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):
@@ -265,8 +266,10 @@ 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() as session:
+            async with aiohttp.ClientSession(
+                timeout=timeout, trust_env=True
+            ) as session:
                 async with session.post(
                     url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
                     json=payload,
@@ -323,7 +326,10 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             )
 
         try:
-            async with aiohttp.ClientSession() as session:
+            timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
+            async with aiohttp.ClientSession(
+                timeout=timeout, trust_env=True
+            ) as session:
                 async with session.post(
                     f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}",
                     json={
@@ -380,7 +386,10 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             data = f"""<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="{locale}">
                 <voice name="{language}">{payload["input"]}</voice>
             </speak>"""
-            async with aiohttp.ClientSession() as session:
+            timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
+            async with aiohttp.ClientSession(
+                timeout=timeout, trust_env=True
+            ) as session:
                 async with session.post(
                     f"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1",
                     headers={
@@ -458,7 +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]
@@ -670,7 +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(
@@ -701,14 +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()
 
@@ -252,14 +251,6 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
             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"
@@ -439,11 +430,6 @@ 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
@@ -546,7 +532,8 @@ async def signout(request: Request, response: Response):
                             if logout_url:
                                 response.delete_cookie("oauth_id_token")
                                 return RedirectResponse(
-                                    url=f"{logout_url}?id_token_hint={oauth_id_token}"
+                                    headers=response.headers,
+                                    url=f"{logout_url}?id_token_hint={oauth_id_token}",
                                 )
                         else:
                             raise HTTPException(
@@ -612,7 +599,7 @@ 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

@@ -75,6 +75,7 @@ class CodeInterpreterConfigForm(BaseModel):
     CODE_EXECUTION_JUPYTER_AUTH: Optional[str]
     CODE_EXECUTION_JUPYTER_AUTH_TOKEN: Optional[str]
     CODE_EXECUTION_JUPYTER_AUTH_PASSWORD: Optional[str]
+    CODE_EXECUTION_JUPYTER_TIMEOUT: Optional[int]
     ENABLE_CODE_INTERPRETER: bool
     CODE_INTERPRETER_ENGINE: str
     CODE_INTERPRETER_PROMPT_TEMPLATE: Optional[str]
@@ -82,6 +83,7 @@ class CodeInterpreterConfigForm(BaseModel):
     CODE_INTERPRETER_JUPYTER_AUTH: Optional[str]
     CODE_INTERPRETER_JUPYTER_AUTH_TOKEN: Optional[str]
     CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD: Optional[str]
+    CODE_INTERPRETER_JUPYTER_TIMEOUT: Optional[int]
 
 
 @router.get("/code_execution", response_model=CodeInterpreterConfigForm)
@@ -92,6 +94,7 @@ async def get_code_execution_config(request: Request, user=Depends(get_admin_use
         "CODE_EXECUTION_JUPYTER_AUTH": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH,
         "CODE_EXECUTION_JUPYTER_AUTH_TOKEN": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH_TOKEN,
         "CODE_EXECUTION_JUPYTER_AUTH_PASSWORD": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD,
+        "CODE_EXECUTION_JUPYTER_TIMEOUT": request.app.state.config.CODE_EXECUTION_JUPYTER_TIMEOUT,
         "ENABLE_CODE_INTERPRETER": request.app.state.config.ENABLE_CODE_INTERPRETER,
         "CODE_INTERPRETER_ENGINE": request.app.state.config.CODE_INTERPRETER_ENGINE,
         "CODE_INTERPRETER_PROMPT_TEMPLATE": request.app.state.config.CODE_INTERPRETER_PROMPT_TEMPLATE,
@@ -99,6 +102,7 @@ async def get_code_execution_config(request: Request, user=Depends(get_admin_use
         "CODE_INTERPRETER_JUPYTER_AUTH": request.app.state.config.CODE_INTERPRETER_JUPYTER_AUTH,
         "CODE_INTERPRETER_JUPYTER_AUTH_TOKEN": request.app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_TOKEN,
         "CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD": request.app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD,
+        "CODE_INTERPRETER_JUPYTER_TIMEOUT": request.app.state.config.CODE_INTERPRETER_JUPYTER_TIMEOUT,
     }
 
 
@@ -120,6 +124,9 @@ async def set_code_execution_config(
     request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD = (
         form_data.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD
     )
+    request.app.state.config.CODE_EXECUTION_JUPYTER_TIMEOUT = (
+        form_data.CODE_EXECUTION_JUPYTER_TIMEOUT
+    )
 
     request.app.state.config.ENABLE_CODE_INTERPRETER = form_data.ENABLE_CODE_INTERPRETER
     request.app.state.config.CODE_INTERPRETER_ENGINE = form_data.CODE_INTERPRETER_ENGINE
@@ -141,6 +148,9 @@ async def set_code_execution_config(
     request.app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD = (
         form_data.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD
     )
+    request.app.state.config.CODE_INTERPRETER_JUPYTER_TIMEOUT = (
+        form_data.CODE_INTERPRETER_JUPYTER_TIMEOUT
+    )
 
     return {
         "CODE_EXECUTION_ENGINE": request.app.state.config.CODE_EXECUTION_ENGINE,
@@ -148,6 +158,7 @@ async def set_code_execution_config(
         "CODE_EXECUTION_JUPYTER_AUTH": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH,
         "CODE_EXECUTION_JUPYTER_AUTH_TOKEN": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH_TOKEN,
         "CODE_EXECUTION_JUPYTER_AUTH_PASSWORD": request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD,
+        "CODE_EXECUTION_JUPYTER_TIMEOUT": request.app.state.config.CODE_EXECUTION_JUPYTER_TIMEOUT,
         "ENABLE_CODE_INTERPRETER": request.app.state.config.ENABLE_CODE_INTERPRETER,
         "CODE_INTERPRETER_ENGINE": request.app.state.config.CODE_INTERPRETER_ENGINE,
         "CODE_INTERPRETER_PROMPT_TEMPLATE": request.app.state.config.CODE_INTERPRETER_PROMPT_TEMPLATE,
@@ -155,6 +166,7 @@ async def set_code_execution_config(
         "CODE_INTERPRETER_JUPYTER_AUTH": request.app.state.config.CODE_INTERPRETER_JUPYTER_AUTH,
         "CODE_INTERPRETER_JUPYTER_AUTH_TOKEN": request.app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_TOKEN,
         "CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD": request.app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD,
+        "CODE_INTERPRETER_JUPYTER_TIMEOUT": request.app.state.config.CODE_INTERPRETER_JUPYTER_TIMEOUT,
     }
 
 

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)
@@ -225,17 +241,24 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
                 filename = file.meta.get("name", file.filename)
                 encoded_filename = quote(filename)  # RFC5987 encoding
 
+                content_type = file.meta.get("content_type")
+                filename = file.meta.get("name", file.filename)
+                encoded_filename = quote(filename)
                 headers = {}
-                if file.meta.get("content_type") not in [
-                    "application/pdf",
-                    "text/plain",
-                ]:
-                    headers = {
-                        **headers,
-                        "Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}",
-                    }
 
-                return FileResponse(file_path, headers=headers)
+                if content_type == "application/pdf" or filename.lower().endswith(
+                    ".pdf"
+                ):
+                    headers["Content-Disposition"] = (
+                        f"inline; filename*=UTF-8''{encoded_filename}"
+                    )
+                    content_type = "application/pdf"
+                elif content_type != "text/plain":
+                    headers["Content-Disposition"] = (
+                        f"attachment; filename*=UTF-8''{encoded_filename}"
+                    )
+
+                return FileResponse(file_path, headers=headers, media_type=content_type)
 
             else:
                 raise HTTPException(
@@ -266,7 +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()
 
@@ -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

@@ -55,6 +55,10 @@ async def get_config(request: Request, user=Depends(get_admin_user)):
             "COMFYUI_WORKFLOW": request.app.state.config.COMFYUI_WORKFLOW,
             "COMFYUI_WORKFLOW_NODES": request.app.state.config.COMFYUI_WORKFLOW_NODES,
         },
+        "gemini": {
+            "GEMINI_API_BASE_URL": request.app.state.config.IMAGES_GEMINI_API_BASE_URL,
+            "GEMINI_API_KEY": request.app.state.config.IMAGES_GEMINI_API_KEY,
+        },
     }
 
 
@@ -78,6 +82,11 @@ class ComfyUIConfigForm(BaseModel):
     COMFYUI_WORKFLOW_NODES: list[dict]
 
 
+class GeminiConfigForm(BaseModel):
+    GEMINI_API_BASE_URL: str
+    GEMINI_API_KEY: str
+
+
 class ConfigForm(BaseModel):
     enabled: bool
     engine: str
@@ -85,6 +94,7 @@ class ConfigForm(BaseModel):
     openai: OpenAIConfigForm
     automatic1111: Automatic1111ConfigForm
     comfyui: ComfyUIConfigForm
+    gemini: GeminiConfigForm
 
 
 @router.post("/config/update")
@@ -103,6 +113,11 @@ async def update_config(
     )
     request.app.state.config.IMAGES_OPENAI_API_KEY = form_data.openai.OPENAI_API_KEY
 
+    request.app.state.config.IMAGES_GEMINI_API_BASE_URL = (
+        form_data.gemini.GEMINI_API_BASE_URL
+    )
+    request.app.state.config.IMAGES_GEMINI_API_KEY = form_data.gemini.GEMINI_API_KEY
+
     request.app.state.config.AUTOMATIC1111_BASE_URL = (
         form_data.automatic1111.AUTOMATIC1111_BASE_URL
     )
@@ -129,6 +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
@@ -155,6 +172,10 @@ async def update_config(
             "COMFYUI_WORKFLOW": request.app.state.config.COMFYUI_WORKFLOW,
             "COMFYUI_WORKFLOW_NODES": request.app.state.config.COMFYUI_WORKFLOW_NODES,
         },
+        "gemini": {
+            "GEMINI_API_BASE_URL": request.app.state.config.IMAGES_GEMINI_API_BASE_URL,
+            "GEMINI_API_KEY": request.app.state.config.IMAGES_GEMINI_API_KEY,
+        },
     }
 
 
@@ -184,9 +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
@@ -224,6 +253,12 @@ def get_image_model(request):
             if request.app.state.config.IMAGE_GENERATION_MODEL
             else "dall-e-2"
         )
+    elif request.app.state.config.IMAGE_GENERATION_ENGINE == "gemini":
+        return (
+            request.app.state.config.IMAGE_GENERATION_MODEL
+            if request.app.state.config.IMAGE_GENERATION_MODEL
+            else "imagen-3.0-generate-002"
+        )
     elif request.app.state.config.IMAGE_GENERATION_ENGINE == "comfyui":
         return (
             request.app.state.config.IMAGE_GENERATION_MODEL
@@ -299,6 +334,10 @@ def get_models(request: Request, user=Depends(get_verified_user)):
                 {"id": "dall-e-2", "name": "DALL·E 2"},
                 {"id": "dall-e-3", "name": "DALL·E 3"},
             ]
+        elif request.app.state.config.IMAGE_GENERATION_ENGINE == "gemini":
+            return [
+                {"id": "imagen-3-0-generate-002", "name": "imagen-3.0 generate-002"},
+            ]
         elif request.app.state.config.IMAGE_GENERATION_ENGINE == "comfyui":
             # TODO - get models from comfyui
             headers = {
@@ -322,7 +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"
                 ]:
@@ -483,6 +522,41 @@ async def image_generations(
                 images.append({"url": url})
             return images
 
+        elif request.app.state.config.IMAGE_GENERATION_ENGINE == "gemini":
+            headers = {}
+            headers["Content-Type"] = "application/json"
+            headers["x-goog-api-key"] = request.app.state.config.IMAGES_GEMINI_API_KEY
+
+            model = get_image_model(request)
+            data = {
+                "instances": {"prompt": form_data.prompt},
+                "parameters": {
+                    "sampleCount": form_data.n,
+                    "outputOptions": {"mimeType": "image/png"},
+                },
+            }
+
+            # Use asyncio.to_thread for the requests.post call
+            r = await asyncio.to_thread(
+                requests.post,
+                url=f"{request.app.state.config.IMAGES_GEMINI_API_BASE_URL}/models/{model}:predict",
+                json=data,
+                headers=headers,
+            )
+
+            r.raise_for_status()
+            res = r.json()
+
+            images = []
+            for image in res["predictions"]:
+                image_data, content_type = load_b64_image_data(
+                    image["bytesBase64Encoded"]
+                )
+                url = upload_image(request, data, image_data, content_type, user)
+                images.append({"url": url})
+
+            return images
+
         elif request.app.state.config.IMAGE_GENERATION_ENGINE == "comfyui":
             data = {
                 "prompt": form_data.prompt,

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,
@@ -26,7 +31,7 @@ from fastapi import (
 )
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, validator
 from starlette.background import BackgroundTask
 
 
@@ -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)
     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()
@@ -191,7 +221,19 @@ async def verify_connection(
         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
@@ -931,15 +1041,29 @@ 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,
     )
 
 
 class ChatMessage(BaseModel):
     role: str
-    content: str
+    content: Optional[str] = None
     tool_calls: Optional[list[dict]] = None
     images: Optional[list[str]] = None
 
+    @validator("content", pre=True)
+    @classmethod
+    def check_at_least_one_field(cls, field_value, values, **kwargs):
+        # Raise an error if both 'content' and 'tool_calls' are None
+        if field_value is None and (
+            "tool_calls" not in values or values["tool_calls"] is None
+        ):
+            raise ValueError(
+                "At least one of 'content' or 'tool_calls' must be provided"
+            )
+
+        return field_value
+
 
 class GenerateChatCompletionForm(BaseModel):
     model: str
@@ -1047,6 +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,
     )
 
 
@@ -1149,6 +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,
     )
 
 
@@ -1227,6 +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,
     )
 
 
@@ -1240,7 +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

@@ -26,6 +26,7 @@ from open_webui.env import (
     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)
     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
 
@@ -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:
@@ -418,7 +441,7 @@ 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]
@@ -515,6 +538,16 @@ 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 +620,7 @@ 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 +810,7 @@ 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

@@ -351,10 +351,17 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
     return {
         "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,
@@ -372,10 +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,
@@ -398,6 +406,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
                 "bing_search_v7_subscription_key": request.app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
                 "exa_api_key": request.app.state.config.EXA_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,
             },
@@ -410,9 +419,15 @@ 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):
@@ -459,12 +474,15 @@ 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
@@ -482,24 +500,51 @@ async def update_rag_config(
         else request.app.state.config.PDF_EXTRACT_IMAGES
     )
 
+    request.app.state.config.RAG_FULL_CONTEXT = (
+        form_data.RAG_FULL_CONTEXT
+        if form_data.RAG_FULL_CONTEXT is not None
+        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
@@ -520,8 +565,8 @@ 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 = (
@@ -588,6 +633,8 @@ async def update_rag_config(
     return {
         "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,
@@ -595,6 +642,10 @@ 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,
@@ -608,7 +659,7 @@ 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,
@@ -871,7 +922,12 @@ 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(
@@ -928,6 +984,8 @@ 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
@@ -970,36 +1028,45 @@ 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):
@@ -1359,9 +1426,11 @@ 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,
@@ -1369,7 +1438,6 @@ async def process_web_search(
                     }
                     for doc in docs
                 ],
-                "filenames": urls,
                 "loaded_count": len(docs),
             }
         else:
@@ -1544,11 +1612,11 @@ 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()
@@ -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()
 
 
@@ -56,6 +61,7 @@ async def execute_code(
                 if request.app.state.config.CODE_EXECUTION_JUPYTER_AUTH == "password"
                 else None
             ),
+            request.app.state.config.CODE_EXECUTION_JUPYTER_TIMEOUT,
         )
 
         return output
@@ -95,7 +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/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,
@@ -13,14 +15,27 @@ 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,
+    AZURE_STORAGE_CONTAINER_NAME,
+    AZURE_STORAGE_KEY,
     STORAGE_PROVIDER,
     UPLOAD_DIR,
 )
 from google.cloud import storage
 from google.cloud.exceptions import GoogleCloudError, NotFound
 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):
@@ -65,7 +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:
@@ -79,9 +94,9 @@ 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):
@@ -92,6 +107,12 @@ class S3StorageProvider(StorageProvider):
             endpoint_url=S3_ENDPOINT_URL,
             aws_access_key_id=S3_ACCESS_KEY_ID,
             aws_secret_access_key=S3_SECRET_ACCESS_KEY,
+            config=Config(
+                s3={
+                    "use_accelerate_endpoint": S3_USE_ACCELERATE_ENDPOINT,
+                    "addressing_style": S3_ADDRESSING_STYLE,
+                },
+            ),
         )
         self.bucket_name = S3_BUCKET_NAME
         self.key_prefix = S3_KEY_PREFIX if S3_KEY_PREFIX else ""
@@ -221,6 +242,74 @@ class GCSStorageProvider(StorageProvider):
         LocalStorageProvider.delete_all_files()
 
 
+class AzureStorageProvider(StorageProvider):
+    def __init__(self):
+        self.endpoint = AZURE_STORAGE_ENDPOINT
+        self.container_name = AZURE_STORAGE_CONTAINER_NAME
+        storage_key = AZURE_STORAGE_KEY
+
+        if storage_key:
+            # Configure using the Azure Storage Account Endpoint and Key
+            self.blob_service_client = BlobServiceClient(
+                account_url=self.endpoint, credential=storage_key
+            )
+        else:
+            # Configure using the Azure Storage Account Endpoint and DefaultAzureCredential
+            # If the key is not configured, then the DefaultAzureCredential will be used to support Managed Identity authentication
+            self.blob_service_client = BlobServiceClient(
+                account_url=self.endpoint, credential=DefaultAzureCredential()
+            )
+        self.container_client = self.blob_service_client.get_container_client(
+            self.container_name
+        )
+
+    def upload_file(self, file: BinaryIO, filename: str) -> Tuple[bytes, str]:
+        """Handles uploading of the file to Azure Blob Storage."""
+        contents, file_path = LocalStorageProvider.upload_file(file, filename)
+        try:
+            blob_client = self.container_client.get_blob_client(filename)
+            blob_client.upload_blob(contents, overwrite=True)
+            return contents, f"{self.endpoint}/{self.container_name}/{filename}"
+        except Exception as e:
+            raise RuntimeError(f"Error uploading file to Azure Blob Storage: {e}")
+
+    def get_file(self, file_path: str) -> str:
+        """Handles downloading of the file from Azure Blob Storage."""
+        try:
+            filename = file_path.split("/")[-1]
+            local_file_path = f"{UPLOAD_DIR}/{filename}"
+            blob_client = self.container_client.get_blob_client(filename)
+            with open(local_file_path, "wb") as download_file:
+                download_file.write(blob_client.download_blob().readall())
+            return local_file_path
+        except ResourceNotFoundError as e:
+            raise RuntimeError(f"Error downloading file from Azure Blob Storage: {e}")
+
+    def delete_file(self, file_path: str) -> None:
+        """Handles deletion of the file from Azure Blob Storage."""
+        try:
+            filename = file_path.split("/")[-1]
+            blob_client = self.container_client.get_blob_client(filename)
+            blob_client.delete_blob()
+        except ResourceNotFoundError as e:
+            raise RuntimeError(f"Error deleting file from Azure Blob Storage: {e}")
+
+        # Always delete from local storage
+        LocalStorageProvider.delete_file(file_path)
+
+    def delete_all_files(self) -> None:
+        """Handles deletion of all files from Azure Blob Storage."""
+        try:
+            blobs = self.container_client.list_blobs()
+            for blob in blobs:
+                self.container_client.delete_blob(blob.name)
+        except Exception as e:
+            raise RuntimeError(f"Error deleting all files from Azure Blob Storage: {e}")
+
+        # Always delete from local storage
+        LocalStorageProvider.delete_all_files()
+
+
 def get_storage_provider(storage_provider: str):
     if storage_provider == "local":
         Storage = LocalStorageProvider()
@@ -228,6 +317,8 @@ def get_storage_provider(storage_provider: str):
         Storage = S3StorageProvider()
     elif storage_provider == "gcs":
         Storage = GCSStorageProvider()
+    elif storage_provider == "azure":
+        Storage = AzureStorageProvider()
     else:
         raise RuntimeError(f"Unsupported storage provider: {storage_provider}")
     return Storage

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

@@ -7,6 +7,8 @@ from moto import mock_aws
 from open_webui.storage import provider
 from gcp_storage_emulator.server import create_server
 from google.cloud import storage
+from azure.storage.blob import BlobServiceClient, ContainerClient, BlobClient
+from unittest.mock import MagicMock
 
 
 def mock_upload_dir(monkeypatch, tmp_path):
@@ -22,6 +24,7 @@ def test_imports():
     provider.LocalStorageProvider
     provider.S3StorageProvider
     provider.GCSStorageProvider
+    provider.AzureStorageProvider
     provider.Storage
 
 
@@ -32,6 +35,8 @@ def test_get_storage_provider():
     assert isinstance(Storage, provider.S3StorageProvider)
     Storage = provider.get_storage_provider("gcs")
     assert isinstance(Storage, provider.GCSStorageProvider)
+    Storage = provider.get_storage_provider("azure")
+    assert isinstance(Storage, provider.AzureStorageProvider)
     with pytest.raises(RuntimeError):
         provider.get_storage_provider("invalid")
 
@@ -48,6 +53,7 @@ def test_class_instantiation():
     provider.LocalStorageProvider()
     provider.S3StorageProvider()
     provider.GCSStorageProvider()
+    provider.AzureStorageProvider()
 
 
 class TestLocalStorageProvider:
@@ -272,3 +278,147 @@ class TestGCSStorageProvider:
         assert not (upload_dir / self.filename_extra).exists()
         assert self.Storage.bucket.get_blob(self.filename) == None
         assert self.Storage.bucket.get_blob(self.filename_extra) == None
+
+
+class TestAzureStorageProvider:
+    def __init__(self):
+        super().__init__()
+
+    @pytest.fixture(scope="class")
+    def setup_storage(self, monkeypatch):
+        # Create mock Blob Service Client and related clients
+        mock_blob_service_client = MagicMock()
+        mock_container_client = MagicMock()
+        mock_blob_client = MagicMock()
+
+        # Set up return values for the mock
+        mock_blob_service_client.get_container_client.return_value = (
+            mock_container_client
+        )
+        mock_container_client.get_blob_client.return_value = mock_blob_client
+
+        # Monkeypatch the Azure classes to return our mocks
+        monkeypatch.setattr(
+            azure.storage.blob,
+            "BlobServiceClient",
+            lambda *args, **kwargs: mock_blob_service_client,
+        )
+        monkeypatch.setattr(
+            azure.storage.blob,
+            "ContainerClient",
+            lambda *args, **kwargs: mock_container_client,
+        )
+        monkeypatch.setattr(
+            azure.storage.blob, "BlobClient", lambda *args, **kwargs: mock_blob_client
+        )
+
+        self.Storage = provider.AzureStorageProvider()
+        self.Storage.endpoint = "https://myaccount.blob.core.windows.net"
+        self.Storage.container_name = "my-container"
+        self.file_content = b"test content"
+        self.filename = "test.txt"
+        self.filename_extra = "test_extra.txt"
+        self.file_bytesio_empty = io.BytesIO()
+
+        # Apply mocks to the Storage instance
+        self.Storage.blob_service_client = mock_blob_service_client
+        self.Storage.container_client = mock_container_client
+
+    def test_upload_file(self, monkeypatch, tmp_path):
+        upload_dir = mock_upload_dir(monkeypatch, tmp_path)
+
+        # Simulate an error when container does not exist
+        self.Storage.container_client.get_blob_client.side_effect = Exception(
+            "Container does not exist"
+        )
+        with pytest.raises(Exception):
+            self.Storage.upload_file(io.BytesIO(self.file_content), self.filename)
+
+        # Reset side effect and create container
+        self.Storage.container_client.get_blob_client.side_effect = None
+        self.Storage.create_container()
+        contents, azure_file_path = self.Storage.upload_file(
+            io.BytesIO(self.file_content), self.filename
+        )
+
+        # Assertions
+        self.Storage.container_client.get_blob_client.assert_called_with(self.filename)
+        self.Storage.container_client.get_blob_client().upload_blob.assert_called_once_with(
+            self.file_content, overwrite=True
+        )
+        assert contents == self.file_content
+        assert (
+            azure_file_path
+            == f"https://myaccount.blob.core.windows.net/{self.Storage.container_name}/{self.filename}"
+        )
+        assert (upload_dir / self.filename).exists()
+        assert (upload_dir / self.filename).read_bytes() == self.file_content
+
+        with pytest.raises(ValueError):
+            self.Storage.upload_file(self.file_bytesio_empty, self.filename)
+
+    def test_get_file(self, monkeypatch, tmp_path):
+        upload_dir = mock_upload_dir(monkeypatch, tmp_path)
+        self.Storage.create_container()
+
+        # Mock upload behavior
+        self.Storage.upload_file(io.BytesIO(self.file_content), self.filename)
+        # Mock blob download behavior
+        self.Storage.container_client.get_blob_client().download_blob().readall.return_value = (
+            self.file_content
+        )
+
+        file_url = f"https://myaccount.blob.core.windows.net/{self.Storage.container_name}/{self.filename}"
+        file_path = self.Storage.get_file(file_url)
+
+        assert file_path == str(upload_dir / self.filename)
+        assert (upload_dir / self.filename).exists()
+        assert (upload_dir / self.filename).read_bytes() == self.file_content
+
+    def test_delete_file(self, monkeypatch, tmp_path):
+        upload_dir = mock_upload_dir(monkeypatch, tmp_path)
+        self.Storage.create_container()
+
+        # Mock file upload
+        self.Storage.upload_file(io.BytesIO(self.file_content), self.filename)
+        # Mock deletion
+        self.Storage.container_client.get_blob_client().delete_blob.return_value = None
+
+        file_url = f"https://myaccount.blob.core.windows.net/{self.Storage.container_name}/{self.filename}"
+        self.Storage.delete_file(file_url)
+
+        self.Storage.container_client.get_blob_client().delete_blob.assert_called_once()
+        assert not (upload_dir / self.filename).exists()
+
+    def test_delete_all_files(self, monkeypatch, tmp_path):
+        upload_dir = mock_upload_dir(monkeypatch, tmp_path)
+        self.Storage.create_container()
+
+        # Mock file uploads
+        self.Storage.upload_file(io.BytesIO(self.file_content), self.filename)
+        self.Storage.upload_file(io.BytesIO(self.file_content), self.filename_extra)
+
+        # Mock listing and deletion behavior
+        self.Storage.container_client.list_blobs.return_value = [
+            {"name": self.filename},
+            {"name": self.filename_extra},
+        ]
+        self.Storage.container_client.get_blob_client().delete_blob.return_value = None
+
+        self.Storage.delete_all_files()
+
+        self.Storage.container_client.list_blobs.assert_called_once()
+        self.Storage.container_client.get_blob_client().delete_blob.assert_any_call()
+        assert not (upload_dir / self.filename).exists()
+        assert not (upload_dir / self.filename_extra).exists()
+
+    def test_get_file_not_found(self, monkeypatch):
+        self.Storage.create_container()
+
+        file_url = f"https://myaccount.blob.core.windows.net/{self.Storage.container_name}/{self.filename}"
+        # Mock behavior to raise an error for missing blobs
+        self.Storage.container_client.get_blob_client().download_blob.side_effect = (
+            Exception("Blob not found")
+        )
+        with pytest.raises(Exception, match="Blob not found"):
+            self.Storage.get_file(file_url)

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

@@ -5,6 +5,7 @@ import base64
 import hmac
 import hashlib
 import requests
+import os
 
 
 from datetime import UTC, datetime, timedelta
@@ -13,15 +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.config import override_static
+from open_webui.env import (
-from open_webui.env import WEBUI_SECRET_KEY, TRUSTED_SIGNATURE_KEY
+    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"
@@ -47,6 +55,19 @@ def verify_signature(payload: str, signature: str) -> bool:
         return False
 
 
+def override_static(path: str, content: str):
+    # Ensure path is safe
+    if "/" in path or ".." in path:
+        log.error(f"Invalid path: {path}")
+        return
+
+    file_path = os.path.join(STATIC_DIR, path)
+    os.makedirs(os.path.dirname(file_path), exist_ok=True)
+
+    with open(file_path, "wb") as f:
+        f.write(base64.b64decode(content))  # Convert Base64 back to raw binary
+
+
 def get_license_data(app, key):
     if key:
         try:
@@ -69,11 +90,11 @@ def get_license_data(app, key):
 
                 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
 
 
@@ -129,6 +150,7 @@ 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
@@ -181,7 +203,10 @@ 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
@@ -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 = {
@@ -351,7 +351,7 @@ 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 +432,7 @@ 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/filter.py

@@ -1,6 +1,12 @@
 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):
@@ -61,7 +67,12 @@ async def process_filter_functions(
         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 +91,7 @@ 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 +100,7 @@ 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

@@ -321,89 +321,95 @@ async def chat_web_search_handler(
         )
         return form_data
 
-    searchQuery = queries[0]
+    all_results = []
 
-    await event_emitter(
+    for searchQuery in queries:
-        {
+        await event_emitter(
-            "type": "status",
+            {
-            "data": {
+                "type": "status",
-                "action": "web_search",
+                "data": {
-                "description": 'Searching "{{searchQuery}}"',
+                    "action": "web_search",
-                "query": searchQuery,
+                    "description": 'Searching "{{searchQuery}}"',
-                "done": False,
-            },
-        }
-    )
-
-    try:
-
-        results = await process_web_search(
-            request,
-            SearchForm(
-                **{
                     "query": searchQuery,
-                }
+                    "done": False,
-            ),
+                },
-            user,
+            }
         )
 
-        if results:
+        try:
-            await event_emitter(
+            results = await process_web_search(
-                {
+                request,
-                    "type": "status",
+                SearchForm(
-                    "data": {
+                    **{
-                        "action": "web_search",
-                        "description": "Searched {{count}} sites",
                         "query": searchQuery,
-                        "urls": results["filenames"],
+                    }
-                        "done": True,
+                ),
-                    },
+                user=user,
-                }
             )
 
-            files = form_data.get("files", [])
+            if results:
+                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(
+                    files.append(
-                    {
+                        {
-                        "docs": results.get("docs", []),
+                            "collection_name": results["collection_name"],
-                        "name": searchQuery,
+                            "name": searchQuery,
-                        "type": "web_search_docs",
+                            "type": "web_search",
-                        "urls": results["filenames"],
+                            "urls": results["filenames"],
-                    }
+                        }
-                )
+                    )
-            else:
+                elif results.get("docs"):
-                files.append(
+                    files.append(
-                    {
+                        {
-                        "collection_name": results["collection_name"],
+                            "docs": results.get("docs", []),
-                        "name": searchQuery,
+                            "name": searchQuery,
-                        "type": "web_search_results",
+                            "type": "web_search",
-                        "urls": results["filenames"],
+                            "urls": results["filenames"],
-                    }
+                        }
-                )
+                    )
-            form_data["files"] = files
+
-        else:
+                form_data["files"] = files
+        except Exception as e:
+            log.exception(e)
             await event_emitter(
                 {
                     "type": "status",
                     "data": {
                         "action": "web_search",
-                        "description": "No search results found",
+                        "description": 'Error searching "{{searchQuery}}"',
                         "query": searchQuery,
                         "done": True,
                         "error": True,
                     },
                 }
             )
-    except Exception as e:
+
-        log.exception(e)
+    if all_results:
+        urls = []
+        for results in all_results:
+            if "filenames" in results:
+                urls.extend(results["filenames"])
+
         await event_emitter(
             {
                 "type": "status",
                 "data": {
                     "action": "web_search",
-                    "description": 'Error searching "{{searchQuery}}"',
+                    "description": "Searched {{count}} sites",
-                    "query": searchQuery,
+                    "urls": urls,
+                    "done": True,
+                },
+            }
+        )
+    else:
+        await event_emitter(
+            {
+                "type": "status",
+                "data": {
+                    "action": "web_search",
+                    "description": "No search results found",
                     "done": True,
                     "error": True,
                 },
@@ -513,6 +519,7 @@ async def chat_completion_files_handler(
     sources = []
 
     if files := body.get("metadata", {}).get("files", None):
+        queries = []
         try:
             queries_response = await generate_queries(
                 request,
@@ -538,8 +545,8 @@ 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"])]
@@ -551,6 +558,7 @@ 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(
@@ -560,9 +568,9 @@ async def chat_completion_files_handler(
                         reranking_function=request.app.state.rf,
                         r=request.app.state.config.RELEVANCE_THRESHOLD,
                         hybrid_search=request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
+                        full_context=request.app.state.config.RAG_FULL_CONTEXT,
                     ),
                 )
-
         except Exception as e:
             log.exception(e)
 
@@ -733,6 +741,7 @@ 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())
@@ -790,8 +799,6 @@ 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"
@@ -1043,6 +1050,21 @@ 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__": metadata.get("model"),
+    }
+    filter_ids = get_sorted_filter_ids(form_data.get("model"))
+
     # Streaming response
     if event_emitter and event_caller:
         task_id = str(uuid4())  # Create a unique task ID.
@@ -1122,12 +1144,12 @@ 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'
 
@@ -1223,9 +1245,9 @@ 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 = (
@@ -1258,7 +1280,8 @@ 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(),
@@ -1270,9 +1293,10 @@ 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):
@@ -1280,7 +1304,7 @@ 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()
@@ -1345,7 +1369,7 @@ 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,
@@ -1359,7 +1383,15 @@ async def process_chat_response(
 
             tool_calls = []
 
-            last_assistant_message = get_last_assistant_message(form_data["messages"])
+            last_assistant_message = None
+            try:
+                if form_data["messages"][-1]["role"] == "assistant":
+                    last_assistant_message = get_last_assistant_message(
+                        form_data["messages"]
+                    )
+            except Exception as e:
+                pass
+
             content = (
                 message.get("content", "")
                 if message
@@ -1375,19 +1407,24 @@ 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:
@@ -1431,119 +1468,154 @@ 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_ids=filter_ids,
-                                    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
+
+                                    delta = choices[0].get("delta", {})
+                                    delta_tool_calls = delta.get("tool_calls", None)
+
+                                    if delta_tool_calls:
+                                        for delta_tool_call in delta_tool_calls:
+                                            tool_call_index = delta_tool_call.get(
+                                                "index"
+                                            )
+
+                                            if tool_call_index is not None:
+                                                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
                                         )
 
-                                    if DETECT_CODE_INTERPRETER:
+                                        if DETECT_REASONING:
-                                        content, content_blocks, end = (
+                                            content, content_blocks, _ = (
-                                            tag_content_handler(
+                                                tag_content_handler(
-                                                "code_interpreter",
+                                                    "reasoning",
-                                                code_interpreter_tags,
+                                                    reasoning_tags,
-                                                content,
+                                                    content,
-                                                content_blocks,
+                                                    content_blocks,
+                                                )
                                             )
-                                        )
 
-                                        if end:
+                                        if DETECT_CODE_INTERPRETER:
-                                            break
+                                            content, content_blocks, end = (
+                                                tag_content_handler(
+                                                    "code_interpreter",
+                                                    code_interpreter_tags,
+                                                    content,
+                                                    content_blocks,
+                                                )
+                                            )
 
-                                    if ENABLE_REALTIME_CHAT_SAVE:
+                                            if end:
-                                        # Save message in the database
+                                                break
-                                        Chats.upsert_message_to_chat_by_id_and_message_id(
+
-                                            metadata["chat_id"],
+                                        if DETECT_SOLUTION:
-                                            metadata["message_id"],
+                                            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
                                                 ),
-                                            },
+                                            }
-                                        )
-                                    else:
-                                        data = {
-                                            "content": serialize_content_blocks(
-                                                content_blocks
-                                            ),
-                                        }
 
-                            await event_emitter(
+                                await event_emitter(
-                                {
+                                    {
-                                    "type": "chat:completion",
+                                        "type": "chat:completion",
-                                    "data": data,
+                                        "data": data,
-                                }
+                                    }
-                            )
+                                )
                         except Exception as e:
                             done = "data: [DONE]" in line
                             if done:
@@ -1748,6 +1820,7 @@ async def process_chat_response(
                                             == "password"
                                             else None
                                         ),
+                                        request.app.state.config.CODE_INTERPRETER_JUPYTER_TIMEOUT,
                                     )
                                 else:
                                     output = {
@@ -1841,7 +1914,10 @@ 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(
@@ -1912,7 +1988,7 @@ 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:
@@ -1933,17 +2009,34 @@ 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_ids=filter_ids,
+                    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_ids=filter_ids,
+                    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 +2,17 @@ import hashlib
 import re
 import time
 import uuid
+import logging
 from datetime import timedelta
 from pathlib import Path
 from typing import Callable, Optional
 
 
 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 +417,7 @@ 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

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

@@ -140,7 +140,14 @@ class OAuthManager:
         log.debug("Running OAUTH Group management")
         oauth_claim = auth_manager_config.OAUTH_GROUPS_CLAIM
 
-        user_oauth_groups: list[str] = user_data.get(oauth_claim, list())
+        # Nested claim search for groups claim
+        if oauth_claim:
+            claim_data = user_data
+            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 []
+
         user_current_groups: list[GroupModel] = Groups.get_groups_by_member_id(user.id)
         all_available_groups: list[GroupModel] = Groups.get_groups()
 
@@ -239,11 +246,46 @@ class OAuthManager:
             raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
         provider_sub = f"{provider}@{sub}"
         email_claim = auth_manager_config.OAUTH_EMAIL_CLAIM
-        email = user_data.get(email_claim, "").lower()
+        email = user_data.get(email_claim, "")
         # We currently mandate that email addresses are provided
         if not email:
-            log.warning(f"OAuth callback failed, email is missing: {user_data}")
+            # If the provider is GitHub,and public email is not provided, we can use the access token to fetch the user's email
-            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+            if provider == "github":
+                try:
+                    access_token = token.get("access_token")
+                    headers = {"Authorization": f"Bearer {access_token}"}
+                    async with aiohttp.ClientSession() as session:
+                        async with session.get(
+                            "https://api.github.com/user/emails", headers=headers
+                        ) as resp:
+                            if resp.ok:
+                                emails = await resp.json()
+                                # use the primary email as the user's email
+                                primary_email = next(
+                                    (e["email"] for e in emails if e.get("primary")),
+                                    None,
+                                )
+                                if primary_email:
+                                    email = primary_email
+                                else:
+                                    log.warning(
+                                        "No primary email found in GitHub response"
+                                    )
+                                    raise HTTPException(
+                                        400, detail=ERROR_MESSAGES.INVALID_CRED
+                                    )
+                            else:
+                                log.warning("Failed to fetch GitHub email")
+                                raise HTTPException(
+                                    400, detail=ERROR_MESSAGES.INVALID_CRED
+                                )
+                except Exception as e:
+                    log.warning(f"Error fetching GitHub email: {e}")
+                    raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+            else:
+                log.warning(f"OAuth callback failed, email is missing: {user_data}")
+                raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+        email = email.lower()
         if (
             "*" not in auth_manager_config.OAUTH_ALLOWED_DOMAINS
             and email.split("@")[-1] not in auth_manager_config.OAUTH_ALLOWED_DOMAINS
@@ -273,21 +315,10 @@ 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
-                existing_user = Users.get_user_by_email(
+                existing_user = Users.get_user_by_email(email)
-                    user_data.get("email", "").lower()
-                )
                 if existing_user:
                     raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
 

backend/open_webui/utils/payload.py

@@ -4,6 +4,7 @@ from open_webui.utils.misc import (
 )
 
 from typing import Callable, Optional
+import json
 
 
 # inplace function: form_data is modified
@@ -66,38 +67,49 @@ def apply_model_params_to_body_openai(params: dict, form_data: dict) -> dict:
 
 
 def apply_model_params_to_body_ollama(params: dict, form_data: dict) -> dict:
-    opts = [
+    # Convert OpenAI parameter names to Ollama parameter names if needed.
-        "temperature",
-        "top_p",
-        "seed",
-        "mirostat",
-        "mirostat_eta",
-        "mirostat_tau",
-        "num_ctx",
-        "num_batch",
-        "num_keep",
-        "repeat_last_n",
-        "tfs_z",
-        "top_k",
-        "min_p",
-        "use_mmap",
-        "use_mlock",
-        "num_thread",
-        "num_gpu",
-    ]
-    mappings = {i: lambda x: x for i in opts}
-    form_data = apply_model_params_to_body(params, form_data, mappings)
-
     name_differences = {
         "max_tokens": "num_predict",
-        "frequency_penalty": "repeat_penalty",
     }
 
     for key, value in name_differences.items():
         if (param := params.get(key, None)) is not None:
-            form_data[value] = param
+            # Copy the parameter to new name then delete it, to prevent Ollama warning of invalid option provided
+            params[value] = params[key]
+            del params[key]
 
-    return form_data
+    # See https://github.com/ollama/ollama/blob/main/docs/api.md#request-8
+    mappings = {
+        "temperature": float,
+        "top_p": float,
+        "seed": lambda x: x,
+        "mirostat": int,
+        "mirostat_eta": float,
+        "mirostat_tau": float,
+        "num_ctx": int,
+        "num_batch": int,
+        "num_keep": int,
+        "num_predict": int,
+        "repeat_last_n": int,
+        "top_k": int,
+        "min_p": float,
+        "typical_p": float,
+        "repeat_penalty": float,
+        "presence_penalty": float,
+        "frequency_penalty": float,
+        "penalize_newline": bool,
+        "stop": lambda x: [bytes(s, "utf-8").decode("unicode_escape") for s in x],
+        "numa": bool,
+        "num_gpu": int,
+        "main_gpu": int,
+        "low_vram": bool,
+        "vocab_only": bool,
+        "use_mmap": bool,
+        "use_mlock": bool,
+        "num_thread": int,
+    }
+
+    return apply_model_params_to_body(params, form_data, mappings)
 
 
 def convert_messages_openai_to_ollama(messages: list[dict]) -> list[dict]:
@@ -108,11 +120,38 @@ def convert_messages_openai_to_ollama(messages: list[dict]) -> list[dict]:
         new_message = {"role": message["role"]}
 
         content = message.get("content", [])
+        tool_calls = message.get("tool_calls", None)
+        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
+
+            # If message is a tool call, add the tool call id to the message
+            if tool_call_id:
+                new_message["tool_call_id"] = tool_call_id
+
+        elif tool_calls:
+            # If tool calls are present, add them to the message
+            ollama_tool_calls = []
+            for tool_call in tool_calls:
+                ollama_tool_call = {
+                    "index": tool_call.get("index", 0),
+                    "id": tool_call.get("id", None),
+                    "function": {
+                        "name": tool_call.get("function", {}).get("name", ""),
+                        "arguments": json.loads(
+                            tool_call.get("function", {}).get("arguments", {})
+                        ),
+                    },
+                }
+                ollama_tool_calls.append(ollama_tool_call)
+            new_message["tool_calls"] = ollama_tool_calls
+
+            # Put the content to empty string (Ollama requires an empty string for tool calls)
+            new_message["content"] = ""
+
         else:
             # Otherwise, assume the content is a list of dicts, e.g., text followed by an image URL
             content_text = ""
@@ -173,33 +212,28 @@ def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
         ollama_payload["format"] = openai_payload["format"]
 
     # If there are advanced parameters in the payload, format them in Ollama's options field
-    ollama_options = {}
-
     if openai_payload.get("options"):
         ollama_payload["options"] = openai_payload["options"]
         ollama_options = openai_payload["options"]
 
-    # Handle parameters which map directly
+        # Re-Mapping OpenAI's `max_tokens` -> Ollama's `num_predict`
-    for param in ["temperature", "top_p", "seed"]:
+        if "max_tokens" in ollama_options:
-        if param in openai_payload:
+            ollama_options["num_predict"] = ollama_options["max_tokens"]
-            ollama_options[param] = openai_payload[param]
+            del ollama_options[
+                "max_tokens"
+            ]  # To prevent Ollama warning of invalid option provided
 
-    # Mapping OpenAI's `max_tokens` -> Ollama's `num_predict`
+        # Ollama lacks a "system" prompt option. It has to be provided as a direct parameter, so we copy it down.
-    if "max_completion_tokens" in openai_payload:
+        if "system" in ollama_options:
-        ollama_options["num_predict"] = openai_payload["max_completion_tokens"]
+            ollama_payload["system"] = ollama_options["system"]
-    elif "max_tokens" in openai_payload:
+            del ollama_options[
-        ollama_options["num_predict"] = openai_payload["max_tokens"]
+                "system"
+            ]  # To prevent Ollama warning of invalid option provided
 
-    # Handle frequency / presence_penalty, which needs renaming and checking
+    # If there is the "stop" parameter in the openai_payload, remap it to the ollama_payload.options
-    if "frequency_penalty" in openai_payload:
+    if "stop" in openai_payload:
-        ollama_options["repeat_penalty"] = openai_payload["frequency_penalty"]
+        ollama_options = ollama_payload.get("options", {})
-
+        ollama_options["stop"] = openai_payload.get("stop")
-    if "presence_penalty" in openai_payload and "penalty" not in ollama_options:
-        # We are assuming presence penalty uses a similar concept in Ollama, which needs custom handling if exists.
-        ollama_options["new_topic_penalty"] = openai_payload["presence_penalty"]
-
-    # Add options to payload if any have been set
-    if ollama_options:
         ollama_payload["options"] = ollama_options
 
     if "metadata" in openai_payload:

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

@@ -24,17 +24,8 @@ def convert_ollama_tool_call_to_openai(tool_calls: dict) -> dict:
     return openai_tool_calls
 
 
-def convert_response_ollama_to_openai(ollama_response: dict) -> dict:
+def convert_ollama_usage_to_openai(data: dict) -> dict:
-    model = ollama_response.get("model", "ollama")
+    return {
-    message_content = ollama_response.get("message", {}).get("content", "")
-    tool_calls = ollama_response.get("message", {}).get("tool_calls", None)
-    openai_tool_calls = None
-
-    if tool_calls:
-        openai_tool_calls = convert_ollama_tool_call_to_openai(tool_calls)
-
-    data = ollama_response
-    usage = {
         "response_token/s": (
             round(
                 (
@@ -66,14 +57,42 @@ def convert_response_ollama_to_openai(ollama_response: dict) -> dict:
         "total_duration": data.get("total_duration", 0),
         "load_duration": data.get("load_duration", 0),
         "prompt_eval_count": data.get("prompt_eval_count", 0),
+        "prompt_tokens": int(
+            data.get("prompt_eval_count", 0)
+        ),  # This is the OpenAI compatible key
         "prompt_eval_duration": data.get("prompt_eval_duration", 0),
         "eval_count": data.get("eval_count", 0),
+        "completion_tokens": int(
+            data.get("eval_count", 0)
+        ),  # This is the OpenAI compatible key
         "eval_duration": data.get("eval_duration", 0),
         "approximate_total": (lambda s: f"{s // 3600}h{(s % 3600) // 60}m{s % 60}s")(
             (data.get("total_duration", 0) or 0) // 1_000_000_000
         ),
+        "total_tokens": int(  # This is the OpenAI compatible key
+            data.get("prompt_eval_count", 0) + data.get("eval_count", 0)
+        ),
+        "completion_tokens_details": {  # This is the OpenAI compatible key
+            "reasoning_tokens": 0,
+            "accepted_prediction_tokens": 0,
+            "rejected_prediction_tokens": 0,
+        },
     }
 
+
+def convert_response_ollama_to_openai(ollama_response: dict) -> dict:
+    model = ollama_response.get("model", "ollama")
+    message_content = ollama_response.get("message", {}).get("content", "")
+    tool_calls = ollama_response.get("message", {}).get("tool_calls", None)
+    openai_tool_calls = None
+
+    if tool_calls:
+        openai_tool_calls = convert_ollama_tool_call_to_openai(tool_calls)
+
+    data = ollama_response
+
+    usage = convert_ollama_usage_to_openai(data)
+
     response = openai_chat_completion_message_template(
         model, message_content, openai_tool_calls, usage
     )
@@ -85,7 +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
 
@@ -96,48 +115,10 @@ async def convert_streaming_response_ollama_to_openai(ollama_streaming_response)
 
         usage = None
         if done:
-            usage = {
+            usage = convert_ollama_usage_to_openai(data)
-                "response_token/s": (
-                    round(
-                        (
-                            (
-                                data.get("eval_count", 0)
-                                / ((data.get("eval_duration", 0) / 10_000_000))
-                            )
-                            * 100
-                        ),
-                        2,
-                    )
-                    if data.get("eval_duration", 0) > 0
-                    else "N/A"
-                ),
-                "prompt_token/s": (
-                    round(
-                        (
-                            (
-                                data.get("prompt_eval_count", 0)
-                                / ((data.get("prompt_eval_duration", 0) / 10_000_000))
-                            )
-                            * 100
-                        ),
-                        2,
-                    )
-                    if data.get("prompt_eval_duration", 0) > 0
-                    else "N/A"
-                ),
-                "total_duration": data.get("total_duration", 0),
-                "load_duration": data.get("load_duration", 0),
-                "prompt_eval_count": data.get("prompt_eval_count", 0),
-                "prompt_eval_duration": data.get("prompt_eval_duration", 0),
-                "eval_count": data.get("eval_count", 0),
-                "eval_duration": data.get("eval_duration", 0),
-                "approximate_total": (
-                    lambda s: f"{s // 3600}h{(s % 3600) // 60}m{s % 60}s"
-                )((data.get("total_duration", 0) or 0) // 1_000_000_000),
-            }
 
         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/requirements.txt

@@ -1,10 +1,10 @@
 fastapi==0.115.7
 uvicorn[standard]==0.30.6
-pydantic==2.9.2
+pydantic==2.10.6
 python-multipart==0.0.18
 
 python-socketio==5.11.3
-python-jose==3.3.0
+python-jose==3.4.0
 passlib[bcrypt]==1.7.4
 
 requests==2.32.3
@@ -31,6 +31,9 @@ APScheduler==3.10.4
 
 RestrictedPython==8.0
 
+loguru==0.7.2
+asgiref==3.8.1
+
 # AI libraries
 openai
 anthropic
@@ -45,7 +48,7 @@ chromadb==0.6.2
 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
 
 transformers
 sentence-transformers==3.3.1
@@ -59,7 +62,7 @@ fpdf2==2.8.2
 pymdown-extensions==10.14.2
 docx2txt==0.8
 python-pptx==1.0.0
-unstructured==0.16.11
+unstructured==0.16.17
 nltk==3.9.1
 Markdown==3.7
 pypandoc==1.13
@@ -71,6 +74,7 @@ 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
@@ -103,5 +107,12 @@ pytest-docker~=3.1.1
 googleapis-common-protos==1.63.2
 google-cloud-storage==2.19.0
 
+azure-identity==1.20.0
+azure-storage-blob==12.24.1
+
+
 ## LDAP
 ldap3==2.9.1
+
+## Firecrawl
+firecrawl-py==1.12.0

backend/start.sh

@@ -3,6 +3,17 @@
 SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
 cd "$SCRIPT_DIR" || exit
 
+# Add conditional Playwright browser installation
+if [[ "${RAG_WEB_LOADER_ENGINE,,}" == "playwright" ]]; then
+    if [[ -z "${PLAYWRIGHT_WS_URI}" ]]; then
+        echo "Installing Playwright browsers..."
+        playwright install chromium
+        playwright install-deps chromium
+    fi
+
+    python -c "import nltk; nltk.download('punkt_tab')"
+fi
+
 KEY_FILE=.webui_secret_key
 
 PORT="${PORT:-8080}"

backend/start_windows.bat

@@ -6,6 +6,17 @@ SETLOCAL ENABLEDELAYEDEXPANSION
 SET "SCRIPT_DIR=%~dp0"
 cd /d "%SCRIPT_DIR%" || exit /b
 
+:: Add conditional Playwright browser installation
+IF /I "%RAG_WEB_LOADER_ENGINE%" == "playwright" (
+    IF "%PLAYWRIGHT_WS_URI%" == "" (
+        echo Installing Playwright browsers...
+        playwright install chromium
+        playwright install-deps chromium
+    )
+
+    python -c "import nltk; nltk.download('punkt_tab')"
+)
+
 SET "KEY_FILE=.webui_secret_key"
 IF "%PORT%"=="" SET PORT=8080
 IF "%HOST%"=="" SET HOST=0.0.0.0

docker-compose.playwright.yaml

@@ -0,0 +1,10 @@
+services:
+  playwright:
+    image: mcr.microsoft.com/playwright:v1.49.1-noble # Version must match requirements.txt
+    container_name: playwright
+    command: npx -y playwright@1.49.1 run-server --port 3000 --host 0.0.0.0
+
+  open-webui:
+    environment:
+      - 'RAG_WEB_LOADER_ENGINE=playwright'
+      - 'PLAYWRIGHT_WS_URI=ws://playwright:3000'

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.5.13",
+	"version": "0.5.18",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.5.13",
+			"version": "0.5.18",
 			"dependencies": {
 				"@codemirror/lang-javascript": "^6.2.2",
 				"@codemirror/lang-python": "^6.1.6",
@@ -41,6 +41,7 @@
 				"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",
@@ -63,6 +64,7 @@
 				"svelte-sonner": "^0.3.19",
 				"tippy.js": "^6.3.7",
 				"turndown": "^7.2.0",
+				"undici": "^7.3.0",
 				"uuid": "^9.0.1",
 				"vite-plugin-static-copy": "^2.2.0"
 			},
@@ -134,9 +136,10 @@
 			}
 		},
 		"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"
 			},
@@ -3169,6 +3172,13 @@
 			"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",
@@ -3198,6 +3208,13 @@
 			"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",
@@ -3793,6 +3810,18 @@
 				"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",
@@ -3828,6 +3857,16 @@
 			"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",
@@ -4032,6 +4071,18 @@
 				"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",
@@ -4130,6 +4181,33 @@
 				"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",
@@ -4598,6 +4676,18 @@
 				"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",
@@ -4642,6 +4732,16 @@
 				"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",
@@ -6105,6 +6205,12 @@
 				"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",
@@ -6700,6 +6806,20 @@
 			"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",
@@ -7212,6 +7332,34 @@
 				"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",
@@ -9028,7 +9176,7 @@
 			"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",
@@ -9754,6 +9902,16 @@
 				"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",
@@ -9893,6 +10051,16 @@
 			"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",
@@ -10784,6 +10952,16 @@
 			"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",
@@ -11165,6 +11343,16 @@
 				"@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",
@@ -11257,6 +11445,16 @@
 				"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",
@@ -11528,6 +11726,15 @@
 				"node": "*"
 			}
 		},
+		"node_modules/undici": {
+			"version": "7.3.0",
+			"resolved": "https://registry.npmjs.org/undici/-/undici-7.3.0.tgz",
+			"integrity": "sha512-Qy96NND4Dou5jKoSJ2gm8ax8AJM/Ey9o9mz7KN1bb9GP+G0l20Zw8afxTnY2f4b7hmhn/z8aC2kfArVQlAhFBw==",
+			"license": "MIT",
+			"engines": {
+				"node": ">=20.18.1"
+			}
+		},
 		"node_modules/undici-types": {
 			"version": "5.26.5",
 			"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
@@ -11587,6 +11794,16 @@
 			"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": "0.5.13",
+	"version": "0.5.18",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -84,6 +84,7 @@
 		"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",
@@ -106,6 +107,7 @@
 		"svelte-sonner": "^0.3.19",
 		"tippy.js": "^6.3.7",
 		"turndown": "^7.2.0",
+		"undici": "^7.3.0",
 		"uuid": "^9.0.1",
 		"vite-plugin-static-copy": "^2.2.0"
 	},

pyproject.toml

@@ -8,11 +8,11 @@ license = { file = "LICENSE" }
 dependencies = [
     "fastapi==0.115.7",
     "uvicorn[standard]==0.30.6",
-    "pydantic==2.9.2",
+    "pydantic==2.10.6",
     "python-multipart==0.0.18",
 
     "python-socketio==5.11.3",
-    "python-jose==3.3.0",
+    "python-jose==3.4.0",
     "passlib[bcrypt]==1.7.4",
 
     "requests==2.32.3",
@@ -40,6 +40,9 @@ dependencies = [
 
     "RestrictedPython==8.0",
 
+    "loguru==0.7.2",
+    "asgiref==3.8.1",
+
     "openai",
     "anthropic",
     "google-generativeai==0.7.2",
@@ -53,6 +56,7 @@ dependencies = [
     "pymilvus==2.5.0",
     "qdrant-client~=1.12.0",
     "opensearch-py==2.8.0",
+    "playwright==1.49.1",
 
     "transformers",
     "sentence-transformers==3.3.1",
@@ -65,7 +69,7 @@ dependencies = [
     "pymdown-extensions==10.14.2",
     "docx2txt==0.8",
     "python-pptx==1.0.0",
-    "unstructured==0.16.11",
+    "unstructured==0.16.17",
     "nltk==3.9.1",
     "Markdown==3.7",
     "pypandoc==1.13",
@@ -77,6 +81,7 @@ 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",
@@ -108,7 +113,13 @@ dependencies = [
     "googleapis-common-protos==1.63.2",
     "google-cloud-storage==2.19.0",
 
+    "azure-identity==1.20.0",
+    "azure-storage-blob==12.24.1",
+
     "ldap3==2.9.1",
+
+    "firecrawl-py==1.12.0",
+
     "gcp-storage-emulator>=2024.8.3",
 ]
 readme = "README.md"

run-compose.sh

@@ -74,6 +74,7 @@ usage() {
     echo "  --enable-api[port=PORT]    Enable API and expose it on the specified port."
     echo "  --webui[port=PORT]         Set the port for the web user interface."
     echo "  --data[folder=PATH]        Bind mount for ollama data folder (by default will create the 'ollama' volume)."
+    echo "  --playwright               Enable Playwright support for web scraping."
     echo "  --build                    Build the docker image before running the compose project."
     echo "  --drop                     Drop the compose project."
     echo "  -q, --quiet                Run script in headless mode."
@@ -100,6 +101,7 @@ webui_port=3000
 headless=false
 build_image=false
 kill_compose=false
+enable_playwright=false
 
 # Function to extract value from the parameter
 extract_value() {
@@ -129,6 +131,9 @@ while [[ $# -gt 0 ]]; do
             value=$(extract_value "$key")
             data_dir=${value:-"./ollama-data"}
             ;;
+        --playwright)
+            enable_playwright=true
+            ;;
         --drop)
             kill_compose=true
             ;;
@@ -182,6 +187,9 @@ else
         DEFAULT_COMPOSE_COMMAND+=" -f docker-compose.data.yaml"
         export OLLAMA_DATA_DIR=$data_dir # Set OLLAMA_DATA_DIR environment variable
     fi
+    if [[ $enable_playwright == true ]]; then
+        DEFAULT_COMPOSE_COMMAND+=" -f docker-compose.playwright.yaml"
+    fi
     if [[ -n $webui_port ]]; then
         export OPEN_WEBUI_PORT=$webui_port # Set OPEN_WEBUI_PORT environment variable
     fi
@@ -201,6 +209,7 @@ echo -e "   ${GREEN}${BOLD}GPU Count:${NC} ${OLLAMA_GPU_COUNT:-Not Enabled}"
 echo -e "   ${GREEN}${BOLD}WebAPI Port:${NC} ${OLLAMA_WEBAPI_PORT:-Not Enabled}"
 echo -e "   ${GREEN}${BOLD}Data Folder:${NC} ${data_dir:-Using ollama volume}"
 echo -e "   ${GREEN}${BOLD}WebUI Port:${NC} $webui_port"
+echo -e "   ${GREEN}${BOLD}Playwright:${NC} ${enable_playwright:-false}"
 echo
 
 if [[ $headless == true ]]; then

scripts/prepare-pyodide.js

@@ -16,8 +16,39 @@ const packages = [
 ];
 
 import { loadPyodide } from 'pyodide';
+import { setGlobalDispatcher, ProxyAgent } from 'undici';
 import { writeFile, readFile, copyFile, readdir, rmdir } from 'fs/promises';
 
+/**
+ * Loading network proxy configurations from the environment variables.
+ * And the proxy config with lowercase name has the highest priority to use.
+ */
+function initNetworkProxyFromEnv() {
+	// we assume all subsequent requests in this script are HTTPS:
+	// https://cdn.jsdelivr.net
+	// https://pypi.org
+	// https://files.pythonhosted.org
+	const allProxy = process.env.all_proxy || process.env.ALL_PROXY;
+	const httpsProxy = process.env.https_proxy || process.env.HTTPS_PROXY;
+	const httpProxy = process.env.http_proxy || process.env.HTTP_PROXY;
+	const preferedProxy = httpsProxy || allProxy || httpProxy;
+	/**
+	 * use only http(s) proxy because socks5 proxy is not supported currently:
+	 * @see https://github.com/nodejs/undici/issues/2224
+	 */
+	if (!preferedProxy || !preferedProxy.startsWith('http')) return;
+	let preferedProxyURL;
+	try {
+		preferedProxyURL = new URL(preferedProxy).toString();
+	} catch {
+		console.warn(`Invalid network proxy URL: "${preferedProxy}"`);
+		return;
+	}
+	const dispatcher = new ProxyAgent({ uri: preferedProxyURL });
+	setGlobalDispatcher(dispatcher);
+	console.log(`Initialized network proxy "${preferedProxy}" from env`);
+}
+
 async function downloadPackages() {
 	console.log('Setting up pyodide + micropip');
 
@@ -84,5 +115,6 @@ async function copyPyodide() {
 	}
 }
 
+initNetworkProxyFromEnv();
 await downloadPackages();
 await copyPyodide();

src/app.css

@@ -101,7 +101,7 @@ li p {
 
 /* Dark theme scrollbar styles */
 .dark ::-webkit-scrollbar-thumb {
-	background-color: rgba(33, 33, 33, 0.8); /* Darker color for dark theme */
+	background-color: rgba(42, 42, 42, 0.8); /* Darker color for dark theme */
 	border-color: rgba(0, 0, 0, var(--tw-border-opacity));
 }
 

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/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

@@ -91,45 +91,65 @@
 							</div>
 						</div>
 
-						<div class=" flex gap-2 w-full items-center justify-between">
+						<div class="mb-2.5 flex flex-col gap-1.5 w-full">
-							<div class="text-xs font-medium">
+							<div class=" flex gap-2 w-full items-center justify-between">
-								{$i18n.t('Jupyter Auth')}
+								<div class="text-xs font-medium">
-							</div>
+									{$i18n.t('Jupyter Auth')}
+								</div>
 
-							<div>
+								<div>
-								<select
+									<select
-									class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-left"
+										class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-left"
-									bind:value={config.CODE_EXECUTION_JUPYTER_AUTH}
+										bind:value={config.CODE_EXECUTION_JUPYTER_AUTH}
-									placeholder={$i18n.t('Select an auth method')}
+										placeholder={$i18n.t('Select an auth method')}
-								>
+									>
-									<option selected value="">{$i18n.t('None')}</option>
+										<option selected value="">{$i18n.t('None')}</option>
-									<option value="token">{$i18n.t('Token')}</option>
+										<option value="token">{$i18n.t('Token')}</option>
-									<option value="password">{$i18n.t('Password')}</option>
+										<option value="password">{$i18n.t('Password')}</option>
-								</select>
+									</select>
-							</div>
-						</div>
-
-						{#if config.CODE_EXECUTION_JUPYTER_AUTH}
-							<div class="flex w-full gap-2">
-								<div class="flex-1">
-									{#if config.CODE_EXECUTION_JUPYTER_AUTH === 'password'}
-										<SensitiveInput
-											type="text"
-											placeholder={$i18n.t('Enter Jupyter Password')}
-											bind:value={config.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD}
-											autocomplete="off"
-										/>
-									{:else}
-										<SensitiveInput
-											type="text"
-											placeholder={$i18n.t('Enter Jupyter Token')}
-											bind:value={config.CODE_EXECUTION_JUPYTER_AUTH_TOKEN}
-											autocomplete="off"
-										/>
-									{/if}
 								</div>
 							</div>
-						{/if}
+
+							{#if config.CODE_EXECUTION_JUPYTER_AUTH}
+								<div class="flex w-full gap-2">
+									<div class="flex-1">
+										{#if config.CODE_EXECUTION_JUPYTER_AUTH === 'password'}
+											<SensitiveInput
+												type="text"
+												placeholder={$i18n.t('Enter Jupyter Password')}
+												bind:value={config.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD}
+												autocomplete="off"
+											/>
+										{:else}
+											<SensitiveInput
+												type="text"
+												placeholder={$i18n.t('Enter Jupyter Token')}
+												bind:value={config.CODE_EXECUTION_JUPYTER_AUTH_TOKEN}
+												autocomplete="off"
+											/>
+										{/if}
+									</div>
+								</div>
+							{/if}
+						</div>
+
+						<div class="flex gap-2 w-full items-center justify-between">
+							<div class="text-xs font-medium">
+								{$i18n.t('Code Execution Timeout')}
+							</div>
+
+							<div class="">
+								<Tooltip content={$i18n.t('Enter timeout in seconds')}>
+									<input
+										class="dark:bg-gray-900 w-fit rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-right"
+										type="number"
+										bind:value={config.CODE_EXECUTION_JUPYTER_TIMEOUT}
+										placeholder={$i18n.t('e.g. 60')}
+										autocomplete="off"
+									/>
+								</Tooltip>
+							</div>
+						</div>
 					{/if}
 				</div>
 
@@ -197,45 +217,65 @@
 								</div>
 							</div>
 
-							<div class="flex gap-2 w-full items-center justify-between">
+							<div class="mb-2.5 flex flex-col gap-1.5 w-full">
-								<div class="text-xs font-medium">
+								<div class="flex gap-2 w-full items-center justify-between">
-									{$i18n.t('Jupyter Auth')}
+									<div class="text-xs font-medium">
-								</div>
+										{$i18n.t('Jupyter Auth')}
+									</div>
 
-								<div>
+									<div>
-									<select
+										<select
-										class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-left"
+											class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-left"
-										bind:value={config.CODE_INTERPRETER_JUPYTER_AUTH}
+											bind:value={config.CODE_INTERPRETER_JUPYTER_AUTH}
-										placeholder={$i18n.t('Select an auth method')}
+											placeholder={$i18n.t('Select an auth method')}
-									>
+										>
-										<option selected value="">{$i18n.t('None')}</option>
+											<option selected value="">{$i18n.t('None')}</option>
-										<option value="token">{$i18n.t('Token')}</option>
+											<option value="token">{$i18n.t('Token')}</option>
-										<option value="password">{$i18n.t('Password')}</option>
+											<option value="password">{$i18n.t('Password')}</option>
-									</select>
+										</select>
-								</div>
-							</div>
-
-							{#if config.CODE_INTERPRETER_JUPYTER_AUTH}
-								<div class="flex w-full gap-2">
-									<div class="flex-1">
-										{#if config.CODE_INTERPRETER_JUPYTER_AUTH === 'password'}
-											<SensitiveInput
-												type="text"
-												placeholder={$i18n.t('Enter Jupyter Password')}
-												bind:value={config.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD}
-												autocomplete="off"
-											/>
-										{:else}
-											<SensitiveInput
-												type="text"
-												placeholder={$i18n.t('Enter Jupyter Token')}
-												bind:value={config.CODE_INTERPRETER_JUPYTER_AUTH_TOKEN}
-												autocomplete="off"
-											/>
-										{/if}
 									</div>
 								</div>
-							{/if}
+
+								{#if config.CODE_INTERPRETER_JUPYTER_AUTH}
+									<div class="flex w-full gap-2">
+										<div class="flex-1">
+											{#if config.CODE_INTERPRETER_JUPYTER_AUTH === 'password'}
+												<SensitiveInput
+													type="text"
+													placeholder={$i18n.t('Enter Jupyter Password')}
+													bind:value={config.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD}
+													autocomplete="off"
+												/>
+											{:else}
+												<SensitiveInput
+													type="text"
+													placeholder={$i18n.t('Enter Jupyter Token')}
+													bind:value={config.CODE_INTERPRETER_JUPYTER_AUTH_TOKEN}
+													autocomplete="off"
+												/>
+											{/if}
+										</div>
+									</div>
+								{/if}
+							</div>
+
+							<div class="flex gap-2 w-full items-center justify-between">
+								<div class="text-xs font-medium">
+									{$i18n.t('Code Execution Timeout')}
+								</div>
+
+								<div class="">
+									<Tooltip content={$i18n.t('Enter timeout in seconds')}>
+										<input
+											class="dark:bg-gray-900 w-fit rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-right"
+											type="number"
+											bind:value={config.CODE_INTERPRETER_JUPYTER_TIMEOUT}
+											placeholder={$i18n.t('e.g. 60')}
+											autocomplete="off"
+										/>
+									</Tooltip>
+								</div>
+							</div>
 						{/if}
 
 						<hr class="border-gray-100 dark:border-gray-850 my-2" />

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/Images.svelte

@@ -261,6 +261,9 @@
 										} else if (config.engine === 'openai' && config.openai.OPENAI_API_KEY === '') {
 											toast.error($i18n.t('OpenAI API Key is required.'));
 											config.enabled = false;
+										} else if (config.engine === 'gemini' && config.gemini.GEMINI_API_KEY === '') {
+											toast.error($i18n.t('Gemini API Key is required.'));
+											config.enabled = false;
 										}
 									}
 
@@ -294,6 +297,7 @@
 							<option value="openai">{$i18n.t('Default (Open AI)')}</option>
 							<option value="comfyui">{$i18n.t('ComfyUI')}</option>
 							<option value="automatic1111">{$i18n.t('Automatic1111')}</option>
+							<option value="gemini">{$i18n.t('Gemini')}</option>
 						</select>
 					</div>
 				</div>
@@ -605,6 +609,24 @@
 							/>
 						</div>
 					</div>
+				{:else if config?.engine === 'gemini'}
+					<div>
+						<div class=" mb-1.5 text-sm font-medium">{$i18n.t('Gemini API Config')}</div>
+
+						<div class="flex gap-2 mb-1">
+							<input
+								class="flex-1 w-full text-sm bg-transparent outline-none"
+								placeholder={$i18n.t('API Base URL')}
+								bind:value={config.gemini.GEMINI_API_BASE_URL}
+								required
+							/>
+
+							<SensitiveInput
+								placeholder={$i18n.t('API Key')}
+								bind:value={config.gemini.GEMINI_API_KEY}
+							/>
+						</div>
+					</div>
 				{/if}
 			</div>
 

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

@@ -51,7 +51,7 @@
 	onMount(async () => {
 		taskConfig = await getTaskConfig(localStorage.token);
 
-		promptSuggestions = $config?.default_prompt_suggestions;
+		promptSuggestions = $config?.default_prompt_suggestions ?? [];
 		banners = await getBanners(localStorage.token);
 	});
 

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

@@ -85,384 +85,416 @@
 >
 	<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>
+							<div class="mb-2.5 flex w-full flex-col">
-								<div class=" self-center text-xs font-medium mb-1">
+								<div>
-									{$i18n.t('Exa API Key')}
+									<div class=" self-center text-xs font-medium mb-1">
-								</div>
+										{$i18n.t('Exa API Key')}
+									</div>
 
-								<SensitiveInput
+									<SensitiveInput
-									placeholder={$i18n.t('Enter Exa API Key')}
+										placeholder={$i18n.t('Enter Exa API Key')}
-									bind:value={webConfig.search.exa_api_key}
+										bind:value={webConfig.search.exa_api_key}
-								/>
+									/>
+								</div>
 							</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 +502,14 @@
 							/>
 						</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

@@ -85,8 +85,9 @@
 				return true;
 			} else {
 				let name = user.name.toLowerCase();
+				let email = user.email.toLowerCase();
 				const query = search.toLowerCase();
-				return name.includes(query);
+				return name.includes(query) || email.includes(query);
 			}
 		})
 		.sort((a, b) => {

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),
@@ -1965,6 +1981,7 @@
 									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/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();
@@ -173,22 +174,6 @@
 		}
 
 		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.
@@ -430,7 +415,7 @@
 								</div>
 							{/if}
 
-							{#if webSearchEnabled || ($settings?.webSearch ?? false) === 'always'}
+							{#if webSearchEnabled || ($config?.features?.enable_web_search && ($settings?.webSearch ?? false)) === 'always'}
 								<div class="flex items-center justify-between w-full">
 									<div class="flex items-center gap-2.5 text-sm dark:text-gray-500">
 										<div class="pl-1">
@@ -827,7 +812,11 @@
 															}
 
 															// Submit the prompt when Enter key is pressed
-															if (prompt !== '' && e.keyCode === 13 && !e.shiftKey) {
+															if (
+																(prompt !== '' || files.length > 0) &&
+																e.keyCode === 13 &&
+																!e.shiftKey
+															) {
 																dispatch('submit', prompt);
 															}
 														}
@@ -906,7 +895,11 @@
 													}
 
 													// Submit the prompt when Enter key is pressed
-													if (prompt !== '' && e.key === 'Enter' && !e.shiftKey) {
+													if (
+														(prompt !== '' || files.length > 0) &&
+														e.key === 'Enter' &&
+														!e.shiftKey
+													) {
 														dispatch('submit', prompt);
 													}
 												}
@@ -1108,6 +1101,21 @@
 													);
 												}
 											}}
+											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 +1293,17 @@
 
 																	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/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 = [];
 
@@ -349,6 +350,7 @@
 	{#if Object.keys(history?.messages ?? {}).length == 0}
 		<ChatPlaceholder
 			modelIds={selectedModels}
+			{atSelectedModel}
 			submitPrompt={async (p) => {
 				let text = p;
 

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

@@ -7,6 +7,7 @@
 
 	const i18n = getContext('i18n');
 
+	export let id = '';
 	export let sources = [];
 
 	let citations = [];
@@ -42,6 +43,7 @@
 	}
 
 	$: {
+		console.log('sources', sources);
 		citations = sources.reduce((acc, source) => {
 			if (Object.keys(source).length === 0) {
 				return acc;
@@ -52,7 +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) {
@@ -100,7 +102,7 @@
 			<div class="flex text-xs font-medium flex-wrap">
 				{#each citations as citation, idx}
 					<button
-						id={`source-${idx}`}
+						id={`source-${id}-${idx}`}
 						class="no-toggle outline-hidden flex dark:text-gray-300 p-1 bg-white dark:bg-gray-900 rounded-xl max-w-96"
 						on:click={() => {
 							showCitationModal = true;
@@ -179,7 +181,7 @@
 					<div class="flex text-xs font-medium flex-wrap">
 						{#each citations as citation, idx}
 							<button
-								id={`source-${idx}`}
+								id={`source-${id}-${idx}`}
 								class="no-toggle outline-hidden flex dark:text-gray-300 p-1 bg-gray-50 hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 transition rounded-xl max-w-96"
 								on:click={() => {
 									showCitationModal = true;

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';
@@ -25,10 +16,12 @@
 	import { toast } from 'svelte-sonner';
 
 	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;
 
@@ -71,7 +64,7 @@
 		saved = true;
 
 		code = _code;
-		dispatch('save', code);
+		onSave(code);
 
 		setTimeout(() => {
 			saved = false;
@@ -123,6 +116,12 @@
 	};
 
 	const executePython = async (code) => {
+		result = null;
+		stdout = null;
+		stderr = null;
+
+		executing = true;
+
 		if ($config?.code?.engine === 'jupyter') {
 			const output = await executeCode(localStorage.token, code).catch((error) => {
 				toast.error(`${error}`);
@@ -130,22 +129,74 @@
 			});
 
 			if (output) {
-				stdout = output.stdout;
+				if (output['stdout']) {
-				stderr = output.stderr;
+					stdout = output['stdout'];
-				result = output.result;
+					const stdoutLines = stdout.split('\n');
+
+					for (const [idx, line] of stdoutLines.entries()) {
+						if (line.startsWith('data:image/png;base64')) {
+							if (files) {
+								files.push({
+									type: 'image/png',
+									data: line
+								});
+							} else {
+								files = [
+									{
+										type: 'image/png',
+										data: line
+									}
+								];
+							}
+
+							if (stdout.startsWith(`${line}\n`)) {
+								stdout = stdout.replace(`${line}\n`, ``);
+							} else if (stdout.startsWith(`${line}`)) {
+								stdout = stdout.replace(`${line}`, ``);
+							}
+						}
+					}
+				}
+
+				if (output['result']) {
+					result = output['result'];
+					const resultLines = result.split('\n');
+
+					for (const [idx, line] of resultLines.entries()) {
+						if (line.startsWith('data:image/png;base64')) {
+							if (files) {
+								files.push({
+									type: 'image/png',
+									data: line
+								});
+							} else {
+								files = [
+									{
+										type: 'image/png',
+										data: line
+									}
+								];
+							}
+
+							if (result.startsWith(`${line}\n`)) {
+								result = result.replace(`${line}\n`, ``);
+							} else if (result.startsWith(`${line}`)) {
+								result = result.replace(`${line}`, ``);
+							}
+						}
+					}
+				}
+
+				output['stderr'] && (stderr = output['stderr']);
 			}
+
+			executing = false;
 		} else {
 			executePythonAsWorker(code);
 		}
 	};
 
 	const executePythonAsWorker = async (code) => {
-		result = null;
-		stdout = null;
-		stderr = null;
-
-		executing = true;
-
 		let packages = [
 			code.includes('requests') ? 'requests' : null,
 			code.includes('bs4') ? 'beautifulsoup4' : null,
@@ -205,7 +256,40 @@
 							];
 						}
 
-						stdout = stdout.replace(`${line}\n`, ``);
+						if (stdout.startsWith(`${line}\n`)) {
+							stdout = stdout.replace(`${line}\n`, ``);
+						} else if (stdout.startsWith(`${line}`)) {
+							stdout = stdout.replace(`${line}`, ``);
+						}
+					}
+				}
+			}
+
+			if (data['result']) {
+				result = data['result'];
+				const resultLines = result.split('\n');
+
+				for (const [idx, line] of resultLines.entries()) {
+					if (line.startsWith('data:image/png;base64')) {
+						if (files) {
+							files.push({
+								type: 'image/png',
+								data: line
+							});
+						} else {
+							files = [
+								{
+									type: 'image/png',
+									data: line
+								}
+							];
+						}
+
+						if (result.startsWith(`${line}\n`)) {
+							result = result.replace(`${line}\n`, ``);
+						} else if (result.startsWith(`${line}`)) {
+							result = result.replace(`${line}`, ``);
+						}
 					}
 				}
 			}
@@ -253,7 +337,7 @@
 		render();
 	}
 
-	$: dispatch('code', { lang, code });
+	$: onCode({ lang, code });
 
 	$: if (attributes) {
 		onAttributesUpdate();
@@ -289,7 +373,7 @@
 		console.log('codeblock', lang, code);
 
 		if (lang) {
-			dispatch('code', { lang, code });
+			onCode({ lang, code });
 		}
 		if (document.documentElement.classList.contains('dark')) {
 			mermaid.initialize({
@@ -377,11 +461,11 @@
 					value={code}
 					{id}
 					{lang}
-					on:save={() => {
+					onSave={() => {
 						saveCode();
 					}}
-					on:change={(e) => {
+					onChange={(value) => {
-						_code = e.detail.value;
+						_code = value;
 					}}
 				/>
 			</div>
@@ -391,7 +475,7 @@
 				class="bg-gray-50 dark:bg-[#202123] dark:text-white max-w-full overflow-x-auto scrollbar-hidden"
 			/>
 
-			{#if executing || stdout || stderr || result}
+			{#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"
 				>
@@ -404,7 +488,13 @@
 						{#if stdout || stderr}
 							<div class=" ">
 								<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
-								<div class="text-sm">{stdout || stderr}</div>
+								<div
+									class="text-sm {stdout?.split('\n')?.length > 100
+										? `max-h-96`
+										: ''}  overflow-y-auto"
+								>
+									{stdout || stderr}
+								</div>
 							</div>
 						{/if}
 						{#if result || files}
@@ -417,7 +507,7 @@
 									<div class="flex flex-col gap-2">
 										{#each files as file}
 											{#if file.type.startsWith('image')}
-												<img src={file.data} alt="Output" />
+												<img src={file.data} alt="Output" class=" w-full max-w-[36rem]" />
 											{/if}
 										{/each}
 									</div>

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

@@ -120,6 +120,11 @@
 		sourceIds={(sources ?? []).reduce((acc, s) => {
 			let ids = [];
 			s.document.forEach((document, index) => {
+				if (model?.info?.meta?.capabilities?.citations == false) {
+					ids.push('N/A');
+					return ids;
+				}
+
 				const metadata = s.metadata?.[index];
 				const id = metadata?.source ?? 'N/A';
 

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

@@ -29,7 +29,7 @@
 		{:else if token.text.includes(`<iframe src="${WEBUI_BASE_URL}/api/v1/files/`)}
 			{@html `${token.text}`}
 		{:else if token.text.includes(`<source_id`)}
-			<Source {token} onClick={onSourceClick} />
+			<Source {id} {token} onClick={onSourceClick} />
 		{:else}
 			{token.text}
 		{/if}

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

@@ -76,7 +76,7 @@
 	{#if token.type === 'hr'}
 		<hr class=" border-gray-100 dark:border-gray-850" />
 	{:else if token.type === 'heading'}
-		<svelte:element this={headerComponent(token.depth)}>
+		<svelte:element this={headerComponent(token.depth)} dir="auto">
 			<MarkdownInlineTokens id={`${id}-${tokenIdx}-h`} tokens={token.tokens} {onSourceClick} />
 		</svelte:element>
 	{:else if token.type === 'code'}
@@ -88,14 +88,14 @@
 				code={token?.text ?? ''}
 				{attributes}
 				{save}
-				on:code={(e) => {
+				onCode={(value) => {
-					dispatch('code', e.detail);
+					dispatch('code', value);
 				}}
-				on:save={(e) => {
+				onSave={(e) => {
 					dispatch('update', {
 						raw: token.raw,
 						oldContent: token.text,
-						newContent: e.detail
+						newContent: value
 					});
 				}}
 			/>
@@ -176,7 +176,7 @@
 		{#if token.ordered}
 			<ol start={token.start || 1}>
 				{#each token.items as item, itemIdx}
-					<li dir="auto">
+					<li dir="auto" class="text-start">
 						{#if item?.task}
 							<input
 								class=" translate-y-[1px] -translate-x-1"
@@ -208,7 +208,7 @@
 		{:else}
 			<ul>
 				{#each token.items as item, itemIdx}
-					<li dir="auto">
+					<li dir="auto" class="text-start">
 						{#if item?.task}
 							<input
 								class=" translate-y-[1px] -translate-x-1"
@@ -239,7 +239,12 @@
 			</ul>
 		{/if}
 	{:else if token.type === 'details'}
-		<Collapsible title={token.summary} attributes={token?.attributes} className="w-full space-y-1">
+		<Collapsible
+			title={token.summary}
+			attributes={token?.attributes}
+			className="w-full space-y-1"
+			dir="auto"
+		>
 			<div class=" mb-1.5" slot="content">
 				<svelte:self
 					id={`${id}-${tokenIdx}-d`}

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

@@ -1,8 +1,9 @@
 <script lang="ts">
+	export let id;
 	export let token;
 	export let onClick: Function = () => {};
 
-	let attributes: Record<string, string> = {};
+	let attributes: Record<string, string | undefined> = {};
 
 	function extractAttributes(input: string): Record<string, string> {
 		const regex = /(\w+)="([^"]*)"/g;
@@ -35,13 +36,15 @@
 	$: attributes = extractAttributes(token.text);
 </script>
 
-<button
+{#if attributes.title !== 'N/A'}
-	class="text-xs font-medium w-fit translate-y-[2px] px-2 py-0.5 dark:bg-white/5 dark:text-white/60 dark:hover:text-white bg-gray-50 text-black/60 hover:text-black transition rounded-lg"
+	<button
-	on:click={() => {
+		class="text-xs font-medium w-fit translate-y-[2px] px-2 py-0.5 dark:bg-white/5 dark:text-white/60 dark:hover:text-white bg-gray-50 text-black/60 hover:text-black transition rounded-lg"
-		onClick(attributes.data);
+		on:click={() => {
-	}}
+			onClick(id, attributes.data);
->
+		}}
-	<span class="line-clamp-1">
+	>
-		{formattedTitle(attributes.title)}
+		<span class="line-clamp-1">
-	</span>
+			{attributes.title ? formattedTitle(attributes.title) : ''}
-</button>
+		</span>
+	</button>
+{/if}

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

@@ -129,6 +129,7 @@
 	export let isLastMessage = true;
 	export let readOnly = false;
 
+	let buttonsContainerElement: HTMLDivElement;
 	let showDeleteConfirm = false;
 
 	let model = null;
@@ -518,6 +519,18 @@
 		// console.log('ResponseMessage mounted');
 
 		await tick();
+		if (buttonsContainerElement) {
+			console.log(buttonsContainerElement);
+			buttonsContainerElement.addEventListener('wheel', function (event) {
+				// console.log(event.deltaY);
+
+				event.preventDefault();
+				if (event.deltaY !== 0) {
+					// Adjust horizontal scroll position based on vertical scroll
+					buttonsContainerElement.scrollLeft += event.deltaY;
+				}
+			});
+		}
 	});
 </script>
 
@@ -732,9 +745,9 @@
 										onTaskClick={async (e) => {
 											console.log(e);
 										}}
-										onSourceClick={async (e) => {
+										onSourceClick={async (id, idx) => {
-											console.log(e);
+											console.log(id, idx);
-											let sourceButton = document.getElementById(`source-${e}`);
+											let sourceButton = document.getElementById(`source-${message.id}-${idx}`);
 											const sourcesCollapsible = document.getElementById(`collapsible-sources`);
 
 											if (sourceButton) {
@@ -753,7 +766,7 @@
 												});
 
 												// Try clicking the source button again
-												sourceButton = document.getElementById(`source-${e}`);
+												sourceButton = document.getElementById(`source-${message.id}-${idx}`);
 												sourceButton && sourceButton.click();
 											}
 										}}
@@ -790,7 +803,7 @@
 								{/if}
 
 								{#if (message?.sources || message?.citations) && (model?.info?.meta?.capabilities?.citations ?? true)}
-									<Citations sources={message?.sources ?? message?.citations} />
+									<Citations id={message?.id} sources={message?.sources ?? message?.citations} />
 								{/if}
 
 								{#if message.code_executions}
@@ -802,10 +815,11 @@
 				</div>
 
 				{#if !edit}
-					{#if message.done || siblings.length > 1}
+					<div
-						<div
+						bind:this={buttonsContainerElement}
-							class=" flex justify-start overflow-x-auto buttons text-gray-600 dark:text-gray-500 mt-0.5"
+						class="flex justify-start overflow-x-auto buttons text-gray-600 dark:text-gray-500 mt-0.5"
-						>
+					>
+						{#if message.done || siblings.length > 1}
 							{#if siblings.length > 1}
 								<div class="flex self-center min-w-fit" dir="ltr">
 									<button
@@ -1313,8 +1327,8 @@
 									{/if}
 								{/if}
 							{/if}
-						</div>
+						{/if}
-					{/if}
+					</div>
 
 					{#if message.done && showRateComment}
 						<RateComment

src/lib/components/chat/Placeholder.svelte

@@ -213,7 +213,8 @@
 	<div class="mx-auto max-w-2xl font-primary" in:fade={{ duration: 200, delay: 200 }}>
 		<div class="mx-5">
 			<Suggestions
-				suggestionPrompts={models[selectedModelIdx]?.info?.meta?.suggestion_prompts ??
+				suggestionPrompts={atSelectedModel?.info?.meta?.suggestion_prompts ??
+					models[selectedModelIdx]?.info?.meta?.suggestion_prompts ??
 					$config?.default_prompt_suggestions ??
 					[]}
 				inputValue={prompt}

src/lib/components/chat/Settings/Personalization/ManageModal.svelte

@@ -12,6 +12,7 @@
 	import { error } from '@sveltejs/kit';
 	import EditMemoryModal from './EditMemoryModal.svelte';
 	import localizedFormat from 'dayjs/plugin/localizedFormat';
+	import ConfirmDialog from '$lib/components/common/ConfirmDialog.svelte';
 
 	const i18n = getContext('i18n');
 	dayjs.extend(localizedFormat);
@@ -26,6 +27,21 @@
 
 	let selectedMemory = null;
 
+	let showClearConfirmDialog = false;
+
+	let onClearConfirmed = async () => {
+		const res = await deleteMemoriesByUserId(localStorage.token).catch((error) => {
+			toast.error(`${error}`);
+			return null;
+		});
+
+		if (res && memories.length > 0) {
+			toast.success($i18n.t('Memory cleared successfully'));
+			memories = [];
+		}
+		showClearConfirmDialog = false;
+	};
+
 	$: if (show && memories.length === 0 && loading) {
 		(async () => {
 			memories = await getMemories(localStorage.token);
@@ -175,15 +191,11 @@
 				>
 				<button
 					class=" px-3.5 py-1.5 font-medium text-red-500 hover:bg-black/5 dark:hover:bg-white/5 outline outline-1 outline-red-300 dark:outline-red-800 rounded-3xl"
-					on:click={async () => {
+					on:click={() => {
-						const res = await deleteMemoriesByUserId(localStorage.token).catch((error) => {
+						if (memories.length > 0) {
-							toast.error(`${error}`);
+							showClearConfirmDialog = true;
-							return null;
+						} else {
-						});
+							toast.error($i18n.t('No memories to clear'));
-
-						if (res) {
-							toast.success($i18n.t('Memory cleared successfully'));
-							memories = [];
 						}
 					}}>{$i18n.t('Clear memory')}</button
 				>
@@ -192,6 +204,16 @@
 	</div>
 </Modal>
 
+<ConfirmDialog
+	title={$i18n.t('Clear Memory')}
+	message={$i18n.t('Are you sure you want to clear all memories? This action cannot be undone.')}
+	show={showClearConfirmDialog}
+	on:confirm={onClearConfirmed}
+	on:cancel={() => {
+		showClearConfirmDialog = false;
+	}}
+/>
+
 <AddMemoryModal
 	bind:show={showAddMemoryModal}
 	on:save={async () => {

src/lib/components/chat/ShortcutsModal.svelte

@@ -122,6 +122,30 @@
 							</div>
 						</div>
 					</div>
+
+					<div class="w-full flex justify-between items-center">
+						<div class=" text-sm">{$i18n.t('Generate prompt pair')}</div>
+
+						<div class="flex space-x-1 text-xs">
+							<div
+								class=" h-fit py-1 px-2 flex items-center justify-center rounded-sm border border-black/10 capitalize text-gray-600 dark:border-white/10 dark:text-gray-300"
+							>
+								Ctrl/⌘
+							</div>
+
+							<div
+								class=" h-fit py-1 px-2 flex items-center justify-center rounded-sm border border-black/10 capitalize text-gray-600 dark:border-white/10 dark:text-gray-300"
+							>
+								Shift
+							</div>
+
+							<div
+								class=" h-fit py-1 px-2 flex items-center justify-center rounded-sm border border-black/10 capitalize text-gray-600 dark:border-white/10 dark:text-gray-300"
+							>
+								Enter
+							</div>
+						</div>
+					</div>
 				</div>
 
 				<div class="flex flex-col space-y-3 w-full self-start">
@@ -219,7 +243,7 @@
 				<div class="flex flex-col space-y-3 w-full self-start">
 					<div class="w-full flex justify-between items-center">
 						<div class=" text-sm">
-							{$i18n.t('Attach file')}
+							{$i18n.t('Attach file from knowledge')}
 						</div>
 
 						<div class="flex space-x-1 text-xs">
@@ -247,7 +271,7 @@
 
 					<div class="w-full flex justify-between items-center">
 						<div class=" text-sm">
-							{$i18n.t('Select model')}
+							{$i18n.t('Talk to model')}
 						</div>
 
 						<div class="flex space-x-1 text-xs">
@@ -258,6 +282,20 @@
 							</div>
 						</div>
 					</div>
+
+					<div class="w-full flex justify-between items-center">
+						<div class=" text-sm">
+							{$i18n.t('Accept autocomplete generation / Jump to prompt variable')}
+						</div>
+
+						<div class="flex space-x-1 text-xs">
+							<div
+								class=" h-fit py-1 px-2 flex items-center justify-center rounded-sm border border-black/10 capitalize text-gray-600 dark:border-white/10 dark:text-gray-300"
+							>
+								TAB
+							</div>
+						</div>
+					</div>
 				</div>
 			</div>
 		</div>

src/lib/components/common/CodeEditor.svelte

@@ -21,6 +21,10 @@
 
 	export let boilerplate = '';
 	export let value = '';
+
+	export let onSave = () => {};
+	export let onChange = () => {};
+
 	let _value = '';
 
 	$: if (value) {
@@ -43,6 +47,10 @@
 
 	let codeEditor;
 
+	export const focus = () => {
+		codeEditor.focus();
+	};
+
 	let isDarkMode = false;
 	let editorTheme = new Compartment();
 	let editorLanguage = new Compartment();
@@ -75,7 +83,7 @@
 				});
 
 				_value = formattedCode;
-				dispatch('change', { value: _value });
+				onChange(_value);
 				await tick();
 
 				toast.success($i18n.t('Code formatted successfully'));
@@ -94,7 +102,7 @@
 		EditorView.updateListener.of((e) => {
 			if (e.docChanged) {
 				_value = e.state.doc.toString();
-				dispatch('change', { value: _value });
+				onChange(_value);
 			}
 		}),
 		editorTheme.of([]),
@@ -170,7 +178,8 @@
 		const keydownHandler = async (e) => {
 			if ((e.ctrlKey || e.metaKey) && e.key === 's') {
 				e.preventDefault();
-				dispatch('save');
+
+				onSave();
 			}
 
 			// Format code when Ctrl + Shift + F is pressed

src/lib/components/common/FileItemModal.svelte

@@ -1,6 +1,7 @@
 <script lang="ts">
 	import { getContext, onMount } from 'svelte';
 	import { formatFileSize, getLineCount } from '$lib/utils';
+	import { WEBUI_API_BASE_URL } from '$lib/constants';
 
 	const i18n = getContext('i18n');
 
@@ -12,14 +13,15 @@
 
 	export let item;
 	export let show = false;
-
 	export let edit = false;
 
 	let enableFullContent = false;
+	$: isPDF =
+		item?.meta?.content_type === 'application/pdf' ||
+		(item?.name && item?.name.toLowerCase().endsWith('.pdf'));
 
 	onMount(() => {
 		console.log(item);
-
 		if (item?.context === 'full') {
 			enableFullContent = true;
 		}
@@ -33,9 +35,16 @@
 				<div>
 					<div class=" font-medium text-lg dark:text-gray-100">
 						<a
-							href={item.url ? (item.type === 'file' ? `${item.url}/content` : `${item.url}`) : '#'}
+							href="#"
-							target="_blank"
 							class="hover:underline line-clamp-1"
+							on:click|preventDefault={() => {
+								if (!isPDF && item.url) {
+									window.open(
+										item.type === 'file' ? `${item.url}/content` : `${item.url}`,
+										'_blank'
+									);
+								}
+							}}
 						>
 							{item?.name ?? 'File'}
 						</a>
@@ -78,7 +87,7 @@
 						<div>
 							<Tooltip
 								content={enableFullContent
-									? 'Inject the entire document as context for comprehensive processing, this is recommended for complex queries.'
+									? '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.'}
 							>
 								<div class="flex items-center gap-1.5 text-xs">
@@ -101,8 +110,18 @@
 			</div>
 		</div>
 
-		<div class="max-h-96 overflow-scroll scrollbar-hidden text-xs whitespace-pre-wrap">
+		<div class="max-h-[75vh] overflow-auto">
-			{item?.file?.data?.content ?? 'No content'}
+			{#if isPDF}
+				<iframe
+					title={item?.name}
+					src={`${WEBUI_API_BASE_URL}/files/${item.id}/content`}
+					class="w-full h-[70vh] border-0 rounded-lg mt-4"
+				/>
+			{:else}
+				<div class="max-h-96 overflow-scroll scrollbar-hidden text-xs whitespace-pre-wrap">
+					{item?.file?.data?.content ?? 'No content'}
+				</div>
+			{/if}
 		</div>
 	</div>
 </Modal>

src/lib/components/common/Modal.svelte

@@ -6,7 +6,6 @@
 
 	export let show = true;
 	export let size = 'md';
-
 	export let containerClassName = 'p-3';
 	export let className = 'bg-gray-50 dark:bg-gray-900 rounded-2xl';
 
@@ -74,7 +73,7 @@
 		}}
 	>
 		<div
-			class=" m-auto max-w-full {sizeToWidth(size)} {size !== 'full'
+			class="m-auto max-w-full {sizeToWidth(size)} {size !== 'full'
 				? 'mx-2'
 				: ''} shadow-3xl min-h-fit scrollbar-hidden {className}"
 			in:flyAndScale

src/lib/components/workspace/Knowledge/KnowledgeBase.svelte

@@ -133,20 +133,6 @@
 
 		knowledge.files = [...(knowledge.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`);
-			}
-		}
-
 		try {
 			const uploadedFile = await uploadFile(localStorage.token, file).catch((e) => {
 				toast.error(`${e}`);

src/lib/components/workspace/Models/ModelEditor.svelte

@@ -180,7 +180,6 @@
 		}
 
 		if (model) {
-			console.log(model);
 			name = model.name;
 			await tick();
 

src/lib/components/workspace/Prompts/PromptMenu.svelte

@@ -2,6 +2,7 @@
 	import { DropdownMenu } from 'bits-ui';
 	import { flyAndScale } from '$lib/utils/transitions';
 	import { getContext } from 'svelte';
+	import { config } from '$lib/stores';
 
 	import Dropdown from '$lib/components/common/Dropdown.svelte';
 	import GarbageBin from '$lib/components/icons/GarbageBin.svelte';
@@ -44,15 +45,17 @@
 			align="start"
 			transition={flyAndScale}
 		>
-			<DropdownMenu.Item
+			{#if $config.features.enable_community_sharing}
-				class="flex gap-2 items-center px-3 py-2 text-sm  font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800  rounded-md"
+				<DropdownMenu.Item
-				on:click={() => {
+					class="flex gap-2 items-center px-3 py-2 text-sm  font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800  rounded-md"
-					shareHandler();
+					on:click={() => {
-				}}
+						shareHandler();
-			>
+					}}
-				<Share />
+				>
-				<div class="flex items-center">{$i18n.t('Share')}</div>
+					<Share />
-			</DropdownMenu.Item>
+					<div class="flex items-center">{$i18n.t('Share')}</div>
+				</DropdownMenu.Item>
+			{/if}
 
 			<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-md"

src/lib/components/workspace/Tools/ToolMenu.svelte

@@ -12,6 +12,7 @@
 	import ArchiveBox from '$lib/components/icons/ArchiveBox.svelte';
 	import DocumentDuplicate from '$lib/components/icons/DocumentDuplicate.svelte';
 	import ArrowDownTray from '$lib/components/icons/ArrowDownTray.svelte';
+	import { config } from '$lib/stores';
 
 	const i18n = getContext('i18n');
 
@@ -69,15 +70,17 @@
 				<div class="flex items-center">{$i18n.t('Edit')}</div>
 			</DropdownMenu.Item>
 
-			<DropdownMenu.Item
+			{#if $config.features.enable_community_sharing}
-				class="flex gap-2 items-center px-3 py-2 text-sm  font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800  rounded-md"
+				<DropdownMenu.Item
-				on:click={() => {
+					class="flex gap-2 items-center px-3 py-2 text-sm  font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800  rounded-md"
-					shareHandler();
+					on:click={() => {
-				}}
+						shareHandler();
-			>
+					}}
-				<Share />
+				>
-				<div class="flex items-center">{$i18n.t('Share')}</div>
+					<Share />
-			</DropdownMenu.Item>
+					<div class="flex items-center">{$i18n.t('Share')}</div>
+				</DropdownMenu.Item>
+			{/if}
 
 			<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-md"

src/lib/components/workspace/Tools/ToolkitEditor.svelte

@@ -1,5 +1,5 @@
 <script>
-	import { getContext, createEventDispatcher, onMount, tick } from 'svelte';
+	import { getContext, onMount, tick } from 'svelte';
 
 	const i18n = getContext('i18n');
 
@@ -12,8 +12,6 @@
 	import LockClosed from '$lib/components/icons/LockClosed.svelte';
 	import AccessControlModal from '../common/AccessControlModal.svelte';
 
-	const dispatch = createEventDispatcher();
-
 	let formElement = null;
 	let loading = false;
 
@@ -23,6 +21,8 @@
 	export let edit = false;
 	export let clone = false;
 
+	export let onSave = () => {};
+
 	export let id = '';
 	export let name = '';
 	export let meta = {
@@ -150,7 +150,7 @@ class Tools:
 
 	const saveHandler = async () => {
 		loading = true;
-		dispatch('save', {
+		onSave({
 			id,
 			name,
 			meta,
@@ -284,10 +284,10 @@ class Tools:
 						value={content}
 						{boilerplate}
 						lang="python"
-						on:change={(e) => {
+						onChange={(e) => {
-							_content = e.detail.value;
+							_content = e;
 						}}
-						on:save={() => {
+						onSave={() => {
 							if (formElement) {
 								formElement.requestSubmit();
 							}

src/lib/i18n/locales/ar-BH/translation.json

@@ -13,6 +13,7 @@
 	"A task model is used when performing tasks such as generating titles for chats and web search queries": "يتم استخدام نموذج المهمة عند تنفيذ مهام مثل إنشاء عناوين للدردشات واستعلامات بحث الويب",
 	"a user": "مستخدم",
 	"About": "عن",
+	"Accept autocomplete generation / Jump to prompt variable": "",
 	"Access": "",
 	"Access Control": "",
 	"Accessible to all users": "",
@@ -85,6 +86,7 @@
 	"Archive All Chats": "أرشفة جميع الدردشات",
 	"Archived Chats": "الأرشيف المحادثات",
 	"archived-chat-export": "",
+	"Are you sure you want to clear all memories? This action cannot be undone.": "",
 	"Are you sure you want to delete this channel?": "",
 	"Are you sure you want to delete this message?": "",
 	"Are you sure you want to unarchive all archived chats?": "",
@@ -93,7 +95,7 @@
 	"Artifacts": "",
 	"Ask a question": "",
 	"Assistant": "",
-	"Attach file": "أرفق ملف",
+	"Attach file from knowledge": "",
 	"Attention to detail": "انتبه للتفاصيل",
 	"Attribute for Mail": "",
 	"Attribute for Username": "",
@@ -127,6 +129,7 @@
 	"Bocha Search API Key": "",
 	"Brave Search API Key": "مفتاح واجهة برمجة تطبيقات البحث الشجاع",
 	"By {{name}}": "",
+	"Bypass Embedding and Retrieval": "",
 	"Bypass SSL verification for Websites": "تجاوز التحقق من SSL للموقع",
 	"Calendar": "",
 	"Call": "",
@@ -156,11 +159,11 @@
 	"Checking for updates...": "البحث عن تحديثات",
 	"Choose a model before saving...": "أختار موديل قبل الحفظ",
 	"Chunk Overlap": "Chunk تداخل",
-	"Chunk Params": "Chunk المتغيرات",
 	"Chunk Size": "Chunk حجم",
 	"Ciphers": "",
 	"Citation": "اقتباس",
 	"Clear memory": "",
+	"Clear Memory": "",
 	"click here": "",
 	"Click here for filter guides.": "",
 	"Click here for help.": "أضغط هنا للمساعدة",
@@ -182,6 +185,7 @@
 	"Code execution": "",
 	"Code Execution": "",
 	"Code Execution Engine": "",
+	"Code Execution Timeout": "",
 	"Code formatted successfully": "",
 	"Code Interpreter": "",
 	"Code Interpreter Engine": "",
@@ -207,7 +211,7 @@
 	"Constrains effort on reasoning for reasoning models. Only applicable to reasoning models from specific providers that support reasoning effort. (Default: medium)": "",
 	"Contact Admin for WebUI Access": "",
 	"Content": "الاتصال",
-	"Content Extraction": "",
+	"Content Extraction Engine": "",
 	"Context Length": "طول السياق",
 	"Continue Response": "متابعة الرد",
 	"Continue with {{provider}}": "",
@@ -244,6 +248,7 @@
 	"Current Model": "الموديل المختار",
 	"Current Password": "كلمة السر الحالية",
 	"Custom": "مخصص",
+	"Danger Zone": "",
 	"Dark": "مظلم",
 	"Database": "قاعدة البيانات",
 	"December": "ديسمبر",
@@ -304,6 +309,8 @@
 	"Do not install functions from sources you do not fully trust.": "",
 	"Do not install tools from sources you do not fully trust.": "",
 	"Document": "المستند",
+	"Document Intelligence": "",
+	"Document Intelligence endpoint and key required.": "",
 	"Documentation": "",
 	"Documents": "مستندات",
 	"does not make any external connections, and your data stays securely on your locally hosted server.": "لا يجري أي اتصالات خارجية، وتظل بياناتك آمنة على الخادم المستضاف محليًا.",
@@ -321,6 +328,7 @@
 	"Draw": "",
 	"Drop any files here to add to the conversation": "أسقط أية ملفات هنا لإضافتها إلى المحادثة",
 	"e.g. '30s','10m'. Valid time units are 's', 'm', 'h'.": "e.g. '30s','10m'. الوحدات الزمنية الصالحة هي 's', 'm', 'h'.",
+	"e.g. 60": "",
 	"e.g. A filter to remove profanity from text": "",
 	"e.g. My Filter": "",
 	"e.g. My Tools": "",
@@ -338,6 +346,7 @@
 	"ElevenLabs": "",
 	"Email": "البريد",
 	"Embark on adventures": "",
+	"Embedding": "",
 	"Embedding Batch Size": "",
 	"Embedding Model": "نموذج التضمين",
 	"Embedding Model Engine": "تضمين محرك النموذج",
@@ -346,15 +355,12 @@
 	"Enable autocomplete generation for chat messages": "",
 	"Enable Code Interpreter": "",
 	"Enable Community Sharing": "تمكين مشاركة المجتمع",
-	"Enable Google Drive": "",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "تفعيل عمليات التسجيل الجديدة",
-	"Enable Web Search": "تمكين بحث الويب",
 	"Enabled": "",
-	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "تأكد من أن ملف CSV الخاص بك يتضمن 4 أعمدة بهذا الترتيب: Name, Email, Password, Role.",
 	"Enter {{role}} message here": "أدخل رسالة {{role}} هنا",
 	"Enter a detail about yourself for your LLMs to recall": "ادخل معلومات عنك تريد أن يتذكرها الموديل",
@@ -370,6 +376,8 @@
 	"Enter Chunk Overlap": "أدخل الChunk Overlap",
 	"Enter Chunk Size": "أدخل Chunk الحجم",
 	"Enter description": "",
+	"Enter Document Intelligence Endpoint": "",
+	"Enter Document Intelligence Key": "",
 	"Enter domains separated by commas (e.g., example.com,site.org)": "",
 	"Enter Exa API Key": "",
 	"Enter Github Raw URL": "أدخل عنوان URL ل Github Raw",
@@ -408,6 +416,7 @@
 	"Enter Tavily API Key": "",
 	"Enter the public URL of your WebUI. This URL will be used to generate links in the notifications.": "",
 	"Enter Tika Server URL": "",
+	"Enter timeout in seconds": "",
 	"Enter Top K": "أدخل Top K",
 	"Enter URL (e.g. http://127.0.0.1:7860/)": "الرابط (e.g. http://127.0.0.1:7860/)",
 	"Enter URL (e.g. http://localhost:11434)": "URL (e.g. http://localhost:11434)",
@@ -500,10 +509,13 @@
 	"Functions allow arbitrary code execution": "",
 	"Functions allow arbitrary code execution.": "",
 	"Functions imported successfully": "",
+	"Gemini": "",
+	"Gemini API Config": "",
+	"Gemini API Key is required.": "",
 	"General": "عام",
-	"General Settings": "الاعدادات العامة",
 	"Generate an image": "",
 	"Generate Image": "",
+	"Generate prompt pair": "",
 	"Generating search query": "إنشاء استعلام بحث",
 	"Get started": "",
 	"Get started with {{WEBUI_NAME}}": "",
@@ -559,6 +571,7 @@
 	"Input commands": "إدخال الأوامر",
 	"Install from Github URL": "التثبيت من عنوان URL لجيثب",
 	"Instant Auto-Send After Voice Transcription": "",
+	"Integration": "",
 	"Interface": "واجهه المستخدم",
 	"Invalid file format.": "",
 	"Invalid Tag": "تاق غير صالحة",
@@ -606,16 +619,17 @@
 	"Listening...": "",
 	"Llama.cpp": "",
 	"LLMs can make mistakes. Verify important information.": "يمكن أن تصدر بعض الأخطاء. لذلك يجب التحقق من المعلومات المهمة",
+	"Loader": "",
 	"Loading Kokoro.js...": "",
 	"Local": "",
 	"Local Models": "",
+	"Location access not allowed": "",
 	"Lost": "",
 	"LTR": "من جهة اليسار إلى اليمين",
 	"Made by Open WebUI Community": "OpenWebUI تم إنشاؤه بواسطة مجتمع ",
 	"Make sure to enclose them with": "تأكد من إرفاقها",
 	"Make sure to export a workflow.json file as API format from ComfyUI.": "",
 	"Manage": "",
-	"Manage Arena Models": "",
 	"Manage Direct Connections": "",
 	"Manage Models": "",
 	"Manage Ollama": "",
@@ -683,6 +697,7 @@
 	"No HTML, CSS, or JavaScript content found.": "",
 	"No inference engine with management support found": "",
 	"No knowledge found": "",
+	"No memories to clear": "",
 	"No model IDs": "",
 	"No models found": "",
 	"No models selected": "",
@@ -712,6 +727,7 @@
 	"Ollama API settings updated": "",
 	"Ollama Version": "Ollama الاصدار",
 	"On": "تشغيل",
+	"OneDrive": "",
 	"Only alphanumeric characters and hyphens are allowed": "",
 	"Only alphanumeric characters and hyphens are allowed in the command string.": "يُسمح فقط بالأحرف الأبجدية الرقمية والواصلات في سلسلة الأمر.",
 	"Only collections can be edited, create a new knowledge base to edit/add documents.": "",
@@ -782,11 +798,9 @@
 	"Prompt updated successfully": "",
 	"Prompts": "مطالبات",
 	"Prompts Access": "",
-	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "Ollama.com \"{{searchValue}}\" أسحب من ",
 	"Pull a model from Ollama.com": "Ollama.com سحب الموديل من ",
 	"Query Generation Prompt": "",
-	"Query Params": "Query Params",
 	"RAG Template": "RAG تنمبلت",
 	"Rating": "",
 	"Re-rank models by topic similarity": "",
@@ -821,6 +835,7 @@
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval": "",
 	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
@@ -874,7 +889,6 @@
 	"Select an Ollama instance": "",
 	"Select Engine": "",
 	"Select Knowledge": "",
-	"Select model": " أختار موديل",
 	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "النموذج (النماذج) المحددة لا تدعم مدخلات الصور",
 	"Semantic distance to query": "",
@@ -951,6 +965,7 @@
 	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
+	"Talk to model": "",
 	"Tap to interrupt": "",
 	"Tasks": "",
 	"Tavily API Key": "",
@@ -1035,6 +1050,7 @@
 	"Top P": "Top P",
 	"Transformers": "",
 	"Trouble accessing Ollama?": "هل تواجه مشكلة في الوصول",
+	"Trust Proxy Environment": "",
 	"TTS Model": "",
 	"TTS Settings": "TTS اعدادات",
 	"TTS Voice": "",
@@ -1098,7 +1114,6 @@
 	"Warning: Jupyter execution enables arbitrary code execution, posing severe security risks—proceed with extreme caution.": "",
 	"Web": "Web",
 	"Web API": "",
-	"Web Loader Settings": "Web تحميل اعدادات",
 	"Web Search": "بحث الويب",
 	"Web Search Engine": "محرك بحث الويب",
 	"Web Search in Chat": "",
@@ -1140,5 +1155,6 @@
 	"Your account status is currently pending activation.": "",
 	"Your entire contribution will go directly to the plugin developer; Open WebUI does not take any percentage. However, the chosen funding platform might have its own fees.": "",
 	"Youtube": "Youtube",
-	"Youtube Loader Settings": "Youtube تحميل اعدادات"
+	"Youtube Language": "",
+	"Youtube Proxy URL": ""
 }