diff --git a/.github/workflows/deploy-to-hf-spaces.yml b/.github/workflows/deploy-to-hf-spaces.yml
index a30046af89..cda9f1eb4b 100644
--- a/.github/workflows/deploy-to-hf-spaces.yml
+++ b/.github/workflows/deploy-to-hf-spaces.yml
@@ -57,7 +57,8 @@ jobs:
git lfs install
git lfs track "*.ttf"
git lfs track "*.jpg"
- rm demo.gif
+ rm demo.png
+ rm banner.png
git add .
git commit -m "GitHub deploy: ${{ github.sha }}"
git push --force https://open-webui:${HF_TOKEN}@huggingface.co/spaces/open-webui/open-webui main
diff --git a/.prettierignore b/.prettierignore
index 82c4912572..83bbde598b 100644
--- a/.prettierignore
+++ b/.prettierignore
@@ -3,8 +3,6 @@ pnpm-lock.yaml
package-lock.json
yarn.lock
-kubernetes/
-
# Copy of .gitignore
.DS_Store
node_modules
diff --git a/CHANGELOG.md b/CHANGELOG.md
index d0730963ec..be130ae6de 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,110 @@ 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).
+## [0.6.42] - 2025-12-21
+
+### Added
+
+- 📚 Knowledge base file management was overhauled with server-side pagination loading 30 files at a time instead of loading entire collections at once, dramatically improving performance and responsiveness for large knowledge bases with hundreds or thousands of files, reducing initial load times and memory usage while adding server-side search and filtering, view options for files added by the user versus shared files, customizable sorting by name or date, and file authorship tracking with upload timestamps. [Commit](https://github.com/open-webui/open-webui/commit/94a8439105f30203ea9d729787c9c5978f5c22a2)
+- ✨ Knowledge base file management was enhanced with automatic list refresh after file operations ensuring immediate UI updates, improved permission validation at the model layer, and automatic channel-file association for files uploaded with channel metadata. [Commit](https://github.com/open-webui/open-webui/commit/c15201620d03a9b60b800a34d8dc3426722c5b8b)
+- 🔎 Knowledge command in chat input now uses server-side search for massive performance increases when selecting knowledge bases and files. [Commit](https://github.com/open-webui/open-webui/commit/0addc1ea461d7b4eee8fe0ca2fedd615b3988b0e)
+- 🗂️ Knowledge workspace listing now uses server-side pagination loading 30 collections at a time with new search endpoints supporting query filtering and view options for created versus shared collections. [Commit](https://github.com/open-webui/open-webui/commit/ceae3d48e603f53313d5483abe94099e20e914e8)
+- 📖 Knowledge workspace now displays all collections with read access including shared read-only collections, enabling users to discover and explore knowledge bases they don't own while maintaining proper access controls through visual "Read Only" badges and automatically disabled editing controls for name, description, file uploads, content editing, and deletion operations. [Commit](https://github.com/open-webui/open-webui/commit/693636d971d0e8398fa0c9ec3897686750007af5)
+- 📁 Bulk website and YouTube video attachment now supports adding multiple URLs at once (newline-separated) with automatic YouTube detection and transcript retrieval, processed sequentially to prevent resource strain, and both websites and videos can now be added directly to knowledge bases through the workspace UI. [Commit](https://github.com/open-webui/open-webui/commit/7746e9f4b831f09953ad2b659b96e0fd52911031), [#6202](https://github.com/open-webui/open-webui/issues/6202), [#19587](https://github.com/open-webui/open-webui/pull/19587), [#8231](https://github.com/open-webui/open-webui/pull/8231)
+- 🪟 Sidebar width is now resizable on desktop devices with persistent storage in localStorage, enforcing minimum and maximum width constraints (220px to 480px) while all layout components now reference the dynamic sidebar width via CSS variables for consistent responsive behavior. [Commit](https://github.com/open-webui/open-webui/commit/b364cf43d3e8fd3557f65f17bc285bfaca5ed368)
+- 📝 Notes feature now supports server-side search and filtering with view options for notes created by the user versus notes shared with them, customizable sorting by name or date in both list and grid view modes within a redesigned interface featuring consolidated note management controls in a unified header, group-based permission sharing with read, write, and read-only access control displaying note authorship and sharing status for better collaboration, and paginated infinite scroll for improved performance with large note collections. [Commit](https://github.com/open-webui/open-webui/commit/9b24cddef6c4862bd899eb8d6332cafff54e871d)
+- 👁️ Notes now support read-only access permissions, allowing users to share notes for viewing without granting edit rights, with the editor automatically becoming non-editable and appropriate UI indicators when read-only access is detected. [Commit](https://github.com/open-webui/open-webui/commit/4363df175d50e0f9729381ac2ba9b37a3c3a966d)
+- 📄 Notes can now be created directly from the chat input field, allowing users to save drafted messages or content as notes without navigation or retyping. [Commit](https://github.com/open-webui/open-webui/commit/00c2b6ca405d617e3d7520953a00a36c19c790ec)
+- 🪟 Sidebar folders, channels, and pinned models sections now automatically expand when creating new items or pinning models, providing immediate visual feedback for user actions. [Commit](https://github.com/open-webui/open-webui/commit/f826d3ed75213a0a1b31b50d030bfb1d5e91d199), [#19929](https://github.com/open-webui/open-webui/pull/19929)
+- 📋 Chat file associations are now properly tracked in the database through a new "chat_file" table, enabling accurate file management across chats and ensuring proper cleanup of files when chats are deleted, while improving database consistency in multi-node deployments. [Commit](https://github.com/open-webui/open-webui/commit/f1bf4f20c53e6493f0eb6fa2f12cb84c2d22da52)
+- 🖼️ User-uploaded images are now automatically converted from base64 to actual file storage on the server, eliminating large inline base64 strings from being stored in chat history and reducing message payload sizes while enabling better image management and sharing across multiple chats. [Commit](https://github.com/open-webui/open-webui/commit/f1bf4f20c53e6493f0eb6fa2f12cb84c2d22da52)
+- 📸 Shared chats with generated or edited images now correctly display images when accessed by other users by properly linking generated images to their chat and message through the chat_file table, ensuring images remain accessible in shared chat links. [Commit](https://github.com/open-webui/open-webui/commit/446cc0ac6063402a743e949f50612376ed5a8437), [#19393](https://github.com/open-webui/open-webui/issues/19393)
+- 📊 File viewer modal was significantly enhanced with native-like viewers for Excel/CSV spreadsheets rendering as interactive scrollable tables with multi-sheet navigation support, Markdown documents displaying with full typography including headers, lists, links, and tables, and source code files showing syntax highlighting, all accessible through a tabbed interface defaulting to raw text view. [#20035](https://github.com/open-webui/open-webui/pull/20035), [#2867](https://github.com/open-webui/open-webui/issues/2867)
+- 📏 Chat input now displays an expand button in the top-right corner when messages exceed two lines, providing optional access to a full-screen editor for composing longer messages with enhanced workspace and visibility while temporarily disabling the main input to prevent editing conflicts. [Commit](https://github.com/open-webui/open-webui/commit/205c7111200c22da42e9b5fe1e676aec9cca6daa)
+- 💬 Channel message data lazy loading was implemented, deferring attachment and file metadata retrieval until needed to improve initial message list load performance. [Commit](https://github.com/open-webui/open-webui/commit/54b7ec56d6bcd2d79addc1694b757dab18cf18c5)
+- 🖼️ Channel image upload handling was optimized to process and store compressed images directly as files rather than inline data, improving memory efficiency and message load times. [Commit](https://github.com/open-webui/open-webui/commit/22f1b764a7ea1add0a896906a9ef00b4b6743adc)
+- 🎥 Video file playback support was added to channel messages, enabling inline video viewing with native player controls. [Commit](https://github.com/open-webui/open-webui/commit/7b126b23d50a0bd36a350fe09dc1dbe3df105318)
+- 🔐 LDAP authentication now supports user entries with multiple username attributes, correctly handling cases where the username field contains a list of values. [Commit](https://github.com/open-webui/open-webui/commit/379f888c9dc6dce21c3ef7a1fc455258aff993dc), [#19878](https://github.com/open-webui/open-webui/issues/19878)
+- 👨👩👧👦 The "ENABLE_PUBLIC_ACTIVE_USERS_COUNT" environment variable now allows restricting active user count visibility to administrators, reducing backend load and addressing privacy concerns in large deployments. [#20027](https://github.com/open-webui/open-webui/pull/20027), [#13026](https://github.com/open-webui/open-webui/issues/13026)
+- 🚀 Models page search input performance was optimized with a 300ms debounce to reduce server load and improve responsiveness. [#19832](https://github.com/open-webui/open-webui/pull/19832)
+- 💨 Frontend performance was optimized by preventing unnecessary API calls for API Keys and Channels features when they are disabled in admin settings, reducing backend noise and improving overall system efficiency. [#20043](https://github.com/open-webui/open-webui/pull/20043), [#19967](https://github.com/open-webui/open-webui/issues/19967)
+- 📎 Channel file association tracking was implemented, automatically linking uploaded files to their respective channels with a dedicated association table enabling better organization and future file management features within channels. [Commit](https://github.com/open-webui/open-webui/commit/2bccf8350d0915f69b8020934bb179c52e81b7b5)
+- 👥 User profile previews now display group membership information for easier identification of user roles and permissions. [Commit](https://github.com/open-webui/open-webui/commit/2b1a29d44bde9fbc20ff9f0a5ded1ce8ded9d90d)
+- 🌍 The "SEARXNG_LANGUAGE" environment variable now allows configuring search language for SearXNG queries, replacing the hardcoded "en-US" default with a configurable setting that defaults to "all". [#19909](https://github.com/open-webui/open-webui/pull/19909)
+- ⏳ The "MINERU_API_TIMEOUT" environment variable now allows configuring request timeouts for MinerU document processing operations. [#20016](https://github.com/open-webui/open-webui/pull/20016), [#18495](https://github.com/open-webui/open-webui/issues/18495)
+- 🔧 The "RAG_EXTERNAL_RERANKER_TIMEOUT" environment variable now allows configuring request timeouts for external reranker operations. [#20049](https://github.com/open-webui/open-webui/pull/20049), [#19900](https://github.com/open-webui/open-webui/issues/19900)
+- 🎨 OpenAI GPT-IMAGE 1.5 model support was added for image generation and editing with automatic image size capabilities. [Commit](https://github.com/open-webui/open-webui/commit/4c2e5c93e9287479f56f780708656136849ccaee)
+- 🔑 The "OAUTH_AUDIENCE" environment variable now allows OAuth providers to specify audience parameters for JWT access token generation. [#19768](https://github.com/open-webui/open-webui/pull/19768)
+- ⏰ The "REDIS_SOCKET_CONNECT_TIMEOUT" environment variable now allows configuring socket connection timeouts for Redis and Sentinel connections, addressing potential failover and responsiveness issues in distributed deployments. [#19799](https://github.com/open-webui/open-webui/pull/19799), [Docs:#882](https://github.com/open-webui/docs/pull/882)
+- ⏱️ The "WEB_LOADER_TIMEOUT" environment variable now allows configuring request timeouts for SafeWebBaseLoader operations. [#19804](https://github.com/open-webui/open-webui/pull/19804), [#19734](https://github.com/open-webui/open-webui/issues/19734)
+- 🚀 Models API endpoint performance was optimized through batched model loading, eliminating N+1 queries and significantly reducing response times when filtering models by user permissions. [Commit](https://github.com/open-webui/open-webui/commit/0dd2cfe1f273fbacdbe90300a97c021f2e678656)
+- 🔀 Custom model fallback handling was added, allowing workspace-created custom models to automatically fall back to the default chat model when their configured base model is not found; set "ENABLE_CUSTOM_MODEL_FALLBACK" to true to enable, preventing workflow disruption when base models are removed or renamed, while ensuring other requests remain unaffected. [Commit](https://github.com/open-webui/open-webui/commit/b35aeb8f46e0e278c6f4538382c2b6838e24cc5a), [#19985](https://github.com/open-webui/open-webui/pull/19985)
+- 📡 A new /feedbacks/all/ids API endpoint was added to return only feedback IDs without metadata, significantly improving performance for external integrations working with large feedback collections. [Commit](https://github.com/open-webui/open-webui/commit/53c1ca64b7205d85f6de06bd69e3e265d15546b8)
+- 📈 An experimental chat usage statistics endpoint (GET /api/v1/chats/stats/usage) was added with pagination support (50 chats per page) and comprehensive per-chat analytics including model usage counts, user and assistant message breakdowns, average response times calculated from message timestamps, average content lengths, and last activity timestamps; this endpoint remains experimental and not suitable for production use as it performs intensive calculations by processing entire message histories for each chat without caching. [Commit](https://github.com/open-webui/open-webui/commit/a7993f6f4e4591cd2aaa4718ece9e5623557d019)
+- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌐 Translations for German, Danish, Finnish, Korean, Portuguese (Brazil), Simplified Chinese, Traditional Chinese, Catalan, and Spanish were enhanced and expanded.
+
+### Fixed
+
+- ⚡ External reranker operations were optimized to prevent event loop blocking by offloading synchronous HTTP requests to a thread pool using asyncio.to_thread(), eliminating application freezes during RAG reranking queries. [#20049](https://github.com/open-webui/open-webui/pull/20049), [#19900](https://github.com/open-webui/open-webui/issues/19900)
+- 💭 Text loss in the explanation feature when using the "CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE" environment variable was resolved by correcting newline handling in streaming responses. [#19829](https://github.com/open-webui/open-webui/pull/19829)
+- 📚 Knowledge base batch file addition failures caused by Pydantic validation errors are now prevented by making the meta field optional in file metadata responses, allowing files without metadata to be processed correctly. [#20022](https://github.com/open-webui/open-webui/pull/20022), [#14220](https://github.com/open-webui/open-webui/issues/14220)
+- 🗄️ PostgreSQL null byte insertion failures when attaching web pages or processing embedded content are now prevented by consolidating text sanitization logic across chat messages, web search results, and knowledge base documents, removing null bytes and invalid UTF-8 surrogates before database insertion. [#20072](https://github.com/open-webui/open-webui/pull/20072), [#19867](https://github.com/open-webui/open-webui/issues/19867), [#18201](https://github.com/open-webui/open-webui/issues/18201), [#15616](https://github.com/open-webui/open-webui/issues/15616)
+- 🎫 MCP OAuth 2.1 token exchange failures are now fixed by removing duplicate credential passing that caused "ID1,ID1" concatenation and 401 errors from the token endpoint. [#20076](https://github.com/open-webui/open-webui/pull/20076), [#19823](https://github.com/open-webui/open-webui/issues/19823)
+- 📝 Notes "Improve" action now works correctly after the streaming API change in v0.6.41 by ensuring uploaded files are fully retrieved with complete metadata before processing, restoring note improvement and summarization functionality. [Commit](https://github.com/open-webui/open-webui/commit/a3458f492c53a3b00405f59fbe1ea953fe364f18), [#20078](https://github.com/open-webui/open-webui/discussions/20078)
+- 🔑 MCP OAuth 2.1 tool servers now work correctly in multi-node deployments through lazy-loading of OAuth clients from Redis-synced configuration, eliminating 404 errors when load balancers route requests to nodes that didn't process the original config update. [#20076](https://github.com/open-webui/open-webui/pull/20076), [#19902](https://github.com/open-webui/open-webui/pull/19902), [#19901](https://github.com/open-webui/open-webui/issues/19901)
+- 🧩 Chat loading failures when channels permissions were disabled are now prevented through graceful error handling. [Commit](https://github.com/open-webui/open-webui/commit/5c2df97f04cce5cb7087d288f816f91a739688c1)
+- 🔍 Search bar freezing and crashing issues in Models, Chat, and Archived Chat pages caused by excessively long queries exceeding server URL limits were resolved by truncating queries to 500 characters, and knowledge base layout shifting with long names was fixed by adjusting flex container properties. [#19832](https://github.com/open-webui/open-webui/pull/19832)
+- 🎛️ Rate limiting errors (HTTP 429) with Brave Search free tier when generating multiple queries are now prevented through asyncio.Semaphore-based concurrency control applied globally to all search engines. [#20070](https://github.com/open-webui/open-webui/pull/20070), [#20003](https://github.com/open-webui/open-webui/issues/20003), [#14107](https://github.com/open-webui/open-webui/issues/14107), [#15134](https://github.com/open-webui/open-webui/issues/15134)
+- 💥 UI crashes and white screen errors caused by null chat lists during loading or network failures were prevented by adding null safety checks to chat iteration in folder placeholders and archived chat modals. [#19898](https://github.com/open-webui/open-webui/pull/19898)
+- 🧩 Chat overview tab crashes caused by undefined model references were resolved by adding proper null checks when accessing deleted or ejected models. [#19935](https://github.com/open-webui/open-webui/pull/19935)
+- 🔄 MultiResponseMessages component crashes when navigating chat history after removing or changing selected models are now prevented through proper component re-initialization. [Commit](https://github.com/open-webui/open-webui/commit/870e29e3738da968c396b70532f365a3c2f71995), [#18599](https://github.com/open-webui/open-webui/issues/18599)
+- 🚫 Channel API endpoint access is now correctly blocked when channels are globally disabled, preventing users with channel permissions from accessing channel data via API requests when the feature is turned off in admin settings. [#19957](https://github.com/open-webui/open-webui/pull/19957), [#19914](https://github.com/open-webui/open-webui/issues/19914)
+- 👤 User list popup display in the admin panel was fixed to correctly track user identity when sorting or filtering changes the list order, preventing popups from showing incorrect user information. [Commit](https://github.com/open-webui/open-webui/commit/ae47101dc6aef2c7d8ae0d843985341fff820057), [#20046](https://github.com/open-webui/open-webui/issues/20046)
+- 👥 User selection in the "Edit User Group" modal now preserves pagination position, allowing administrators to select multiple users across pages without resetting to page 1. [#19959](https://github.com/open-webui/open-webui/pull/19959)
+- 📸 Model avatar images now update immediately in the admin models list through proper Cache-Control headers, eliminating the need for manual cache clearing. [#19959](https://github.com/open-webui/open-webui/pull/19959)
+- 🔒 Temporary chat permission enforcement now correctly prevents users from enabling the feature through personal settings when disabled in default or group permissions. [#19785](https://github.com/open-webui/open-webui/issues/19785)
+- 🎨 Image editing with reference images now correctly uses both previously generated images and newly uploaded reference images. [Commit](https://github.com/open-webui/open-webui/commit/bcd50ed8f1b7387fd700538ae0d74fc72f3c53d0)
+- 🧠 Image generation and editing operations are now explicitly injected into system context, improving LLM comprehension even for weaker models so they reliably acknowledge operations instead of incorrectly claiming they cannot generate images. [Commit](https://github.com/open-webui/open-webui/commit/28b2fcab0cd036dbe646a66fe81890f288c77121)
+- 📑 Source citation rendering errors when citation syntax appeared in user messages or contexts without source data were resolved. [Commit](https://github.com/open-webui/open-webui/commit/3c8f1cf8e58d52e86375634b0381374298b1b4f3)
+- 📄 DOCX file parsing now works correctly in temporary chats through client-side text extraction, preventing raw data from being displayed. [Commit](https://github.com/open-webui/open-webui/commit/6993b0b40b10af8cdbe6626702cc94080fff9e22)
+- 🔧 Pipeline settings save failures when valve properties contain null values are now handled correctly. [#19791](https://github.com/open-webui/open-webui/pull/19791)
+- ⚙️ Model usage settings are now correctly preserved when switching between models instead of being unexpectedly cleared or reset. [#19868](https://github.com/open-webui/open-webui/pull/19868), [#19549](https://github.com/open-webui/open-webui/issues/19549)
+- 🛡️ Invalid PASSWORD_VALIDATION_REGEX_PATTERN configurations no longer cause startup warnings, with automatic fallback to the default pattern when regex compilation fails. [#20058](https://github.com/open-webui/open-webui/pull/20058)
+- 🎯 The DefaultFiltersSelector component in model settings now correctly displays when only global toggleable filters are present, enabling per-model default configuration. [#20066](https://github.com/open-webui/open-webui/pull/20066)
+- 🎤 Audio file upload failures caused by MIME type matching issues with spacing variations and codec parameters were resolved by implementing proper MIME type parsing. [#17771](https://github.com/open-webui/open-webui/pull/17771), [#17761](https://github.com/open-webui/open-webui/issues/17761)
+- ⌨️ Regenerate response keyboard shortcut now only activates when chat input is selected, preventing unintended regeneration when modals are open or other UI elements are focused. [#19875](https://github.com/open-webui/open-webui/pull/19875)
+- 📋 Log truncation issues in Docker deployments during application crashes were resolved by disabling Python stdio buffering, ensuring complete diagnostic output is captured. [#19844](https://github.com/open-webui/open-webui/issues/19844)
+- 🔴 Redis cluster compatibility issues with disabled KEYS command were resolved by replacing blocking KEYS operations with production-safe SCAN iterations. [#19871](https://github.com/open-webui/open-webui/pull/19871), [#15834](https://github.com/open-webui/open-webui/issues/15834)
+- 🔤 File attachment container layout issues when using RTL languages were resolved by applying chat direction settings to file containers across all message types. [#19891](https://github.com/open-webui/open-webui/pull/19891), [#19742](https://github.com/open-webui/open-webui/issues/19742)
+- 🔃 Ollama model list now automatically refreshes after model deletion, preventing deleted models from persisting in the UI and being inadvertently re-downloaded during subsequent pull operations. [#19912](https://github.com/open-webui/open-webui/pull/19912)
+- 🌐 Ollama Cloud web search now correctly applies domain filtering to search results. [Commit](https://github.com/open-webui/open-webui/commit/d4bd938a77c22409a1643c058b937a06e07baca9)
+- 📜 Tool specification serialization now preserves non-ASCII characters including Chinese text, improving LLM comprehension and tool selection accuracy by avoiding Unicode escape sequences. [#19942](https://github.com/open-webui/open-webui/pull/19942)
+- 🛟 Model editor stability was improved with null safety checks for tools, functions, and file input operations, preventing crashes when stores are undefined or file objects are invalid. [#19939](https://github.com/open-webui/open-webui/pull/19939)
+- 🗣️ MoA completion handling stability was improved with null safety checks for response objects, boolean casting for settings, and proper timeout type definitions. [#19921](https://github.com/open-webui/open-webui/pull/19921)
+- 🎛️ Chat functionality failures caused by empty logit_bias parameter values are now prevented by properly handling empty strings in the parameter parsing middleware. [#19982](https://github.com/open-webui/open-webui/issues/19982)
+- 🔏 Administrators can now delete read-only knowledge bases from deleted users, resolving permission issues that previously prevented cleanup of orphaned read-only content. [Commit](https://github.com/open-webui/open-webui/commit/59d6eb2badf46f9c2b1e879484ac33432915b575)
+- 💾 Cloned prompts and tools now correctly preserve their access control settings instead of being reset to null, preventing unintended visibility changes when duplicating private or restricted items. [#19960](https://github.com/open-webui/open-webui/pull/19960), [#19360](https://github.com/open-webui/open-webui/issues/19360)
+- 🎚️ Text scale adjustment buttons in Interface Settings were fixed to correctly increment and decrement the scale value. [#19699](https://github.com/open-webui/open-webui/pull/19699)
+- 🎭 Group channel invite button text visibility in light theme was corrected to display properly against dark backgrounds. [#19828](https://github.com/open-webui/open-webui/issues/19828)
+- 📁 The move button is now hidden when no folders exist, preventing display of non-functional controls. [#19705](https://github.com/open-webui/open-webui/pull/19705)
+- 📦 Qdrant client dependency was updated to resolve startup version incompatibility warnings. [#19757](https://github.com/open-webui/open-webui/pull/19757)
+- 🧮 The "ENABLE_ASYNC_EMBEDDING" environment variable is now correctly applied to embedding operations when configured exclusively via environment variables. [#19748](https://github.com/open-webui/open-webui/pull/19748)
+- 🌄 The "COMFYUI_WORKFLOW_NODES" and "IMAGES_EDIT_COMFYUI_WORKFLOW_NODES" environment variables are now correctly loaded and parsed as JSON lists, and the configuration key name was corrected from "COMFYUI_WORKFLOW" to "COMFYUI_WORKFLOW_NODES". [#19918](https://github.com/open-webui/open-webui/pull/19918), [#19886](https://github.com/open-webui/open-webui/issues/19886)
+- 💫 Channel name length is now limited to 128 characters with validation to prevent display issues caused by excessively long names. [Commit](https://github.com/open-webui/open-webui/commit/f509f5542dde384d34402f6df763f49a06bea109)
+- 🔐 Invalid PASSWORD_VALIDATION_REGEX_PATTERN configurations no longer cause startup warnings, with automatic fallback to the default pattern when regex compilation fails. [#20058](https://github.com/open-webui/open-webui/pull/20058)
+- 🔎 Bocha search with filter list functionality now works correctly by returning results as a list instead of a dictionary wrapper, ensuring compatibility with result filtering operations. [Commit](https://github.com/open-webui/open-webui/commit/b5bd8704fe1672da839bb3be6210d7cb494797ce), [#19733](https://github.com/open-webui/open-webui/issues/19733)
+
+### Changed
+
+- ⚠️ This release includes database schema changes; multi-worker, multi-server, or load-balanced deployments must update all instances simultaneously rather than performing rolling updates, as running mixed versions will cause application failures due to schema incompatibility between old and new instances.
+- 📡 WEB_SEARCH_CONCURRENT_REQUESTS default changed from 10 to 0 (unlimited) — This setting now applies to all search engines instead of only DuckDuckGo; previously users were implicitly limited to 10 concurrent queries, but now have unlimited parallel requests by default; set to 1 for sequential execution if using rate-limited APIs like Brave free tier. [#20070](https://github.com/open-webui/open-webui/pull/20070)
+- 💾 SQLCipher absolute path handling was fixed to properly support absolute database paths (e.g., "/app/data.db") instead of incorrectly stripping leading slashes and converting them to relative paths; this restores functionality for Docker volume mounts and explicit absolute path configurations while maintaining backward compatibility with relative paths. [#20074](https://github.com/open-webui/open-webui/pull/20074)
+- 🔌 Knowledge base file listing API was redesigned with paginated responses and new filtering parameters; the GET /knowledge/{id}/files endpoint now returns paginated results with user attribution instead of embedding all files in the knowledge object, which may require updates to custom integrations or scripts accessing knowledge base data programmatically. [Commit](https://github.com/open-webui/open-webui/commit/94a8439105f30203ea9d729787c9c5978f5c22a2)
+- 🗑️ Legacy knowledge base support for deprecated document collections and tag-based collections was removed; users with pre-knowledge base documents must migrate to the current knowledge base system as legacy items will no longer appear in selectors or command menus. [Commit](https://github.com/open-webui/open-webui/commit/a934dc997ed67a036dd7975e380f8036c447d3ed)
+- 🔨 Source-level log environment variables (AUDIO_LOG_LEVEL, CONFIG_LOG_LEVEL, MODELS_LOG_LEVEL, etc.) were removed as they provided limited configuration options and added significant complexity across 100+ files; the GLOBAL_LOG_LEVEL environment variable, which already took precedence over source-level settings, now serves as the exclusive logging configuration method. [#20045](https://github.com/open-webui/open-webui/pull/20045)
+- 🐍 LangChain was upgraded to version 1.2.0, representing a major dependency update and significant progress toward Python 3.13 compatibility while improving RAG pipeline functionality for document loading and retrieval operations. [#19991](https://github.com/open-webui/open-webui/pull/19991)
+
## [0.6.41] - 2025-12-02
### Added
diff --git a/Dockerfile b/Dockerfile
index ad393338d8..08c2de6dfa 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -55,6 +55,9 @@ ARG USE_RERANKING_MODEL
ARG UID
ARG GID
+# Python settings
+ENV PYTHONUNBUFFERED=1
+
## Basis ##
ENV ENV=prod \
PORT=8080 \
diff --git a/INSTALLATION.md b/INSTALLATION.md
deleted file mode 100644
index 4298b173e9..0000000000
--- a/INSTALLATION.md
+++ /dev/null
@@ -1,35 +0,0 @@
-### Installing Both Ollama and Open WebUI Using Kustomize
-
-For cpu-only pod
-
-```bash
-kubectl apply -f ./kubernetes/manifest/base
-```
-
-For gpu-enabled pod
-
-```bash
-kubectl apply -k ./kubernetes/manifest
-```
-
-### Installing Both Ollama and Open WebUI Using Helm
-
-Package Helm file first
-
-```bash
-helm package ./kubernetes/helm/
-```
-
-For cpu-only pod
-
-```bash
-helm install ollama-webui ./ollama-webui-*.tgz
-```
-
-For gpu-enabled pod
-
-```bash
-helm install ollama-webui ./ollama-webui-*.tgz --set ollama.resources.limits.nvidia.com/gpu="1"
-```
-
-Check the `kubernetes/helm/values.yaml` file to know which parameters are available for customization
diff --git a/LICENSE b/LICENSE
index 3991050972..faa0129c65 100644
--- a/LICENSE
+++ b/LICENSE
@@ -1,4 +1,4 @@
-Copyright (c) 2023-2025 Timothy Jaeryang Baek (Open WebUI)
+Copyright (c) 2023- Open WebUI Inc. [Created by Timothy Jaeryang Baek]
All rights reserved.
Redistribution and use in source and binary forms, with or without
diff --git a/README.md b/README.md
index 638cdacabb..a783db5c7e 100644
--- a/README.md
+++ b/README.md
@@ -10,11 +10,13 @@
[](https://discord.gg/5rJgQTnV4s)
[](https://github.com/sponsors/tjbck)
+
+
**Open WebUI is an [extensible](https://docs.openwebui.com/features/plugin/), feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline.** It supports various LLM runners like **Ollama** and **OpenAI-compatible APIs**, with **built-in inference engine** for RAG, making it a **powerful AI deployment solution**.
Passionate about open-source AI? [Join our team →](https://careers.openwebui.com/)
-
+
> [!TIP]
> **Looking for an [Enterprise Plan](https://docs.openwebui.com/enterprise)?** – **[Speak with Our Sales Team Today!](https://docs.openwebui.com/enterprise)**
@@ -188,14 +190,6 @@ docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=
### Keeping Your Docker Installation Up-to-Date
-In case you want to update your local Docker installation to the latest version, you can do it with [Watchtower](https://containrrr.dev/watchtower/):
-
-```bash
-docker run --rm --volume /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower --run-once open-webui
-```
-
-In the last part of the command, replace `open-webui` with your container name if it is different.
-
Check our Updating Guide available in our [Open WebUI Documentation](https://docs.openwebui.com/getting-started/updating).
### Using the Dev Branch 🌙
diff --git a/backend/open_webui/config.py b/backend/open_webui/config.py
index 41e88df5d2..c5ac40babd 100644
--- a/backend/open_webui/config.py
+++ b/backend/open_webui/config.py
@@ -629,6 +629,12 @@ OAUTH_ACCESS_TOKEN_REQUEST_INCLUDE_CLIENT_ID = (
== "true"
)
+OAUTH_AUDIENCE = PersistentConfig(
+ "OAUTH_AUDIENCE",
+ "oauth.audience",
+ os.environ.get("OAUTH_AUDIENCE", ""),
+)
+
def load_oauth_providers():
OAUTH_PROVIDERS.clear()
@@ -1300,7 +1306,7 @@ USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING = (
USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_SHARING = (
os.environ.get(
- "USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_PUBLIC_SHARING", "False"
+ "USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_SHARING", "False"
).lower()
== "true"
)
@@ -1339,8 +1345,7 @@ USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_PUBLIC_SHARING = (
USER_PERMISSIONS_NOTES_ALLOW_SHARING = (
- os.environ.get("USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING", "False").lower()
- == "true"
+ os.environ.get("USER_PERMISSIONS_NOTES_ALLOW_SHARING", "False").lower() == "true"
)
USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING = (
@@ -2518,6 +2523,12 @@ MINERU_API_URL = PersistentConfig(
os.environ.get("MINERU_API_URL", "http://localhost:8000"),
)
+MINERU_API_TIMEOUT = PersistentConfig(
+ "MINERU_API_TIMEOUT",
+ "rag.mineru_api_timeout",
+ os.environ.get("MINERU_API_TIMEOUT", "300"),
+)
+
MINERU_API_KEY = PersistentConfig(
"MINERU_API_KEY",
"rag.mineru_api_key",
@@ -2791,6 +2802,12 @@ RAG_EXTERNAL_RERANKER_API_KEY = PersistentConfig(
os.environ.get("RAG_EXTERNAL_RERANKER_API_KEY", ""),
)
+RAG_EXTERNAL_RERANKER_TIMEOUT = PersistentConfig(
+ "RAG_EXTERNAL_RERANKER_TIMEOUT",
+ "rag.external_reranker_timeout",
+ os.environ.get("RAG_EXTERNAL_RERANKER_TIMEOUT", ""),
+)
+
RAG_TEXT_SPLITTER = PersistentConfig(
"RAG_TEXT_SPLITTER",
@@ -2977,7 +2994,7 @@ WEB_SEARCH_DOMAIN_FILTER_LIST = PersistentConfig(
WEB_SEARCH_CONCURRENT_REQUESTS = PersistentConfig(
"WEB_SEARCH_CONCURRENT_REQUESTS",
"rag.web.search.concurrent_requests",
- int(os.getenv("WEB_SEARCH_CONCURRENT_REQUESTS", "10")),
+ int(os.getenv("WEB_SEARCH_CONCURRENT_REQUESTS", "0")),
)
@@ -2994,6 +3011,12 @@ WEB_LOADER_CONCURRENT_REQUESTS = PersistentConfig(
int(os.getenv("WEB_LOADER_CONCURRENT_REQUESTS", "10")),
)
+WEB_LOADER_TIMEOUT = PersistentConfig(
+ "WEB_LOADER_TIMEOUT",
+ "rag.web.loader.timeout",
+ os.getenv("WEB_LOADER_TIMEOUT", ""),
+)
+
ENABLE_WEB_LOADER_SSL_VERIFICATION = PersistentConfig(
"ENABLE_WEB_LOADER_SSL_VERIFICATION",
@@ -3020,6 +3043,12 @@ SEARXNG_QUERY_URL = PersistentConfig(
os.getenv("SEARXNG_QUERY_URL", ""),
)
+SEARXNG_LANGUAGE = PersistentConfig(
+ "SEARXNG_LANGUAGE",
+ "rag.web.search.searxng_language",
+ os.getenv("SEARXNG_LANGUAGE", "all"),
+)
+
YACY_QUERY_URL = PersistentConfig(
"YACY_QUERY_URL",
"rag.web.search.yacy_query_url",
@@ -3450,10 +3479,16 @@ COMFYUI_WORKFLOW = PersistentConfig(
os.getenv("COMFYUI_WORKFLOW", COMFYUI_DEFAULT_WORKFLOW),
)
+comfyui_workflow_nodes = os.getenv("COMFYUI_WORKFLOW_NODES", "")
+try:
+ comfyui_workflow_nodes = json.loads(comfyui_workflow_nodes)
+except json.JSONDecodeError:
+ comfyui_workflow_nodes = []
+
COMFYUI_WORKFLOW_NODES = PersistentConfig(
- "COMFYUI_WORKFLOW",
+ "COMFYUI_WORKFLOW_NODES",
"image_generation.comfyui.nodes",
- [],
+ comfyui_workflow_nodes,
)
IMAGES_OPENAI_API_BASE_URL = PersistentConfig(
@@ -3570,10 +3605,16 @@ IMAGES_EDIT_COMFYUI_WORKFLOW = PersistentConfig(
os.getenv("IMAGES_EDIT_COMFYUI_WORKFLOW", ""),
)
+images_edit_comfyui_workflow_nodes = os.getenv("IMAGES_EDIT_COMFYUI_WORKFLOW_NODES", "")
+try:
+ images_edit_comfyui_workflow_nodes = json.loads(images_edit_comfyui_workflow_nodes)
+except json.JSONDecodeError:
+ images_edit_comfyui_workflow_nodes = []
+
IMAGES_EDIT_COMFYUI_WORKFLOW_NODES = PersistentConfig(
"IMAGES_EDIT_COMFYUI_WORKFLOW_NODES",
"images.edit.comfyui.nodes",
- [],
+ images_edit_comfyui_workflow_nodes,
)
####################################
diff --git a/backend/open_webui/env.py b/backend/open_webui/env.py
index e3c50ea8d1..36860a0bee 100644
--- a/backend/open_webui/env.py
+++ b/backend/open_webui/env.py
@@ -85,32 +85,6 @@ if "cuda_error" in locals():
log.exception(cuda_error)
del cuda_error
-log_sources = [
- "AUDIO",
- "COMFYUI",
- "CONFIG",
- "DB",
- "IMAGES",
- "MAIN",
- "MODELS",
- "OLLAMA",
- "OPENAI",
- "RAG",
- "WEBHOOK",
- "SOCKET",
- "OAUTH",
-]
-
-SRC_LOG_LEVELS = {}
-
-for source in log_sources:
- log_env_var = source + "_LOG_LEVEL"
- SRC_LOG_LEVELS[source] = os.environ.get(log_env_var, "").upper()
- if SRC_LOG_LEVELS[source] not in logging.getLevelNamesMapping():
- SRC_LOG_LEVELS[source] = GLOBAL_LOG_LEVEL
- log.info(f"{log_env_var}: {SRC_LOG_LEVELS[source]}")
-
-log.setLevel(SRC_LOG_LEVELS["CONFIG"])
WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
if WEBUI_NAME != "Open WebUI":
@@ -364,6 +338,11 @@ if DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL is not None:
except Exception:
DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL = 0.0
+# Enable public visibility of active user count (when disabled, only admins can see it)
+ENABLE_PUBLIC_ACTIVE_USERS_COUNT = (
+ os.environ.get("ENABLE_PUBLIC_ACTIVE_USERS_COUNT", "True").lower() == "true"
+)
+
RESET_CONFIG_ON_START = (
os.environ.get("RESET_CONFIG_ON_START", "False").lower() == "true"
)
@@ -395,6 +374,13 @@ try:
except ValueError:
REDIS_SENTINEL_MAX_RETRY_COUNT = 2
+
+REDIS_SOCKET_CONNECT_TIMEOUT = os.environ.get("REDIS_SOCKET_CONNECT_TIMEOUT", "")
+try:
+ REDIS_SOCKET_CONNECT_TIMEOUT = float(REDIS_SOCKET_CONNECT_TIMEOUT)
+except ValueError:
+ REDIS_SOCKET_CONNECT_TIMEOUT = None
+
####################################
# UVICORN WORKERS
####################################
@@ -439,7 +425,13 @@ PASSWORD_VALIDATION_REGEX_PATTERN = os.environ.get(
"^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[^\w\s]).{8,}$",
)
-PASSWORD_VALIDATION_REGEX_PATTERN = re.compile(PASSWORD_VALIDATION_REGEX_PATTERN)
+try:
+ PASSWORD_VALIDATION_REGEX_PATTERN = re.compile(PASSWORD_VALIDATION_REGEX_PATTERN)
+except Exception as e:
+ log.error(f"Invalid PASSWORD_VALIDATION_REGEX_PATTERN: {e}")
+ PASSWORD_VALIDATION_REGEX_PATTERN = re.compile(
+ "^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[^\w\s]).{8,}$"
+ )
BYPASS_MODEL_ACCESS_CONTROL = (
@@ -546,6 +538,10 @@ if LICENSE_PUBLIC_KEY:
# MODELS
####################################
+ENABLE_CUSTOM_MODEL_FALLBACK = (
+ os.environ.get("ENABLE_CUSTOM_MODEL_FALLBACK", "False").lower() == "true"
+)
+
MODELS_CACHE_TTL = os.environ.get("MODELS_CACHE_TTL", "1")
if MODELS_CACHE_TTL == "":
MODELS_CACHE_TTL = None
@@ -620,9 +616,16 @@ ENABLE_WEBSOCKET_SUPPORT = (
WEBSOCKET_MANAGER = os.environ.get("WEBSOCKET_MANAGER", "")
WEBSOCKET_REDIS_OPTIONS = os.environ.get("WEBSOCKET_REDIS_OPTIONS", "")
+
+
if WEBSOCKET_REDIS_OPTIONS == "":
- log.debug("No WEBSOCKET_REDIS_OPTIONS provided, defaulting to None")
- WEBSOCKET_REDIS_OPTIONS = None
+ if REDIS_SOCKET_CONNECT_TIMEOUT:
+ WEBSOCKET_REDIS_OPTIONS = {
+ "socket_connect_timeout": REDIS_SOCKET_CONNECT_TIMEOUT
+ }
+ else:
+ log.debug("No WEBSOCKET_REDIS_OPTIONS provided, defaulting to None")
+ WEBSOCKET_REDIS_OPTIONS = None
else:
try:
WEBSOCKET_REDIS_OPTIONS = json.loads(WEBSOCKET_REDIS_OPTIONS)
diff --git a/backend/open_webui/functions.py b/backend/open_webui/functions.py
index 316efe18e7..e1604d126a 100644
--- a/backend/open_webui/functions.py
+++ b/backend/open_webui/functions.py
@@ -37,7 +37,7 @@ from open_webui.utils.plugin import (
from open_webui.utils.tools import get_tools
from open_webui.utils.access_control import has_access
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.env import GLOBAL_LOG_LEVEL
from open_webui.utils.misc import (
add_or_update_system_message,
@@ -54,7 +54,6 @@ from open_webui.utils.payload import (
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
def get_function_module_by_id(request: Request, pipe_id: str):
diff --git a/backend/open_webui/internal/db.py b/backend/open_webui/internal/db.py
index b6913d87b0..a5eecd6605 100644
--- a/backend/open_webui/internal/db.py
+++ b/backend/open_webui/internal/db.py
@@ -9,7 +9,6 @@ from open_webui.env import (
OPEN_WEBUI_DIR,
DATABASE_URL,
DATABASE_SCHEMA,
- SRC_LOG_LEVELS,
DATABASE_POOL_MAX_OVERFLOW,
DATABASE_POOL_RECYCLE,
DATABASE_POOL_SIZE,
@@ -25,7 +24,6 @@ from sqlalchemy.sql.type_api import _T
from typing_extensions import Self
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["DB"])
class JSONField(types.TypeDecorator):
@@ -92,8 +90,6 @@ if SQLALCHEMY_DATABASE_URL.startswith("sqlite+sqlcipher://"):
# Extract database path from SQLCipher URL
db_path = SQLALCHEMY_DATABASE_URL.replace("sqlite+sqlcipher://", "")
- if db_path.startswith("/"):
- db_path = db_path[1:] # Remove leading slash for relative paths
# Create a custom creator function that uses sqlcipher3
def create_sqlcipher_connection():
diff --git a/backend/open_webui/internal/wrappers.py b/backend/open_webui/internal/wrappers.py
index 554a5effdd..80b1aab8ff 100644
--- a/backend/open_webui/internal/wrappers.py
+++ b/backend/open_webui/internal/wrappers.py
@@ -2,7 +2,6 @@ import logging
import os
from contextvars import ContextVar
-from open_webui.env import SRC_LOG_LEVELS
from peewee import *
from peewee import InterfaceError as PeeWeeInterfaceError
from peewee import PostgresqlDatabase
@@ -10,7 +9,6 @@ from playhouse.db_url import connect, parse
from playhouse.shortcuts import ReconnectMixin
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["DB"])
db_state_default = {"closed": None, "conn": None, "ctx": None, "transactions": None}
db_state = ContextVar("db_state", default=db_state_default.copy())
@@ -56,8 +54,6 @@ def register_connection(db_url):
# Parse the database path from SQLCipher URL
# Convert sqlite+sqlcipher:///path/to/db.sqlite to /path/to/db.sqlite
db_path = db_url.replace("sqlite+sqlcipher://", "")
- if db_path.startswith("/"):
- db_path = db_path[1:] # Remove leading slash for relative paths
# Use Peewee's native SqlCipherDatabase with encryption
db = SqlCipherDatabase(db_path, passphrase=database_password)
diff --git a/backend/open_webui/main.py b/backend/open_webui/main.py
index 21a1aee043..63ae72f7bc 100644
--- a/backend/open_webui/main.py
+++ b/backend/open_webui/main.py
@@ -208,6 +208,7 @@ from open_webui.config import (
FIRECRAWL_API_KEY,
WEB_LOADER_ENGINE,
WEB_LOADER_CONCURRENT_REQUESTS,
+ WEB_LOADER_TIMEOUT,
WHISPER_MODEL,
WHISPER_VAD_FILTER,
WHISPER_LANGUAGE,
@@ -226,6 +227,7 @@ from open_webui.config import (
RAG_RERANKING_MODEL,
RAG_EXTERNAL_RERANKER_URL,
RAG_EXTERNAL_RERANKER_API_KEY,
+ RAG_EXTERNAL_RERANKER_TIMEOUT,
RAG_RERANKING_MODEL_AUTO_UPDATE,
RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
RAG_EMBEDDING_ENGINE,
@@ -263,6 +265,7 @@ from open_webui.config import (
MINERU_API_MODE,
MINERU_API_URL,
MINERU_API_KEY,
+ MINERU_API_TIMEOUT,
MINERU_PARAMS,
DATALAB_MARKER_USE_LLM,
EXTERNAL_DOCUMENT_LOADER_URL,
@@ -297,6 +300,7 @@ from open_webui.config import (
SERPAPI_API_KEY,
SERPAPI_ENGINE,
SEARXNG_QUERY_URL,
+ SEARXNG_LANGUAGE,
YACY_QUERY_URL,
YACY_USERNAME,
YACY_PASSWORD,
@@ -435,6 +439,7 @@ from open_webui.config import (
reset_config,
)
from open_webui.env import (
+ ENABLE_CUSTOM_MODEL_FALLBACK,
LICENSE_KEY,
AUDIT_EXCLUDED_PATHS,
AUDIT_LOG_LEVEL,
@@ -447,7 +452,6 @@ from open_webui.env import (
GLOBAL_LOG_LEVEL,
MAX_BODY_LOG_SIZE,
SAFE_MODE,
- SRC_LOG_LEVELS,
VERSION,
DEPLOYMENT_ID,
INSTANCE_ID,
@@ -471,6 +475,7 @@ from open_webui.env import (
EXTERNAL_PWA_MANIFEST_URL,
AIOHTTP_CLIENT_SESSION_SSL,
ENABLE_STAR_SESSIONS_MIDDLEWARE,
+ ENABLE_PUBLIC_ACTIVE_USERS_COUNT,
)
@@ -528,7 +533,6 @@ if SAFE_MODE:
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
class SPAStaticFiles(StaticFiles):
@@ -878,6 +882,7 @@ app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY
app.state.config.MINERU_API_MODE = MINERU_API_MODE
app.state.config.MINERU_API_URL = MINERU_API_URL
app.state.config.MINERU_API_KEY = MINERU_API_KEY
+app.state.config.MINERU_API_TIMEOUT = MINERU_API_TIMEOUT
app.state.config.MINERU_PARAMS = MINERU_PARAMS
app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
@@ -895,6 +900,7 @@ app.state.config.RAG_RERANKING_ENGINE = RAG_RERANKING_ENGINE
app.state.config.RAG_RERANKING_MODEL = RAG_RERANKING_MODEL
app.state.config.RAG_EXTERNAL_RERANKER_URL = RAG_EXTERNAL_RERANKER_URL
app.state.config.RAG_EXTERNAL_RERANKER_API_KEY = RAG_EXTERNAL_RERANKER_API_KEY
+app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT = RAG_EXTERNAL_RERANKER_TIMEOUT
app.state.config.RAG_TEMPLATE = RAG_TEMPLATE
@@ -922,6 +928,7 @@ app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS = WEB_SEARCH_CONCURRENT_REQUESTS
app.state.config.WEB_LOADER_ENGINE = WEB_LOADER_ENGINE
app.state.config.WEB_LOADER_CONCURRENT_REQUESTS = WEB_LOADER_CONCURRENT_REQUESTS
+app.state.config.WEB_LOADER_TIMEOUT = WEB_LOADER_TIMEOUT
app.state.config.WEB_SEARCH_TRUST_ENV = WEB_SEARCH_TRUST_ENV
app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
@@ -934,6 +941,7 @@ app.state.config.ENABLE_ONEDRIVE_INTEGRATION = ENABLE_ONEDRIVE_INTEGRATION
app.state.config.OLLAMA_CLOUD_WEB_SEARCH_API_KEY = OLLAMA_CLOUD_WEB_SEARCH_API_KEY
app.state.config.SEARXNG_QUERY_URL = SEARXNG_QUERY_URL
+app.state.config.SEARXNG_LANGUAGE = SEARXNG_LANGUAGE
app.state.config.YACY_QUERY_URL = YACY_QUERY_URL
app.state.config.YACY_USERNAME = YACY_USERNAME
app.state.config.YACY_PASSWORD = YACY_PASSWORD
@@ -995,6 +1003,7 @@ try:
app.state.config.RAG_RERANKING_MODEL,
app.state.config.RAG_EXTERNAL_RERANKER_URL,
app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
+ app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT,
)
else:
app.state.rf = None
@@ -1031,6 +1040,7 @@ app.state.EMBEDDING_FUNCTION = get_embedding_function(
if app.state.config.RAG_EMBEDDING_ENGINE == "azure_openai"
else None
),
+ enable_async=app.state.config.ENABLE_ASYNC_EMBEDDING,
)
app.state.RERANKING_FUNCTION = get_reranking_function(
@@ -1530,6 +1540,7 @@ async def chat_completion(
metadata = {}
try:
+ model_info = None
if not model_item.get("direct", False):
if model_id not in request.app.state.MODELS:
raise Exception("Model not found")
@@ -1547,7 +1558,6 @@ async def chat_completion(
raise e
else:
model = model_item
- model_info = None
request.state.direct = True
request.state.model = model
@@ -1556,6 +1566,26 @@ async def chat_completion(
model_info.params.model_dump() if model_info and model_info.params else {}
)
+ # Check base model existence for custom models
+ if model_info_params.get("base_model_id"):
+ base_model_id = model_info_params.get("base_model_id")
+ if base_model_id not in request.app.state.MODELS:
+ if ENABLE_CUSTOM_MODEL_FALLBACK:
+ default_models = (
+ request.app.state.config.DEFAULT_MODELS or ""
+ ).split(",")
+
+ fallback_model_id = (
+ default_models[0].strip() if default_models[0] else None
+ )
+
+ if fallback_model_id:
+ request.base_model_id = fallback_model_id
+ else:
+ raise Exception("Model not found")
+ else:
+ raise Exception("Model not found")
+
# Chat Params
stream_delta_chunk_size = form_data.get("params", {}).get(
"stream_delta_chunk_size"
@@ -1576,6 +1606,7 @@ async def chat_completion(
"user_id": user.id,
"chat_id": form_data.pop("chat_id", None),
"message_id": form_data.pop("id", None),
+ "parent_message": form_data.pop("parent_message", None),
"parent_message_id": form_data.pop("parent_id", None),
"session_id": form_data.pop("session_id", None),
"filter_ids": form_data.pop("filter_ids", []),
@@ -1600,15 +1631,38 @@ async def chat_completion(
},
}
- if metadata.get("chat_id") and (user and user.role != "admin"):
- if not metadata["chat_id"].startswith("local:"):
+ if metadata.get("chat_id") and user:
+ if not metadata["chat_id"].startswith(
+ "local:"
+ ): # temporary chats are not stored
+
+ # Verify chat ownership
chat = Chats.get_chat_by_id_and_user_id(metadata["chat_id"], user.id)
- if chat is None:
+ if chat is None and user.role != "admin": # admins can access any chat
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=ERROR_MESSAGES.DEFAULT(),
)
+ # Insert chat files from parent message if any
+ parent_message = metadata.get("parent_message", {})
+ parent_message_files = parent_message.get("files", [])
+ if parent_message_files:
+ try:
+ Chats.insert_chat_files(
+ metadata["chat_id"],
+ parent_message.get("id"),
+ [
+ file_item.get("id")
+ for file_item in parent_message_files
+ if file_item.get("type") == "file"
+ ],
+ user.id,
+ )
+ except Exception as e:
+ log.debug(f"Error inserting chat files: {e}")
+ pass
+
request.state.metadata = metadata
form_data["metadata"] = metadata
@@ -1843,6 +1897,7 @@ async def get_app_config(request: Request):
"enable_login_form": app.state.config.ENABLE_LOGIN_FORM,
"enable_websocket": ENABLE_WEBSOCKET_SUPPORT,
"enable_version_update_check": ENABLE_VERSION_UPDATE_CHECK,
+ "enable_public_active_users_count": ENABLE_PUBLIC_ACTIVE_USERS_COUNT,
**(
{
"enable_direct_connections": app.state.config.ENABLE_DIRECT_CONNECTIONS,
@@ -2019,10 +2074,19 @@ async def get_current_usage(user=Depends(get_verified_user)):
This is an experimental endpoint and subject to change.
"""
try:
+ # If public visibility is disabled, only allow admins to access this endpoint
+ if not ENABLE_PUBLIC_ACTIVE_USERS_COUNT and user.role != "admin":
+ raise HTTPException(
+ status_code=status.HTTP_403_FORBIDDEN,
+ detail="Access denied. Only administrators can view usage statistics.",
+ )
+
return {
"model_ids": get_models_in_use(),
"user_count": Users.get_active_user_count(),
}
+ except HTTPException:
+ raise
except Exception as e:
log.error(f"Error getting usage statistics: {e}")
raise HTTPException(status_code=500, detail="Internal Server Error")
diff --git a/backend/open_webui/migrations/versions/6283dc0e4d8d_add_channel_file_table.py b/backend/open_webui/migrations/versions/6283dc0e4d8d_add_channel_file_table.py
new file mode 100644
index 0000000000..59fe57a421
--- /dev/null
+++ b/backend/open_webui/migrations/versions/6283dc0e4d8d_add_channel_file_table.py
@@ -0,0 +1,54 @@
+"""Add channel file table
+
+Revision ID: 6283dc0e4d8d
+Revises: 3e0e00844bb0
+Create Date: 2025-12-10 15:11:39.424601
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import open_webui.internal.db
+
+
+# revision identifiers, used by Alembic.
+revision: str = "6283dc0e4d8d"
+down_revision: Union[str, None] = "3e0e00844bb0"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+ op.create_table(
+ "channel_file",
+ sa.Column("id", sa.Text(), primary_key=True),
+ sa.Column("user_id", sa.Text(), nullable=False),
+ sa.Column(
+ "channel_id",
+ sa.Text(),
+ sa.ForeignKey("channel.id", ondelete="CASCADE"),
+ nullable=False,
+ ),
+ sa.Column(
+ "file_id",
+ sa.Text(),
+ sa.ForeignKey("file.id", ondelete="CASCADE"),
+ nullable=False,
+ ),
+ sa.Column("created_at", sa.BigInteger(), nullable=False),
+ sa.Column("updated_at", sa.BigInteger(), nullable=False),
+ # indexes
+ sa.Index("ix_channel_file_channel_id", "channel_id"),
+ sa.Index("ix_channel_file_file_id", "file_id"),
+ sa.Index("ix_channel_file_user_id", "user_id"),
+ # unique constraints
+ sa.UniqueConstraint(
+ "channel_id", "file_id", name="uq_channel_file_channel_file"
+ ), # prevent duplicate entries
+ )
+
+
+def downgrade() -> None:
+ op.drop_table("channel_file")
diff --git a/backend/open_webui/migrations/versions/81cc2ce44d79_update_channel_file_and_knowledge_table.py b/backend/open_webui/migrations/versions/81cc2ce44d79_update_channel_file_and_knowledge_table.py
new file mode 100644
index 0000000000..181b280666
--- /dev/null
+++ b/backend/open_webui/migrations/versions/81cc2ce44d79_update_channel_file_and_knowledge_table.py
@@ -0,0 +1,49 @@
+"""Update channel file and knowledge table
+
+Revision ID: 81cc2ce44d79
+Revises: 6283dc0e4d8d
+Create Date: 2025-12-10 16:07:58.001282
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import open_webui.internal.db
+
+
+# revision identifiers, used by Alembic.
+revision: str = "81cc2ce44d79"
+down_revision: Union[str, None] = "6283dc0e4d8d"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+ # Add message_id column to channel_file table
+ with op.batch_alter_table("channel_file", schema=None) as batch_op:
+ batch_op.add_column(
+ sa.Column(
+ "message_id",
+ sa.Text(),
+ sa.ForeignKey(
+ "message.id", ondelete="CASCADE", name="fk_channel_file_message_id"
+ ),
+ nullable=True,
+ )
+ )
+
+ # Add data column to knowledge table
+ with op.batch_alter_table("knowledge", schema=None) as batch_op:
+ batch_op.add_column(sa.Column("data", sa.JSON(), nullable=True))
+
+
+def downgrade() -> None:
+ # Remove message_id column from channel_file table
+ with op.batch_alter_table("channel_file", schema=None) as batch_op:
+ batch_op.drop_column("message_id")
+
+ # Remove data column from knowledge table
+ with op.batch_alter_table("knowledge", schema=None) as batch_op:
+ batch_op.drop_column("data")
diff --git a/backend/open_webui/migrations/versions/c440947495f3_add_chat_file_table.py b/backend/open_webui/migrations/versions/c440947495f3_add_chat_file_table.py
new file mode 100644
index 0000000000..20f4a6d7b6
--- /dev/null
+++ b/backend/open_webui/migrations/versions/c440947495f3_add_chat_file_table.py
@@ -0,0 +1,57 @@
+"""Add chat_file table
+
+Revision ID: c440947495f3
+Revises: 81cc2ce44d79
+Create Date: 2025-12-21 20:27:41.694897
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "c440947495f3"
+down_revision: Union[str, None] = "81cc2ce44d79"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+ op.create_table(
+ "chat_file",
+ sa.Column("id", sa.Text(), primary_key=True),
+ sa.Column("user_id", sa.Text(), nullable=False),
+ sa.Column(
+ "chat_id",
+ sa.Text(),
+ sa.ForeignKey("chat.id", ondelete="CASCADE"),
+ nullable=False,
+ ),
+ sa.Column(
+ "file_id",
+ sa.Text(),
+ sa.ForeignKey("file.id", ondelete="CASCADE"),
+ nullable=False,
+ ),
+ sa.Column("message_id", sa.Text(), nullable=True),
+ sa.Column("created_at", sa.BigInteger(), nullable=False),
+ sa.Column("updated_at", sa.BigInteger(), nullable=False),
+ # indexes
+ sa.Index("ix_chat_file_chat_id", "chat_id"),
+ sa.Index("ix_chat_file_file_id", "file_id"),
+ sa.Index("ix_chat_file_message_id", "message_id"),
+ sa.Index("ix_chat_file_user_id", "user_id"),
+ # unique constraints
+ sa.UniqueConstraint(
+ "chat_id", "file_id", name="uq_chat_file_chat_file"
+ ), # prevent duplicate entries
+ )
+ pass
+
+
+def downgrade() -> None:
+ op.drop_table("chat_file")
+ pass
diff --git a/backend/open_webui/models/auths.py b/backend/open_webui/models/auths.py
index 8b03580e6c..cb6c057c88 100644
--- a/backend/open_webui/models/auths.py
+++ b/backend/open_webui/models/auths.py
@@ -4,12 +4,10 @@ from typing import Optional
from open_webui.internal.db import Base, get_db
from open_webui.models.users import UserModel, UserProfileImageResponse, Users
-from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel
from sqlalchemy import Boolean, Column, String, Text
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# DB MODEL
diff --git a/backend/open_webui/models/channels.py b/backend/open_webui/models/channels.py
index 754f6e3dfa..362222a284 100644
--- a/backend/open_webui/models/channels.py
+++ b/backend/open_webui/models/channels.py
@@ -10,7 +10,18 @@ from pydantic import BaseModel, ConfigDict
from sqlalchemy.dialects.postgresql import JSONB
-from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON, case, cast
+from sqlalchemy import (
+ BigInteger,
+ Boolean,
+ Column,
+ ForeignKey,
+ String,
+ Text,
+ JSON,
+ UniqueConstraint,
+ case,
+ cast,
+)
from sqlalchemy import or_, func, select, and_, text
from sqlalchemy.sql import exists
@@ -137,6 +148,41 @@ class ChannelMemberModel(BaseModel):
updated_at: Optional[int] = None # timestamp in epoch (time_ns)
+class ChannelFile(Base):
+ __tablename__ = "channel_file"
+
+ id = Column(Text, unique=True, primary_key=True)
+ user_id = Column(Text, nullable=False)
+
+ channel_id = Column(
+ Text, ForeignKey("channel.id", ondelete="CASCADE"), nullable=False
+ )
+ message_id = Column(
+ Text, ForeignKey("message.id", ondelete="CASCADE"), nullable=True
+ )
+ file_id = Column(Text, ForeignKey("file.id", ondelete="CASCADE"), nullable=False)
+
+ created_at = Column(BigInteger, nullable=False)
+ updated_at = Column(BigInteger, nullable=False)
+
+ __table_args__ = (
+ UniqueConstraint("channel_id", "file_id", name="uq_channel_file_channel_file"),
+ )
+
+
+class ChannelFileModel(BaseModel):
+ model_config = ConfigDict(from_attributes=True)
+
+ id: str
+
+ channel_id: str
+ file_id: str
+ user_id: str
+
+ created_at: int # timestamp in epoch (time_ns)
+ updated_at: int # timestamp in epoch (time_ns)
+
+
class ChannelWebhook(Base):
__tablename__ = "channel_webhook"
@@ -642,6 +688,135 @@ class ChannelTable:
channel = db.query(Channel).filter(Channel.id == id).first()
return ChannelModel.model_validate(channel) if channel else None
+ def get_channels_by_file_id(self, file_id: str) -> list[ChannelModel]:
+ with get_db() as db:
+ channel_files = (
+ db.query(ChannelFile).filter(ChannelFile.file_id == file_id).all()
+ )
+ channel_ids = [cf.channel_id for cf in channel_files]
+ channels = db.query(Channel).filter(Channel.id.in_(channel_ids)).all()
+ return [ChannelModel.model_validate(channel) for channel in channels]
+
+ def get_channels_by_file_id_and_user_id(
+ self, file_id: str, user_id: str
+ ) -> list[ChannelModel]:
+ with get_db() as db:
+ # 1. Determine which channels have this file
+ channel_file_rows = (
+ db.query(ChannelFile).filter(ChannelFile.file_id == file_id).all()
+ )
+ channel_ids = [row.channel_id for row in channel_file_rows]
+
+ if not channel_ids:
+ return []
+
+ # 2. Load all channel rows that still exist
+ channels = (
+ db.query(Channel)
+ .filter(
+ Channel.id.in_(channel_ids),
+ Channel.deleted_at.is_(None),
+ Channel.archived_at.is_(None),
+ )
+ .all()
+ )
+ if not channels:
+ return []
+
+ # Preload user's group membership
+ user_group_ids = [g.id for g in Groups.get_groups_by_member_id(user_id)]
+
+ allowed_channels = []
+
+ for channel in channels:
+ # --- Case A: group or dm => user must be an active member ---
+ if channel.type in ["group", "dm"]:
+ membership = (
+ db.query(ChannelMember)
+ .filter(
+ ChannelMember.channel_id == channel.id,
+ ChannelMember.user_id == user_id,
+ ChannelMember.is_active.is_(True),
+ )
+ .first()
+ )
+ if membership:
+ allowed_channels.append(ChannelModel.model_validate(channel))
+ continue
+
+ # --- Case B: standard channel => rely on ACL permissions ---
+ query = db.query(Channel).filter(Channel.id == channel.id)
+
+ query = self._has_permission(
+ db,
+ query,
+ {"user_id": user_id, "group_ids": user_group_ids},
+ permission="read",
+ )
+
+ allowed = query.first()
+ if allowed:
+ allowed_channels.append(ChannelModel.model_validate(allowed))
+
+ return allowed_channels
+
+ def get_channel_by_id_and_user_id(
+ self, id: str, user_id: str
+ ) -> Optional[ChannelModel]:
+ with get_db() as db:
+ # Fetch the channel
+ channel: Channel = (
+ db.query(Channel)
+ .filter(
+ Channel.id == id,
+ Channel.deleted_at.is_(None),
+ Channel.archived_at.is_(None),
+ )
+ .first()
+ )
+
+ if not channel:
+ return None
+
+ # If the channel is a group or dm, read access requires membership (active)
+ if channel.type in ["group", "dm"]:
+ membership = (
+ db.query(ChannelMember)
+ .filter(
+ ChannelMember.channel_id == id,
+ ChannelMember.user_id == user_id,
+ ChannelMember.is_active.is_(True),
+ )
+ .first()
+ )
+ if membership:
+ return ChannelModel.model_validate(channel)
+ else:
+ return None
+
+ # For channels that are NOT group/dm, fall back to ACL-based read access
+ query = db.query(Channel).filter(Channel.id == id)
+
+ # Determine user groups
+ user_group_ids = [
+ group.id for group in Groups.get_groups_by_member_id(user_id)
+ ]
+
+ # Apply ACL rules
+ query = self._has_permission(
+ db,
+ query,
+ {"user_id": user_id, "group_ids": user_group_ids},
+ permission="read",
+ )
+
+ channel_allowed = query.first()
+ return (
+ ChannelModel.model_validate(channel_allowed)
+ if channel_allowed
+ else None
+ )
+
def update_channel_by_id(
self, id: str, form_data: ChannelForm
) -> Optional[ChannelModel]:
@@ -663,6 +838,65 @@ class ChannelTable:
db.commit()
return ChannelModel.model_validate(channel) if channel else None
+ def add_file_to_channel_by_id(
+ self, channel_id: str, file_id: str, user_id: str
+ ) -> Optional[ChannelFileModel]:
+ with get_db() as db:
+ channel_file = ChannelFileModel(
+ **{
+ "id": str(uuid.uuid4()),
+ "channel_id": channel_id,
+ "file_id": file_id,
+ "user_id": user_id,
+ "created_at": int(time.time()),
+ "updated_at": int(time.time()),
+ }
+ )
+
+ try:
+ result = ChannelFile(**channel_file.model_dump())
+ db.add(result)
+ db.commit()
+ db.refresh(result)
+ if result:
+ return ChannelFileModel.model_validate(result)
+ else:
+ return None
+ except Exception:
+ return None
+
+ def set_file_message_id_in_channel_by_id(
+ self, channel_id: str, file_id: str, message_id: str
+ ) -> bool:
+ try:
+ with get_db() as db:
+ channel_file = (
+ db.query(ChannelFile)
+ .filter_by(channel_id=channel_id, file_id=file_id)
+ .first()
+ )
+ if not channel_file:
+ return False
+
+ channel_file.message_id = message_id
+ channel_file.updated_at = int(time.time())
+
+ db.commit()
+ return True
+ except Exception:
+ return False
+
+ def remove_file_from_channel_by_id(self, channel_id: str, file_id: str) -> bool:
+ try:
+ with get_db() as db:
+ db.query(ChannelFile).filter_by(
+ channel_id=channel_id, file_id=file_id
+ ).delete()
+ db.commit()
+ return True
+ except Exception:
+ return False
+
def delete_channel_by_id(self, id: str):
with get_db() as db:
db.query(Channel).filter(Channel.id == id).delete()
diff --git a/backend/open_webui/models/chats.py b/backend/open_webui/models/chats.py
index 187a4522c9..d821985a4e 100644
--- a/backend/open_webui/models/chats.py
+++ b/backend/open_webui/models/chats.py
@@ -7,10 +7,20 @@ 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.models.folders import Folders
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.utils.misc import sanitize_data_for_db, sanitize_text_for_db
from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON, Index
+from sqlalchemy import (
+ BigInteger,
+ Boolean,
+ Column,
+ ForeignKey,
+ String,
+ Text,
+ JSON,
+ Index,
+ UniqueConstraint,
+)
from sqlalchemy import or_, func, select, and_, text
from sqlalchemy.sql import exists
from sqlalchemy.sql.expression import bindparam
@@ -20,7 +30,6 @@ from sqlalchemy.sql.expression import bindparam
####################
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
class Chat(Base):
@@ -75,6 +84,38 @@ class ChatModel(BaseModel):
folder_id: Optional[str] = None
+class ChatFile(Base):
+ __tablename__ = "chat_file"
+
+ id = Column(Text, unique=True, primary_key=True)
+ user_id = Column(Text, nullable=False)
+
+ chat_id = Column(Text, ForeignKey("chat.id", ondelete="CASCADE"), nullable=False)
+ message_id = Column(Text, nullable=True)
+ file_id = Column(Text, ForeignKey("file.id", ondelete="CASCADE"), nullable=False)
+
+ created_at = Column(BigInteger, nullable=False)
+ updated_at = Column(BigInteger, nullable=False)
+
+ __table_args__ = (
+ UniqueConstraint("chat_id", "file_id", name="uq_chat_file_chat_file"),
+ )
+
+
+class ChatFileModel(BaseModel):
+ id: str
+ user_id: str
+
+ chat_id: str
+ message_id: Optional[str] = None
+ file_id: str
+
+ created_at: int
+ updated_at: int
+
+ model_config = ConfigDict(from_attributes=True)
+
+
####################
# Forms
####################
@@ -126,20 +167,53 @@ class ChatTitleIdResponse(BaseModel):
created_at: int
+class ChatListResponse(BaseModel):
+ items: list[ChatModel]
+ total: int
+
+
+class ChatUsageStatsResponse(BaseModel):
+ id: str # chat id
+
+ models: dict = {} # models used in the chat with their usage counts
+ message_count: int # number of messages in the chat
+
+ history_models: dict = {} # models used in the chat history with their usage counts
+ history_message_count: int # number of messages in the chat history
+ history_user_message_count: int # number of user messages in the chat history
+ history_assistant_message_count: (
+ int # number of assistant messages in the chat history
+ )
+
+ average_response_time: (
+ float # average response time of assistant messages in seconds
+ )
+ average_user_message_content_length: (
+ float # average length of user message contents
+ )
+ average_assistant_message_content_length: (
+ float # average length of assistant message contents
+ )
+
+ tags: list[str] = [] # tags associated with the chat
+
+ last_message_at: int # timestamp of the last message
+ updated_at: int
+ created_at: int
+
+ model_config = ConfigDict(extra="allow")
+
+
+class ChatUsageStatsListResponse(BaseModel):
+ items: list[ChatUsageStatsResponse]
+ total: int
+ model_config = ConfigDict(extra="allow")
+
+
class ChatTable:
def _clean_null_bytes(self, obj):
- """
- Recursively remove actual null bytes (\x00) and unicode escape \\u0000
- from strings inside dict/list structures.
- Safe for JSON objects.
- """
- if isinstance(obj, str):
- return obj.replace("\x00", "").replace("\u0000", "")
- elif isinstance(obj, dict):
- return {k: self._clean_null_bytes(v) for k, v in obj.items()}
- elif isinstance(obj, list):
- return [self._clean_null_bytes(v) for v in obj]
- return obj
+ """Recursively remove null bytes from strings in dict/list structures."""
+ return sanitize_data_for_db(obj)
def _sanitize_chat_row(self, chat_item):
"""
@@ -310,7 +384,7 @@ class ChatTable:
# Sanitize message content for null characters before upserting
if isinstance(message.get("content"), str):
- message["content"] = message["content"].replace("\x00", "")
+ message["content"] = sanitize_text_for_db(message["content"])
chat = chat.chat
history = chat.get("history", {})
@@ -675,14 +749,31 @@ class ChatTable:
)
return [ChatModel.model_validate(chat) for chat in all_chats]
- def get_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
+ def get_chats_by_user_id(
+ self, user_id: str, skip: Optional[int] = None, limit: Optional[int] = None
+ ) -> ChatListResponse:
with get_db() as db:
- all_chats = (
+ query = (
db.query(Chat)
.filter_by(user_id=user_id)
.order_by(Chat.updated_at.desc())
)
- return [ChatModel.model_validate(chat) for chat in all_chats]
+
+ total = query.count()
+
+ if skip is not None:
+ query = query.offset(skip)
+ if limit is not None:
+ query = query.limit(limit)
+
+ all_chats = query.all()
+
+ return ChatListResponse(
+ **{
+ "items": [ChatModel.model_validate(chat) for chat in all_chats],
+ "total": total,
+ }
+ )
def get_pinned_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
with get_db() as db:
@@ -713,7 +804,7 @@ class ChatTable:
"""
Filters chats based on a search query using Python, allowing pagination using skip and limit.
"""
- search_text = search_text.replace("\u0000", "").lower().strip()
+ search_text = sanitize_text_for_db(search_text).lower().strip()
if not search_text:
return self.get_chat_list_by_user_id(
@@ -1170,5 +1261,93 @@ class ChatTable:
except Exception:
return False
+ def insert_chat_files(
+ self, chat_id: str, message_id: str, file_ids: list[str], user_id: str
+ ) -> Optional[list[ChatFileModel]]:
+ if not file_ids:
+ return None
+
+ chat_message_file_ids = [
+ item.id
+ for item in self.get_chat_files_by_chat_id_and_message_id(
+ chat_id, message_id
+ )
+ ]
+ # Remove duplicates and existing file_ids
+ file_ids = list(
+ set(
+ [
+ file_id
+ for file_id in file_ids
+ if file_id and file_id not in chat_message_file_ids
+ ]
+ )
+ )
+ if not file_ids:
+ return None
+
+ try:
+ with get_db() as db:
+ now = int(time.time())
+
+ chat_files = [
+ ChatFileModel(
+ id=str(uuid.uuid4()),
+ user_id=user_id,
+ chat_id=chat_id,
+ message_id=message_id,
+ file_id=file_id,
+ created_at=now,
+ updated_at=now,
+ )
+ for file_id in file_ids
+ ]
+
+ results = [
+ ChatFile(**chat_file.model_dump()) for chat_file in chat_files
+ ]
+
+ db.add_all(results)
+ db.commit()
+
+ return chat_files
+ except Exception:
+ return None
+
+ def get_chat_files_by_chat_id_and_message_id(
+ self, chat_id: str, message_id: str
+ ) -> list[ChatFileModel]:
+ with get_db() as db:
+ all_chat_files = (
+ db.query(ChatFile)
+ .filter_by(chat_id=chat_id, message_id=message_id)
+ .order_by(ChatFile.created_at.asc())
+ .all()
+ )
+ return [
+ ChatFileModel.model_validate(chat_file) for chat_file in all_chat_files
+ ]
+
+ def delete_chat_file(self, chat_id: str, file_id: str) -> bool:
+ try:
+ with get_db() as db:
+ db.query(ChatFile).filter_by(chat_id=chat_id, file_id=file_id).delete()
+ db.commit()
+ return True
+ except Exception:
+ return False
+
+ def get_shared_chats_by_file_id(self, file_id: str) -> list[ChatModel]:
+ with get_db() as db:
+ # Join Chat and ChatFile tables to get shared chats associated with the file_id
+ all_chats = (
+ db.query(Chat)
+ .join(ChatFile, Chat.id == ChatFile.chat_id)
+ .filter(ChatFile.file_id == file_id, Chat.share_id.isnot(None))
+ .all()
+ )
+
+ return [ChatModel.model_validate(chat) for chat in all_chats]
+
Chats = ChatTable()
diff --git a/backend/open_webui/models/feedbacks.py b/backend/open_webui/models/feedbacks.py
index 5a91804b56..39e22ff2d9 100644
--- a/backend/open_webui/models/feedbacks.py
+++ b/backend/open_webui/models/feedbacks.py
@@ -6,12 +6,10 @@ from typing import Optional
from open_webui.internal.db import Base, get_db
from open_webui.models.users import User
-from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, Text, JSON, Boolean
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
@@ -62,6 +60,13 @@ class FeedbackResponse(BaseModel):
updated_at: int
+class FeedbackIdResponse(BaseModel):
+ id: str
+ user_id: str
+ created_at: int
+ updated_at: int
+
+
class RatingData(BaseModel):
rating: Optional[str | int] = None
model_id: Optional[str] = None
diff --git a/backend/open_webui/models/files.py b/backend/open_webui/models/files.py
index 1ed743df87..9d4e8fb054 100644
--- a/backend/open_webui/models/files.py
+++ b/backend/open_webui/models/files.py
@@ -3,12 +3,10 @@ import time
from typing import Optional
from open_webui.internal.db import Base, JSONField, get_db
-from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, String, Text, JSON
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# Files DB Schema
@@ -83,7 +81,7 @@ class FileModelResponse(BaseModel):
class FileMetadataResponse(BaseModel):
id: str
hash: Optional[str] = None
- meta: dict
+ meta: Optional[dict] = None
created_at: int # timestamp in epoch
updated_at: int # timestamp in epoch
@@ -104,6 +102,11 @@ class FileUpdateForm(BaseModel):
meta: Optional[dict] = None
+class FileListResponse(BaseModel):
+ items: list[FileModel]
+ total: int
+
+
class FilesTable:
def insert_new_file(self, user_id: str, form_data: FileForm) -> Optional[FileModel]:
with get_db() as db:
@@ -238,6 +241,7 @@ class FilesTable:
try:
file = db.query(File).filter_by(id=id).first()
file.hash = hash
+ file.updated_at = int(time.time())
db.commit()
return FileModel.model_validate(file)
@@ -249,6 +253,7 @@ class FilesTable:
try:
file = db.query(File).filter_by(id=id).first()
file.data = {**(file.data if file.data else {}), **data}
+ file.updated_at = int(time.time())
db.commit()
return FileModel.model_validate(file)
except Exception as e:
@@ -260,6 +265,7 @@ class FilesTable:
try:
file = db.query(File).filter_by(id=id).first()
file.meta = {**(file.meta if file.meta else {}), **meta}
+ file.updated_at = int(time.time())
db.commit()
return FileModel.model_validate(file)
except Exception:
diff --git a/backend/open_webui/models/folders.py b/backend/open_webui/models/folders.py
index 6e1735ecea..0043dd3644 100644
--- a/backend/open_webui/models/folders.py
+++ b/backend/open_webui/models/folders.py
@@ -9,11 +9,9 @@ from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, Text, JSON, Boolean, func
from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
diff --git a/backend/open_webui/models/functions.py b/backend/open_webui/models/functions.py
index 91736f949a..19ad985d0c 100644
--- a/backend/open_webui/models/functions.py
+++ b/backend/open_webui/models/functions.py
@@ -4,12 +4,10 @@ from typing import Optional
from open_webui.internal.db import Base, JSONField, get_db
from open_webui.models.users import Users, UserModel
-from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Boolean, Column, String, Text, Index
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# Functions DB Schema
diff --git a/backend/open_webui/models/groups.py b/backend/open_webui/models/groups.py
index a7900e2c78..da94287111 100644
--- a/backend/open_webui/models/groups.py
+++ b/backend/open_webui/models/groups.py
@@ -5,7 +5,6 @@ from typing import Optional
import uuid
from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.models.files import FileMetadataResponse
@@ -26,7 +25,6 @@ from sqlalchemy import (
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# UserGroup DB Schema
diff --git a/backend/open_webui/models/knowledge.py b/backend/open_webui/models/knowledge.py
index 2c72401181..d8af004338 100644
--- a/backend/open_webui/models/knowledge.py
+++ b/backend/open_webui/models/knowledge.py
@@ -5,11 +5,15 @@ from typing import Optional
import uuid
from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
-from open_webui.models.files import File, FileModel, FileMetadataResponse
+from open_webui.models.files import (
+ File,
+ FileModel,
+ FileMetadataResponse,
+ FileModelResponse,
+)
from open_webui.models.groups import Groups
-from open_webui.models.users import Users, UserResponse
+from open_webui.models.users import User, UserModel, Users, UserResponse
from pydantic import BaseModel, ConfigDict
@@ -21,12 +25,14 @@ from sqlalchemy import (
Text,
JSON,
UniqueConstraint,
+ or_,
)
from open_webui.utils.access_control import has_access
+from open_webui.utils.db.access_control import has_permission
+
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# Knowledge DB Schema
@@ -126,7 +132,7 @@ class KnowledgeResponse(KnowledgeModel):
class KnowledgeUserResponse(KnowledgeUserModel):
- files: Optional[list[FileMetadataResponse | dict]] = None
+ pass
class KnowledgeForm(BaseModel):
@@ -135,6 +141,20 @@ class KnowledgeForm(BaseModel):
access_control: Optional[dict] = None
+class FileUserResponse(FileModelResponse):
+ user: Optional[UserResponse] = None
+
+
+class KnowledgeListResponse(BaseModel):
+ items: list[KnowledgeUserModel]
+ total: int
+
+
+class KnowledgeFileListResponse(BaseModel):
+ items: list[FileUserResponse]
+ total: int
+
+
class KnowledgeTable:
def insert_new_knowledge(
self, user_id: str, form_data: KnowledgeForm
@@ -162,12 +182,13 @@ class KnowledgeTable:
except Exception:
return None
- def get_knowledge_bases(self) -> list[KnowledgeUserModel]:
+ def get_knowledge_bases(
+ self, skip: int = 0, limit: int = 30
+ ) -> list[KnowledgeUserModel]:
with get_db() as db:
all_knowledge = (
db.query(Knowledge).order_by(Knowledge.updated_at.desc()).all()
)
-
user_ids = list(set(knowledge.user_id for knowledge in all_knowledge))
users = Users.get_users_by_user_ids(user_ids) if user_ids else []
@@ -186,6 +207,126 @@ class KnowledgeTable:
)
return knowledge_bases
+ def search_knowledge_bases(
+ self, user_id: str, filter: dict, skip: int = 0, limit: int = 30
+ ) -> KnowledgeListResponse:
+ try:
+ with get_db() as db:
+ query = db.query(Knowledge, User).outerjoin(
+ User, User.id == Knowledge.user_id
+ )
+
+ if filter:
+ query_key = filter.get("query")
+ if query_key:
+ query = query.filter(
+ or_(
+ Knowledge.name.ilike(f"%{query_key}%"),
+ Knowledge.description.ilike(f"%{query_key}%"),
+ )
+ )
+
+ view_option = filter.get("view_option")
+ if view_option == "created":
+ query = query.filter(Knowledge.user_id == user_id)
+ elif view_option == "shared":
+ query = query.filter(Knowledge.user_id != user_id)
+
+ query = has_permission(db, Knowledge, query, filter)
+
+ query = query.order_by(Knowledge.updated_at.desc())
+
+ total = query.count()
+ if skip:
+ query = query.offset(skip)
+ if limit:
+ query = query.limit(limit)
+
+ items = query.all()
+
+ knowledge_bases = []
+ for knowledge_base, user in items:
+ knowledge_bases.append(
+ KnowledgeUserModel.model_validate(
+ {
+ **KnowledgeModel.model_validate(
+ knowledge_base
+ ).model_dump(),
+ "user": (
+ UserModel.model_validate(user).model_dump()
+ if user
+ else None
+ ),
+ }
+ )
+ )
+
+ return KnowledgeListResponse(items=knowledge_bases, total=total)
+ except Exception as e:
+ print(e)
+ return KnowledgeListResponse(items=[], total=0)
+
+ def search_knowledge_files(
+ self, filter: dict, skip: int = 0, limit: int = 30
+ ) -> KnowledgeFileListResponse:
+ """
+ Scalable version: search files across all knowledge bases the user has
+ READ access to, without loading all KBs or using large IN() lists.
+ """
+ try:
+ with get_db() as db:
+ # Base query: join Knowledge → KnowledgeFile → File
+ query = (
+ db.query(File, User)
+ .join(KnowledgeFile, File.id == KnowledgeFile.file_id)
+ .join(Knowledge, KnowledgeFile.knowledge_id == Knowledge.id)
+ .outerjoin(User, User.id == KnowledgeFile.user_id)
+ )
+
+ # Apply access-control directly to the joined query
+ # This makes the database handle filtering, even with 10k+ KBs
+ query = has_permission(db, Knowledge, query, filter)
+
+ # Apply filename search
+ if filter:
+ q = filter.get("query")
+ if q:
+ query = query.filter(File.filename.ilike(f"%{q}%"))
+
+ # Order by file changes
+ query = query.order_by(File.updated_at.desc())
+
+ # Count before pagination
+ total = query.count()
+
+ if skip:
+ query = query.offset(skip)
+ if limit:
+ query = query.limit(limit)
+
+ rows = query.all()
+
+ items = []
+ for file, user in rows:
+ items.append(
+ FileUserResponse(
+ **FileModel.model_validate(file).model_dump(),
+ user=(
+ UserResponse(
+ **UserModel.model_validate(user).model_dump()
+ )
+ if user
+ else None
+ ),
+ )
+ )
+
+ return KnowledgeFileListResponse(items=items, total=total)
+
+ except Exception as e:
+ print("search_knowledge_files error:", e)
+ return KnowledgeFileListResponse(items=[], total=0)
+
def check_access_by_user_id(self, id, user_id, permission="write") -> bool:
knowledge = self.get_knowledge_by_id(id)
if not knowledge:
@@ -217,6 +358,21 @@ class KnowledgeTable:
except Exception:
return None
+ def get_knowledge_by_id_and_user_id(
+ self, id: str, user_id: str
+ ) -> Optional[KnowledgeModel]:
+ knowledge = self.get_knowledge_by_id(id)
+ if not knowledge:
+ return None
+
+ if knowledge.user_id == user_id:
+ return knowledge
+
+ user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user_id)}
+ if has_access(user_id, "write", knowledge.access_control, user_group_ids):
+ return knowledge
+ return None
+
def get_knowledges_by_file_id(self, file_id: str) -> list[KnowledgeModel]:
try:
with get_db() as db:
@@ -232,6 +388,88 @@ class KnowledgeTable:
except Exception:
return []
+ def search_files_by_id(
+ self,
+ knowledge_id: str,
+ user_id: str,
+ filter: dict,
+ skip: int = 0,
+ limit: int = 30,
+ ) -> KnowledgeFileListResponse:
+ try:
+ with get_db() as db:
+ query = (
+ db.query(File, User)
+ .join(KnowledgeFile, File.id == KnowledgeFile.file_id)
+ .outerjoin(User, User.id == KnowledgeFile.user_id)
+ .filter(KnowledgeFile.knowledge_id == knowledge_id)
+ )
+
+ if filter:
+ query_key = filter.get("query")
+ if query_key:
+ query = query.filter(or_(File.filename.ilike(f"%{query_key}%")))
+
+ view_option = filter.get("view_option")
+ if view_option == "created":
+ query = query.filter(KnowledgeFile.user_id == user_id)
+ elif view_option == "shared":
+ query = query.filter(KnowledgeFile.user_id != user_id)
+
+ order_by = filter.get("order_by")
+ direction = filter.get("direction")
+
+ if order_by == "name":
+ if direction == "asc":
+ query = query.order_by(File.filename.asc())
+ else:
+ query = query.order_by(File.filename.desc())
+ elif order_by == "created_at":
+ if direction == "asc":
+ query = query.order_by(File.created_at.asc())
+ else:
+ query = query.order_by(File.created_at.desc())
+ elif order_by == "updated_at":
+ if direction == "asc":
+ query = query.order_by(File.updated_at.asc())
+ else:
+ query = query.order_by(File.updated_at.desc())
+ else:
+ query = query.order_by(File.updated_at.desc())
+
+ else:
+ query = query.order_by(File.updated_at.desc())
+
+ # Count BEFORE pagination
+ total = query.count()
+
+ if skip:
+ query = query.offset(skip)
+ if limit:
+ query = query.limit(limit)
+
+ items = query.all()
+
+ files = []
+ for file, user in items:
+ files.append(
+ FileUserResponse(
+ **FileModel.model_validate(file).model_dump(),
+ user=(
+ UserResponse(
+ **UserModel.model_validate(user).model_dump()
+ )
+ if user
+ else None
+ ),
+ )
+ )
+
+ return KnowledgeFileListResponse(items=files, total=total)
+ except Exception as e:
+ print(e)
+ return KnowledgeFileListResponse(items=[], total=0)
+
def get_files_by_id(self, knowledge_id: str) -> list[FileModel]:
try:
with get_db() as db:
diff --git a/backend/open_webui/models/messages.py b/backend/open_webui/models/messages.py
index 98be21463d..5b068b6449 100644
--- a/backend/open_webui/models/messages.py
+++ b/backend/open_webui/models/messages.py
@@ -9,7 +9,7 @@ from open_webui.models.users import Users, User, UserNameResponse
from open_webui.models.channels import Channels, ChannelMember
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, field_validator
from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
from sqlalchemy import or_, func, select, and_, text
from sqlalchemy.sql import exists
@@ -108,11 +108,24 @@ class MessageUserResponse(MessageModel):
user: Optional[UserNameResponse] = None
+class MessageUserSlimResponse(MessageUserResponse):
+ data: bool | None = None
+
+ @field_validator("data", mode="before")
+ def convert_data_to_bool(cls, v):
+ # No data or not a dict → False
+ if not isinstance(v, dict):
+ return False
+
+ # True if ANY value in the dict is non-empty
+ return any(bool(val) for val in v.values())
+
+
class MessageReplyToResponse(MessageUserResponse):
- reply_to_message: Optional[MessageUserResponse] = None
+ reply_to_message: Optional[MessageUserSlimResponse] = None
-class MessageWithReactionsResponse(MessageUserResponse):
+class MessageWithReactionsResponse(MessageUserSlimResponse):
reactions: list[Reactions]
diff --git a/backend/open_webui/models/models.py b/backend/open_webui/models/models.py
index 1c44d311ba..08dcfe87a1 100755
--- a/backend/open_webui/models/models.py
+++ b/backend/open_webui/models/models.py
@@ -3,7 +3,6 @@ import time
from typing import Optional
from open_webui.internal.db import Base, JSONField, get_db
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.models.groups import Groups
from open_webui.models.users import User, UserModel, Users, UserResponse
@@ -22,7 +21,6 @@ from open_webui.utils.access_control import has_access
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
@@ -359,6 +357,14 @@ class ModelsTable:
except Exception:
return None
+ def get_models_by_ids(self, ids: list[str]) -> list[ModelModel]:
+ try:
+ with get_db() as db:
+ models = db.query(Model).filter(Model.id.in_(ids)).all()
+ return [ModelModel.model_validate(model) for model in models]
+ except Exception:
+ return []
+
def toggle_model_by_id(self, id: str) -> Optional[ModelModel]:
with get_db() as db:
try:
diff --git a/backend/open_webui/models/notes.py b/backend/open_webui/models/notes.py
index af75fab598..cfeddf4a8c 100644
--- a/backend/open_webui/models/notes.py
+++ b/backend/open_webui/models/notes.py
@@ -7,12 +7,15 @@ from functools import lru_cache
from open_webui.internal.db import Base, get_db
from open_webui.models.groups import Groups
from open_webui.utils.access_control import has_access
-from open_webui.models.users import Users, UserResponse
+from open_webui.models.users import User, UserModel, Users, UserResponse
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
-from sqlalchemy import or_, func, select, and_, text
+from sqlalchemy.dialects.postgresql import JSONB
+
+
+from sqlalchemy import or_, func, select, and_, text, cast, or_, and_, func
from sqlalchemy.sql import exists
####################
@@ -75,7 +78,138 @@ class NoteUserResponse(NoteModel):
user: Optional[UserResponse] = None
+class NoteItemResponse(BaseModel):
+ id: str
+ title: str
+ data: Optional[dict]
+ updated_at: int
+ created_at: int
+ user: Optional[UserResponse] = None
+
+
+class NoteListResponse(BaseModel):
+ items: list[NoteUserResponse]
+ total: int
+
+
class NoteTable:
+ def _has_permission(self, db, query, filter: dict, permission: str = "read"):
+ group_ids = filter.get("group_ids", [])
+ user_id = filter.get("user_id")
+ dialect_name = db.bind.dialect.name
+
+ conditions = []
+
+ # Handle read_only permission separately
+ if permission == "read_only":
+ # For read_only, we want items where:
+ # 1. User has explicit read permission (via groups or user-level)
+ # 2. BUT does NOT have write permission
+ # 3. Public items are NOT considered read_only
+
+ read_conditions = []
+
+ # Group-level read permission
+ if group_ids:
+ group_read_conditions = []
+ for gid in group_ids:
+ if dialect_name == "sqlite":
+ group_read_conditions.append(
+ Note.access_control["read"]["group_ids"].contains([gid])
+ )
+ elif dialect_name == "postgresql":
+ group_read_conditions.append(
+ cast(
+ Note.access_control["read"]["group_ids"],
+ JSONB,
+ ).contains([gid])
+ )
+
+ if group_read_conditions:
+ read_conditions.append(or_(*group_read_conditions))
+
+ # Combine read conditions
+ if read_conditions:
+ has_read = or_(*read_conditions)
+ else:
+ # If no read conditions, return empty result
+ return query.filter(False)
+
+ # Now exclude items where user has write permission
+ write_exclusions = []
+
+ # Exclude items owned by user (they have implicit write)
+ if user_id:
+ write_exclusions.append(Note.user_id != user_id)
+
+ # Exclude items where user has explicit write permission via groups
+ if group_ids:
+ group_write_conditions = []
+ for gid in group_ids:
+ if dialect_name == "sqlite":
+ group_write_conditions.append(
+ Note.access_control["write"]["group_ids"].contains([gid])
+ )
+ elif dialect_name == "postgresql":
+ group_write_conditions.append(
+ cast(
+ Note.access_control["write"]["group_ids"],
+ JSONB,
+ ).contains([gid])
+ )
+
+ if group_write_conditions:
+ # User should NOT have write permission
+ write_exclusions.append(~or_(*group_write_conditions))
+
+ # Exclude public items (items without access_control)
+ write_exclusions.append(Note.access_control.isnot(None))
+ write_exclusions.append(cast(Note.access_control, String) != "null")
+
+ # Combine: has read AND does not have write AND not public
+ if write_exclusions:
+ query = query.filter(and_(has_read, *write_exclusions))
+ else:
+ query = query.filter(has_read)
+
+ return query
+
+ # Original logic for other permissions (read, write, etc.)
+ # Public access conditions
+ if group_ids or user_id:
+ conditions.extend(
+ [
+ Note.access_control.is_(None),
+ cast(Note.access_control, String) == "null",
+ ]
+ )
+
+ # User-level permission (owner has all permissions)
+ if user_id:
+ conditions.append(Note.user_id == user_id)
+
+ # Group-level permission
+ if group_ids:
+ group_conditions = []
+ for gid in group_ids:
+ if dialect_name == "sqlite":
+ group_conditions.append(
+ Note.access_control[permission]["group_ids"].contains([gid])
+ )
+ elif dialect_name == "postgresql":
+ group_conditions.append(
+ cast(
+ Note.access_control[permission]["group_ids"],
+ JSONB,
+ ).contains([gid])
+ )
+ conditions.append(or_(*group_conditions))
+
+ if conditions:
+ query = query.filter(or_(*conditions))
+
+ return query
+
def insert_new_note(
self,
form_data: NoteForm,
@@ -110,15 +244,107 @@ class NoteTable:
notes = query.all()
return [NoteModel.model_validate(note) for note in notes]
+ def search_notes(
+ self, user_id: str, filter: dict = {}, skip: int = 0, limit: int = 30
+ ) -> NoteListResponse:
+ with get_db() as db:
+ query = db.query(Note, User).outerjoin(User, User.id == Note.user_id)
+ if filter:
+ query_key = filter.get("query")
+ if query_key:
+ query = query.filter(
+ or_(
+ Note.title.ilike(f"%{query_key}%"),
+ cast(Note.data["content"]["md"], Text).ilike(
+ f"%{query_key}%"
+ ),
+ )
+ )
+
+ view_option = filter.get("view_option")
+ if view_option == "created":
+ query = query.filter(Note.user_id == user_id)
+ elif view_option == "shared":
+ query = query.filter(Note.user_id != user_id)
+
+ # Apply access control filtering
+ if "permission" in filter:
+ permission = filter["permission"]
+ else:
+ permission = "write"
+
+ query = self._has_permission(
+ db,
+ query,
+ filter,
+ permission=permission,
+ )
+
+ order_by = filter.get("order_by")
+ direction = filter.get("direction")
+
+ if order_by == "name":
+ if direction == "asc":
+ query = query.order_by(Note.title.asc())
+ else:
+ query = query.order_by(Note.title.desc())
+ elif order_by == "created_at":
+ if direction == "asc":
+ query = query.order_by(Note.created_at.asc())
+ else:
+ query = query.order_by(Note.created_at.desc())
+ elif order_by == "updated_at":
+ if direction == "asc":
+ query = query.order_by(Note.updated_at.asc())
+ else:
+ query = query.order_by(Note.updated_at.desc())
+ else:
+ query = query.order_by(Note.updated_at.desc())
+
+ else:
+ query = query.order_by(Note.updated_at.desc())
+
+ # Count BEFORE pagination
+ total = query.count()
+
+ if skip:
+ query = query.offset(skip)
+ if limit:
+ query = query.limit(limit)
+
+ items = query.all()
+
+ notes = []
+ for note, user in items:
+ notes.append(
+ NoteUserResponse(
+ **NoteModel.model_validate(note).model_dump(),
+ user=(
+ UserResponse(**UserModel.model_validate(user).model_dump())
+ if user
+ else None
+ ),
+ )
+ )
+
+ return NoteListResponse(items=notes, total=total)
+
def get_notes_by_user_id(
self,
user_id: str,
+ permission: str = "read",
skip: Optional[int] = None,
limit: Optional[int] = None,
) -> list[NoteModel]:
with get_db() as db:
- query = db.query(Note).filter(Note.user_id == user_id)
- query = query.order_by(Note.updated_at.desc())
+ user_group_ids = [
+ group.id for group in Groups.get_groups_by_member_id(user_id)
+ ]
+
+ query = db.query(Note).order_by(Note.updated_at.desc())
+ query = self._has_permission(
+ db, query, {"user_id": user_id, "group_ids": user_group_ids}, permission
+ )
if skip is not None:
query = query.offset(skip)
@@ -128,56 +354,6 @@ class NoteTable:
notes = query.all()
return [NoteModel.model_validate(note) for note in notes]
- def get_notes_by_permission(
- self,
- user_id: str,
- permission: str = "write",
- skip: Optional[int] = None,
- limit: Optional[int] = None,
- ) -> list[NoteModel]:
- with get_db() as db:
- user_groups = Groups.get_groups_by_member_id(user_id)
- user_group_ids = {group.id for group in user_groups}
-
- # Order newest-first. We stream to keep memory usage low.
- query = (
- db.query(Note)
- .order_by(Note.updated_at.desc())
- .execution_options(stream_results=True)
- .yield_per(256)
- )
-
- results: list[NoteModel] = []
- n_skipped = 0
-
- for note in query:
- # Fast-pass #1: owner
- if note.user_id == user_id:
- permitted = True
- # Fast-pass #2: public/open
- elif note.access_control is None:
- # Technically this should mean public access for both read and write, but we'll only do read for now
- # We might want to change this behavior later
- permitted = permission == "read"
- else:
- permitted = has_access(
- user_id, permission, note.access_control, user_group_ids
- )
-
- if not permitted:
- continue
-
- # Apply skip AFTER permission filtering so it counts only accessible notes
- if skip and n_skipped < skip:
- n_skipped += 1
- continue
-
- results.append(NoteModel.model_validate(note))
- if limit is not None and len(results) >= limit:
- break
-
- return results
-
def get_note_by_id(self, id: str) -> Optional[NoteModel]:
with get_db() as db:
note = db.query(Note).filter(Note.id == id).first()
diff --git a/backend/open_webui/models/oauth_sessions.py b/backend/open_webui/models/oauth_sessions.py
index d07faad35e..8b0334ed19 100644
--- a/backend/open_webui/models/oauth_sessions.py
+++ b/backend/open_webui/models/oauth_sessions.py
@@ -9,13 +9,12 @@ import json
from cryptography.fernet import Fernet
from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS, OAUTH_SESSION_TOKEN_ENCRYPTION_KEY
+from open_webui.env import OAUTH_SESSION_TOKEN_ENCRYPTION_KEY
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, String, Text, Index
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# DB MODEL
diff --git a/backend/open_webui/models/tags.py b/backend/open_webui/models/tags.py
index e1cbb68a0b..499f3859dc 100644
--- a/backend/open_webui/models/tags.py
+++ b/backend/open_webui/models/tags.py
@@ -6,12 +6,10 @@ from typing import Optional
from open_webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, String, JSON, PrimaryKeyConstraint, Index
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
diff --git a/backend/open_webui/models/tools.py b/backend/open_webui/models/tools.py
index 7f6c7fd3f5..fff53a7e94 100644
--- a/backend/open_webui/models/tools.py
+++ b/backend/open_webui/models/tools.py
@@ -6,7 +6,6 @@ from open_webui.internal.db import Base, JSONField, get_db
from open_webui.models.users import Users, UserResponse
from open_webui.models.groups import Groups
-from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, String, Text, JSON
@@ -14,7 +13,6 @@ from open_webui.utils.access_control import has_access
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
# Tools DB Schema
diff --git a/backend/open_webui/models/users.py b/backend/open_webui/models/users.py
index 86f9d011e8..5807603a89 100644
--- a/backend/open_webui/models/users.py
+++ b/backend/open_webui/models/users.py
@@ -5,11 +5,11 @@ from open_webui.internal.db import Base, JSONField, get_db
from open_webui.env import DATABASE_USER_ACTIVE_STATUS_UPDATE_INTERVAL
+
from open_webui.models.chats import Chats
from open_webui.models.groups import Groups, GroupMember
from open_webui.models.channels import ChannelMember
-
from open_webui.utils.misc import throttle
diff --git a/backend/open_webui/retrieval/loaders/external_document.py b/backend/open_webui/retrieval/loaders/external_document.py
index 998afd36f6..e1371be288 100644
--- a/backend/open_webui/retrieval/loaders/external_document.py
+++ b/backend/open_webui/retrieval/loaders/external_document.py
@@ -6,10 +6,8 @@ from urllib.parse import quote
from langchain_core.document_loaders import BaseLoader
from langchain_core.documents import Document
from open_webui.utils.headers import include_user_info_headers
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class ExternalDocumentLoader(BaseLoader):
diff --git a/backend/open_webui/retrieval/loaders/external_web.py b/backend/open_webui/retrieval/loaders/external_web.py
index 68ed66162b..39644caddb 100644
--- a/backend/open_webui/retrieval/loaders/external_web.py
+++ b/backend/open_webui/retrieval/loaders/external_web.py
@@ -4,10 +4,8 @@ from typing import Iterator, List, Union
from langchain_core.document_loaders import BaseLoader
from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class ExternalWebLoader(BaseLoader):
diff --git a/backend/open_webui/retrieval/loaders/main.py b/backend/open_webui/retrieval/loaders/main.py
index 1346cd065c..b0bc1dd068 100644
--- a/backend/open_webui/retrieval/loaders/main.py
+++ b/backend/open_webui/retrieval/loaders/main.py
@@ -30,11 +30,10 @@ from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
from open_webui.retrieval.loaders.mineru import MinerULoader
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.env import GLOBAL_LOG_LEVEL
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
known_source_ext = [
"go",
@@ -144,19 +143,17 @@ class DoclingLoader:
with open(self.file_path, "rb") as f:
headers = {}
if self.api_key:
- headers["Authorization"] = f"Bearer {self.api_key}"
-
- files = {
- "files": (
- self.file_path,
- f,
- self.mime_type or "application/octet-stream",
- )
- }
+ headers["X-Api-Key"] = f"Bearer {self.api_key}"
r = requests.post(
f"{self.url}/v1/convert/file",
- files=files,
+ files={
+ "files": (
+ self.file_path,
+ f,
+ self.mime_type or "application/octet-stream",
+ )
+ },
data={
"image_export_mode": "placeholder",
**self.params,
@@ -334,12 +331,21 @@ class Loader:
elif self.engine == "mineru" and file_ext in [
"pdf"
]: # MinerU currently only supports PDF
+
+ mineru_timeout = self.kwargs.get("MINERU_API_TIMEOUT", 300)
+ if mineru_timeout:
+ try:
+ mineru_timeout = int(mineru_timeout)
+ except ValueError:
+ mineru_timeout = 300
+
loader = MinerULoader(
file_path=file_path,
api_mode=self.kwargs.get("MINERU_API_MODE", "local"),
api_url=self.kwargs.get("MINERU_API_URL", "http://localhost:8000"),
api_key=self.kwargs.get("MINERU_API_KEY", ""),
params=self.kwargs.get("MINERU_PARAMS", {}),
+ timeout=mineru_timeout,
)
elif (
self.engine == "mistral_ocr"
diff --git a/backend/open_webui/retrieval/loaders/mineru.py b/backend/open_webui/retrieval/loaders/mineru.py
index 360af804c7..617be8e87a 100644
--- a/backend/open_webui/retrieval/loaders/mineru.py
+++ b/backend/open_webui/retrieval/loaders/mineru.py
@@ -26,11 +26,13 @@ class MinerULoader:
api_url: str = "http://localhost:8000",
api_key: str = "",
params: dict = None,
+ timeout: Optional[int] = 300,
):
self.file_path = file_path
self.api_mode = api_mode.lower()
self.api_url = api_url.rstrip("/")
self.api_key = api_key
+ self.timeout = timeout
# Parse params dict with defaults
self.params = params or {}
@@ -101,7 +103,7 @@ class MinerULoader:
f"{self.api_url}/file_parse",
data=form_data,
files=files,
- timeout=300, # 5 minute timeout for large documents
+ timeout=self.timeout,
)
response.raise_for_status()
@@ -300,7 +302,7 @@ class MinerULoader:
response = requests.put(
upload_url,
data=f,
- timeout=300, # 5 minute timeout for large files
+ timeout=self.timeout,
)
response.raise_for_status()
except FileNotFoundError:
diff --git a/backend/open_webui/retrieval/loaders/mistral.py b/backend/open_webui/retrieval/loaders/mistral.py
index 6a2d235559..68570757c8 100644
--- a/backend/open_webui/retrieval/loaders/mistral.py
+++ b/backend/open_webui/retrieval/loaders/mistral.py
@@ -9,11 +9,10 @@ from typing import List, Dict, Any
from contextlib import asynccontextmanager
from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.env import GLOBAL_LOG_LEVEL
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class MistralLoader:
diff --git a/backend/open_webui/retrieval/loaders/tavily.py b/backend/open_webui/retrieval/loaders/tavily.py
index 15a3d7f97f..f298de80b4 100644
--- a/backend/open_webui/retrieval/loaders/tavily.py
+++ b/backend/open_webui/retrieval/loaders/tavily.py
@@ -4,10 +4,8 @@ from typing import Iterator, List, Literal, Union
from langchain_core.document_loaders import BaseLoader
from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class TavilyLoader(BaseLoader):
diff --git a/backend/open_webui/retrieval/loaders/youtube.py b/backend/open_webui/retrieval/loaders/youtube.py
index cba602ed87..faf7b4452e 100644
--- a/backend/open_webui/retrieval/loaders/youtube.py
+++ b/backend/open_webui/retrieval/loaders/youtube.py
@@ -4,10 +4,8 @@ from xml.etree.ElementTree import ParseError
from typing import Any, Dict, Generator, List, Optional, Sequence, Union
from urllib.parse import parse_qs, urlparse
from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
ALLOWED_SCHEMES = {"http", "https"}
ALLOWED_NETLOCS = {
diff --git a/backend/open_webui/retrieval/models/colbert.py b/backend/open_webui/retrieval/models/colbert.py
index 7ec888437a..2a8c0329d7 100644
--- a/backend/open_webui/retrieval/models/colbert.py
+++ b/backend/open_webui/retrieval/models/colbert.py
@@ -5,12 +5,10 @@ import numpy as np
from colbert.infra import ColBERTConfig
from colbert.modeling.checkpoint import Checkpoint
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.retrieval.models.base_reranker import BaseReranker
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class ColBERT(BaseReranker):
diff --git a/backend/open_webui/retrieval/models/external.py b/backend/open_webui/retrieval/models/external.py
index 822cb3e3dd..d567bf4fe5 100644
--- a/backend/open_webui/retrieval/models/external.py
+++ b/backend/open_webui/retrieval/models/external.py
@@ -4,13 +4,12 @@ from typing import Optional, List, Tuple
from urllib.parse import quote
-from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, SRC_LOG_LEVELS
+from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS
from open_webui.retrieval.models.base_reranker import BaseReranker
from open_webui.utils.headers import include_user_info_headers
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class ExternalReranker(BaseReranker):
@@ -19,10 +18,12 @@ class ExternalReranker(BaseReranker):
api_key: str,
url: str = "http://localhost:8080/v1/rerank",
model: str = "reranker",
+ timeout: Optional[int] = None,
):
self.api_key = api_key
self.url = url
self.model = model
+ self.timeout = timeout
def predict(
self, sentences: List[Tuple[str, str]], user=None
@@ -53,6 +54,7 @@ class ExternalReranker(BaseReranker):
f"{self.url}",
headers=headers,
json=payload,
+ timeout=self.timeout,
)
r.raise_for_status()
diff --git a/backend/open_webui/retrieval/utils.py b/backend/open_webui/retrieval/utils.py
index 711b1a8b79..bb2c3ef12f 100644
--- a/backend/open_webui/retrieval/utils.py
+++ b/backend/open_webui/retrieval/utils.py
@@ -12,7 +12,10 @@ import re
from urllib.parse import quote
from huggingface_hub import snapshot_download
-from langchain.retrievers import ContextualCompressionRetriever, EnsembleRetriever
+from langchain_classic.retrievers import (
+ ContextualCompressionRetriever,
+ EnsembleRetriever,
+)
from langchain_community.retrievers import BM25Retriever
from langchain_core.documents import Document
@@ -37,7 +40,6 @@ from open_webui.retrieval.loaders.youtube import YoutubeLoader
from open_webui.env import (
- SRC_LOG_LEVELS,
OFFLINE_MODE,
ENABLE_FORWARD_USER_INFO_HEADERS,
)
@@ -48,7 +50,6 @@ from open_webui.config import (
)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
from typing import Any
@@ -1281,7 +1282,7 @@ class RerankCompressor(BaseDocumentCompressor):
scores = None
if reranking:
- scores = self.reranking_function(query, documents)
+ scores = await asyncio.to_thread(self.reranking_function, query, documents)
else:
from sentence_transformers import util
diff --git a/backend/open_webui/retrieval/vector/dbs/chroma.py b/backend/open_webui/retrieval/vector/dbs/chroma.py
index 1fdb064c51..69d894afde 100755
--- a/backend/open_webui/retrieval/vector/dbs/chroma.py
+++ b/backend/open_webui/retrieval/vector/dbs/chroma.py
@@ -24,10 +24,8 @@ from open_webui.config import (
CHROMA_CLIENT_AUTH_PROVIDER,
CHROMA_CLIENT_AUTH_CREDENTIALS,
)
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class ChromaClient(VectorDBBase):
diff --git a/backend/open_webui/retrieval/vector/dbs/milvus.py b/backend/open_webui/retrieval/vector/dbs/milvus.py
index 3dae4672f3..23e4bbd03e 100644
--- a/backend/open_webui/retrieval/vector/dbs/milvus.py
+++ b/backend/open_webui/retrieval/vector/dbs/milvus.py
@@ -25,10 +25,8 @@ from open_webui.config import (
MILVUS_DISKANN_MAX_DEGREE,
MILVUS_DISKANN_SEARCH_LIST_SIZE,
)
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class MilvusClient(VectorDBBase):
diff --git a/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py b/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py
index cd2ceed795..203a36141e 100644
--- a/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py
+++ b/backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py
@@ -12,7 +12,6 @@ from open_webui.config import (
MILVUS_HNSW_EFCONSTRUCTION,
MILVUS_IVF_FLAT_NLIST,
)
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.retrieval.vector.main import (
GetResult,
SearchResult,
@@ -29,7 +28,6 @@ from pymilvus import (
)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
RESOURCE_ID_FIELD = "resource_id"
diff --git a/backend/open_webui/retrieval/vector/dbs/oracle23ai.py b/backend/open_webui/retrieval/vector/dbs/oracle23ai.py
index b714588bdc..3f5c3463f0 100644
--- a/backend/open_webui/retrieval/vector/dbs/oracle23ai.py
+++ b/backend/open_webui/retrieval/vector/dbs/oracle23ai.py
@@ -55,10 +55,8 @@ from open_webui.config import (
ORACLE_DB_POOL_MAX,
ORACLE_DB_POOL_INCREMENT,
)
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class Oracle23aiClient(VectorDBBase):
diff --git a/backend/open_webui/retrieval/vector/dbs/pgvector.py b/backend/open_webui/retrieval/vector/dbs/pgvector.py
index 85c2ef009d..2f4677995a 100644
--- a/backend/open_webui/retrieval/vector/dbs/pgvector.py
+++ b/backend/open_webui/retrieval/vector/dbs/pgvector.py
@@ -51,7 +51,6 @@ from open_webui.config import (
PGVECTOR_USE_HALFVEC,
)
-from open_webui.env import SRC_LOG_LEVELS
VECTOR_LENGTH = PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH
USE_HALFVEC = PGVECTOR_USE_HALFVEC
@@ -61,7 +60,6 @@ VECTOR_OPCLASS = "halfvec_cosine_ops" if USE_HALFVEC else "vector_cosine_ops"
Base = declarative_base()
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def pgcrypto_encrypt(val, key):
diff --git a/backend/open_webui/retrieval/vector/dbs/pinecone.py b/backend/open_webui/retrieval/vector/dbs/pinecone.py
index 5bef0d9ea7..94d09dabf5 100644
--- a/backend/open_webui/retrieval/vector/dbs/pinecone.py
+++ b/backend/open_webui/retrieval/vector/dbs/pinecone.py
@@ -31,7 +31,6 @@ from open_webui.config import (
PINECONE_METRIC,
PINECONE_CLOUD,
)
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.retrieval.vector.utils import process_metadata
@@ -39,7 +38,6 @@ NO_LIMIT = 10000 # Reasonable limit to avoid overwhelming the system
BATCH_SIZE = 100 # Recommended batch size for Pinecone operations
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class PineconeClient(VectorDBBase):
diff --git a/backend/open_webui/retrieval/vector/dbs/qdrant.py b/backend/open_webui/retrieval/vector/dbs/qdrant.py
index ea43297499..ce7095bea2 100644
--- a/backend/open_webui/retrieval/vector/dbs/qdrant.py
+++ b/backend/open_webui/retrieval/vector/dbs/qdrant.py
@@ -22,12 +22,10 @@ from open_webui.config import (
QDRANT_TIMEOUT,
QDRANT_HNSW_M,
)
-from open_webui.env import SRC_LOG_LEVELS
NO_LIMIT = 999999999
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class QdrantClient(VectorDBBase):
diff --git a/backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py b/backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py
index e9fa03d459..fdc8f9d897 100644
--- a/backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py
+++ b/backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py
@@ -13,7 +13,6 @@ from open_webui.config import (
QDRANT_TIMEOUT,
QDRANT_HNSW_M,
)
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.retrieval.vector.main import (
GetResult,
SearchResult,
@@ -30,7 +29,6 @@ TENANT_ID_FIELD = "tenant_id"
DEFAULT_DIMENSION = 384
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def _tenant_filter(tenant_id: str) -> models.FieldCondition:
diff --git a/backend/open_webui/retrieval/vector/dbs/s3vector.py b/backend/open_webui/retrieval/vector/dbs/s3vector.py
index e2a7adfd8b..95fc5d3f24 100644
--- a/backend/open_webui/retrieval/vector/dbs/s3vector.py
+++ b/backend/open_webui/retrieval/vector/dbs/s3vector.py
@@ -6,13 +6,11 @@ from open_webui.retrieval.vector.main import (
SearchResult,
)
from open_webui.config import S3_VECTOR_BUCKET_NAME, S3_VECTOR_REGION
-from open_webui.env import SRC_LOG_LEVELS
from typing import List, Optional, Dict, Any, Union
import logging
import boto3
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
class S3VectorClient(VectorDBBase):
diff --git a/backend/open_webui/retrieval/web/azure.py b/backend/open_webui/retrieval/web/azure.py
index 814cf4b63c..3859ccc9b7 100644
--- a/backend/open_webui/retrieval/web/azure.py
+++ b/backend/open_webui/retrieval/web/azure.py
@@ -1,10 +1,8 @@
import logging
from typing import Optional
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
"""
Azure AI Search integration for Open WebUI.
diff --git a/backend/open_webui/retrieval/web/bing.py b/backend/open_webui/retrieval/web/bing.py
index 0a3ba4621c..4c9822b900 100644
--- a/backend/open_webui/retrieval/web/bing.py
+++ b/backend/open_webui/retrieval/web/bing.py
@@ -4,11 +4,9 @@ from pprint import pprint
from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
import argparse
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
"""
Documentation: https://docs.microsoft.com/en-us/bing/search-apis/bing-web-search/overview
"""
diff --git a/backend/open_webui/retrieval/web/bocha.py b/backend/open_webui/retrieval/web/bocha.py
index f26da36f84..7e3c9b0a40 100644
--- a/backend/open_webui/retrieval/web/bocha.py
+++ b/backend/open_webui/retrieval/web/bocha.py
@@ -4,20 +4,18 @@ from typing import Optional
import requests
import json
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def _parse_response(response):
- result = {}
+ results = []
if "data" in response:
data = response["data"]
if "webPages" in data:
webPages = data["webPages"]
if "value" in webPages:
- result["webpage"] = [
+ results = [
{
"id": item.get("id", ""),
"name": item.get("name", ""),
@@ -31,7 +29,7 @@ def _parse_response(response):
}
for item in webPages["value"]
]
- return result
+ return results
def search_bocha(
@@ -53,7 +51,7 @@ def search_bocha(
response = requests.post(url, headers=headers, data=payload, timeout=5)
response.raise_for_status()
results = _parse_response(response.json())
- print(results)
+
if filter_list:
results = get_filtered_results(results, filter_list)
@@ -61,5 +59,5 @@ def search_bocha(
SearchResult(
link=result["url"], title=result.get("name"), snippet=result.get("summary")
)
- for result in results.get("webpage", [])[:count]
+ for result in results[:count]
]
diff --git a/backend/open_webui/retrieval/web/brave.py b/backend/open_webui/retrieval/web/brave.py
index 7bea575620..e047602b36 100644
--- a/backend/open_webui/retrieval/web/brave.py
+++ b/backend/open_webui/retrieval/web/brave.py
@@ -3,10 +3,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_brave(
diff --git a/backend/open_webui/retrieval/web/duckduckgo.py b/backend/open_webui/retrieval/web/duckduckgo.py
index e4cf9d00ec..0303b4e303 100644
--- a/backend/open_webui/retrieval/web/duckduckgo.py
+++ b/backend/open_webui/retrieval/web/duckduckgo.py
@@ -4,10 +4,8 @@ from typing import Optional
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
from ddgs import DDGS
from ddgs.exceptions import RatelimitException
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_duckduckgo(
diff --git a/backend/open_webui/retrieval/web/exa.py b/backend/open_webui/retrieval/web/exa.py
index 927adef413..df9554fab2 100644
--- a/backend/open_webui/retrieval/web/exa.py
+++ b/backend/open_webui/retrieval/web/exa.py
@@ -3,11 +3,9 @@ from dataclasses import dataclass
from typing import Optional
import requests
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.retrieval.web.main import SearchResult
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
EXA_API_BASE = "https://api.exa.ai"
diff --git a/backend/open_webui/retrieval/web/external.py b/backend/open_webui/retrieval/web/external.py
index 13f6a5aa68..527c918a47 100644
--- a/backend/open_webui/retrieval/web/external.py
+++ b/backend/open_webui/retrieval/web/external.py
@@ -5,14 +5,12 @@ import requests
from fastapi import Request
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
from open_webui.utils.headers import include_user_info_headers
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_external(
diff --git a/backend/open_webui/retrieval/web/firecrawl.py b/backend/open_webui/retrieval/web/firecrawl.py
index 2d9b104bca..82635aa8ca 100644
--- a/backend/open_webui/retrieval/web/firecrawl.py
+++ b/backend/open_webui/retrieval/web/firecrawl.py
@@ -2,11 +2,9 @@ import logging
from typing import Optional, List
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_firecrawl(
diff --git a/backend/open_webui/retrieval/web/google_pse.py b/backend/open_webui/retrieval/web/google_pse.py
index 69de24711a..96fa8c98cd 100644
--- a/backend/open_webui/retrieval/web/google_pse.py
+++ b/backend/open_webui/retrieval/web/google_pse.py
@@ -3,10 +3,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_google_pse(
diff --git a/backend/open_webui/retrieval/web/jina_search.py b/backend/open_webui/retrieval/web/jina_search.py
index a87293db5c..bcc5794027 100644
--- a/backend/open_webui/retrieval/web/jina_search.py
+++ b/backend/open_webui/retrieval/web/jina_search.py
@@ -2,11 +2,9 @@ import logging
import requests
from open_webui.retrieval.web.main import SearchResult
-from open_webui.env import SRC_LOG_LEVELS
from yarl import URL
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_jina(api_key: str, query: str, count: int) -> list[SearchResult]:
diff --git a/backend/open_webui/retrieval/web/kagi.py b/backend/open_webui/retrieval/web/kagi.py
index 0b69da8bce..f0303acf69 100644
--- a/backend/open_webui/retrieval/web/kagi.py
+++ b/backend/open_webui/retrieval/web/kagi.py
@@ -3,10 +3,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_kagi(
diff --git a/backend/open_webui/retrieval/web/mojeek.py b/backend/open_webui/retrieval/web/mojeek.py
index d298b0ee51..d48f7aeef8 100644
--- a/backend/open_webui/retrieval/web/mojeek.py
+++ b/backend/open_webui/retrieval/web/mojeek.py
@@ -3,10 +3,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_mojeek(
diff --git a/backend/open_webui/retrieval/web/ollama.py b/backend/open_webui/retrieval/web/ollama.py
index a199a14389..71bd9d5124 100644
--- a/backend/open_webui/retrieval/web/ollama.py
+++ b/backend/open_webui/retrieval/web/ollama.py
@@ -3,11 +3,9 @@ from dataclasses import dataclass
from typing import Optional
import requests
-from open_webui.env import SRC_LOG_LEVELS
-from open_webui.retrieval.web.main import SearchResult
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_ollama_cloud(
@@ -38,6 +36,9 @@ def search_ollama_cloud(
results = data.get("results", [])
log.info(f"Found {len(results)} results")
+ if filter_list:
+ results = get_filtered_results(results, filter_list)
+
return [
SearchResult(
link=result.get("url", ""),
diff --git a/backend/open_webui/retrieval/web/perplexity.py b/backend/open_webui/retrieval/web/perplexity.py
index 4e046668fa..aae802b432 100644
--- a/backend/open_webui/retrieval/web/perplexity.py
+++ b/backend/open_webui/retrieval/web/perplexity.py
@@ -3,7 +3,6 @@ from typing import Optional, Literal
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
MODELS = Literal[
"sonar",
@@ -16,7 +15,6 @@ SEARCH_CONTEXT_USAGE_LEVELS = Literal["low", "medium", "high"]
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_perplexity(
diff --git a/backend/open_webui/retrieval/web/perplexity_search.py b/backend/open_webui/retrieval/web/perplexity_search.py
index 97961f478b..5c591ff64f 100644
--- a/backend/open_webui/retrieval/web/perplexity_search.py
+++ b/backend/open_webui/retrieval/web/perplexity_search.py
@@ -4,11 +4,9 @@ import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
from open_webui.utils.headers import include_user_info_headers
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_perplexity_search(
diff --git a/backend/open_webui/retrieval/web/searchapi.py b/backend/open_webui/retrieval/web/searchapi.py
index d7704638c2..caf781c5df 100644
--- a/backend/open_webui/retrieval/web/searchapi.py
+++ b/backend/open_webui/retrieval/web/searchapi.py
@@ -4,10 +4,8 @@ from urllib.parse import urlencode
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_searchapi(
diff --git a/backend/open_webui/retrieval/web/searxng.py b/backend/open_webui/retrieval/web/searxng.py
index 15e3c098a9..b3d4eb8795 100644
--- a/backend/open_webui/retrieval/web/searxng.py
+++ b/backend/open_webui/retrieval/web/searxng.py
@@ -3,10 +3,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_searxng(
@@ -27,7 +25,7 @@ def search_searxng(
count (int): The maximum number of results to retrieve from the search.
Keyword Args:
- language (str): Language filter for the search results; e.g., "en-US". Defaults to an empty string.
+ language (str): Language filter for the search results; e.g., "all", "en-US", "es". Defaults to "all".
safesearch (int): Safe search filter for safer web results; 0 = off, 1 = moderate, 2 = strict. Defaults to 1 (moderate).
time_range (str): Time range for filtering results by date; e.g., "2023-04-05..today" or "all-time". Defaults to ''.
categories: (Optional[list[str]]): Specific categories within which the search should be performed, defaulting to an empty string if not provided.
@@ -40,7 +38,7 @@ def search_searxng(
"""
# Default values for optional parameters are provided as empty strings or None when not specified.
- language = kwargs.get("language", "en-US")
+ language = kwargs.get("language", "all")
safesearch = kwargs.get("safesearch", "1")
time_range = kwargs.get("time_range", "")
categories = "".join(kwargs.get("categories", []))
diff --git a/backend/open_webui/retrieval/web/serpapi.py b/backend/open_webui/retrieval/web/serpapi.py
index 8762210bfd..bb421b500f 100644
--- a/backend/open_webui/retrieval/web/serpapi.py
+++ b/backend/open_webui/retrieval/web/serpapi.py
@@ -4,10 +4,8 @@ from urllib.parse import urlencode
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_serpapi(
diff --git a/backend/open_webui/retrieval/web/serper.py b/backend/open_webui/retrieval/web/serper.py
index 685e34375d..5a745e304e 100644
--- a/backend/open_webui/retrieval/web/serper.py
+++ b/backend/open_webui/retrieval/web/serper.py
@@ -4,10 +4,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_serper(
diff --git a/backend/open_webui/retrieval/web/serply.py b/backend/open_webui/retrieval/web/serply.py
index a9b473eb04..68843eba85 100644
--- a/backend/open_webui/retrieval/web/serply.py
+++ b/backend/open_webui/retrieval/web/serply.py
@@ -4,10 +4,8 @@ from urllib.parse import urlencode
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_serply(
diff --git a/backend/open_webui/retrieval/web/serpstack.py b/backend/open_webui/retrieval/web/serpstack.py
index d4dbda57ca..97db858724 100644
--- a/backend/open_webui/retrieval/web/serpstack.py
+++ b/backend/open_webui/retrieval/web/serpstack.py
@@ -3,10 +3,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_serpstack(
diff --git a/backend/open_webui/retrieval/web/sougou.py b/backend/open_webui/retrieval/web/sougou.py
index af7957c4fc..d8747c3ade 100644
--- a/backend/open_webui/retrieval/web/sougou.py
+++ b/backend/open_webui/retrieval/web/sougou.py
@@ -4,10 +4,8 @@ from typing import Optional, List
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_sougou(
diff --git a/backend/open_webui/retrieval/web/tavily.py b/backend/open_webui/retrieval/web/tavily.py
index bfd102afa6..6d9ff89a87 100644
--- a/backend/open_webui/retrieval/web/tavily.py
+++ b/backend/open_webui/retrieval/web/tavily.py
@@ -3,10 +3,8 @@ from typing import Optional
import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_tavily(
diff --git a/backend/open_webui/retrieval/web/utils.py b/backend/open_webui/retrieval/web/utils.py
index bdbde0b3a9..eb01976e95 100644
--- a/backend/open_webui/retrieval/web/utils.py
+++ b/backend/open_webui/retrieval/web/utils.py
@@ -33,6 +33,7 @@ from open_webui.config import (
PLAYWRIGHT_WS_URL,
PLAYWRIGHT_TIMEOUT,
WEB_LOADER_ENGINE,
+ WEB_LOADER_TIMEOUT,
FIRECRAWL_API_BASE_URL,
FIRECRAWL_API_KEY,
TAVILY_API_KEY,
@@ -41,11 +42,9 @@ from open_webui.config import (
EXTERNAL_WEB_LOADER_API_KEY,
WEB_FETCH_FILTER_LIST,
)
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.utils.misc import is_string_allowed
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def resolve_hostname(hostname):
@@ -674,6 +673,20 @@ def get_web_loader(
if WEB_LOADER_ENGINE.value == "" or WEB_LOADER_ENGINE.value == "safe_web":
WebLoaderClass = SafeWebBaseLoader
+
+ request_kwargs = {}
+ if WEB_LOADER_TIMEOUT.value:
+ try:
+ timeout_value = float(WEB_LOADER_TIMEOUT.value)
+ except ValueError:
+ timeout_value = None
+
+ if timeout_value:
+ request_kwargs["timeout"] = timeout_value
+
+ if request_kwargs:
+ web_loader_args["requests_kwargs"] = request_kwargs
+
if WEB_LOADER_ENGINE.value == "playwright":
WebLoaderClass = SafePlaywrightURLLoader
web_loader_args["playwright_timeout"] = PLAYWRIGHT_TIMEOUT.value
diff --git a/backend/open_webui/retrieval/web/yacy.py b/backend/open_webui/retrieval/web/yacy.py
index bc61425cbc..2419717b24 100644
--- a/backend/open_webui/retrieval/web/yacy.py
+++ b/backend/open_webui/retrieval/web/yacy.py
@@ -4,10 +4,8 @@ from typing import Optional
import requests
from requests.auth import HTTPDigestAuth
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_yacy(
diff --git a/backend/open_webui/routers/audio.py b/backend/open_webui/routers/audio.py
index 9c84f9c704..0816cdcde3 100644
--- a/backend/open_webui/routers/audio.py
+++ b/backend/open_webui/routers/audio.py
@@ -33,6 +33,7 @@ from fastapi.responses import FileResponse
from pydantic import BaseModel
+from open_webui.utils.misc import strict_match_mime_type
from open_webui.utils.auth import get_admin_user, get_verified_user
from open_webui.utils.headers import include_user_info_headers
from open_webui.config import (
@@ -48,7 +49,6 @@ from open_webui.env import (
ENV,
AIOHTTP_CLIENT_SESSION_SSL,
AIOHTTP_CLIENT_TIMEOUT,
- SRC_LOG_LEVELS,
DEVICE_TYPE,
ENABLE_FORWARD_USER_INFO_HEADERS,
)
@@ -63,7 +63,6 @@ AZURE_MAX_FILE_SIZE_MB = 200
AZURE_MAX_FILE_SIZE = AZURE_MAX_FILE_SIZE_MB * 1024 * 1024 # Convert MB to bytes
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["AUDIO"])
SPEECH_CACHE_DIR = CACHE_DIR / "audio" / "speech"
SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
@@ -1155,17 +1154,9 @@ def transcription(
stt_supported_content_types = getattr(
request.app.state.config, "STT_SUPPORTED_CONTENT_TYPES", []
- )
+ ) or ["audio/*", "video/webm"]
- if not any(
- fnmatch(file.content_type, content_type)
- for content_type in (
- stt_supported_content_types
- if stt_supported_content_types
- and any(t.strip() for t in stt_supported_content_types)
- else ["audio/*", "video/webm"]
- )
- ):
+ if not strict_match_mime_type(stt_supported_content_types, file.content_type):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
diff --git a/backend/open_webui/routers/auths.py b/backend/open_webui/routers/auths.py
index 3d83dcaea6..59c5322c7f 100644
--- a/backend/open_webui/routers/auths.py
+++ b/backend/open_webui/routers/auths.py
@@ -37,7 +37,6 @@ from open_webui.env import (
WEBUI_AUTH_COOKIE_SECURE,
WEBUI_AUTH_SIGNOUT_REDIRECT_URL,
ENABLE_INITIAL_ADMIN_SIGNUP,
- SRC_LOG_LEVELS,
)
from fastapi import APIRouter, Depends, HTTPException, Request, status
from fastapi.responses import RedirectResponse, Response, JSONResponse
@@ -81,7 +80,6 @@ from ldap3.utils.conv import escape_filter_chars
router = APIRouter()
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
signin_rate_limiter = RateLimiter(
redis_client=get_redis_client(), limit=5 * 3, window=60 * 3
@@ -288,13 +286,11 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
f"{LDAP_ATTRIBUTE_FOR_MAIL}",
"cn",
]
-
if ENABLE_LDAP_GROUP_MANAGEMENT:
search_attributes.append(f"{LDAP_ATTRIBUTE_FOR_GROUPS}")
log.info(
f"LDAP Group Management enabled. Adding {LDAP_ATTRIBUTE_FOR_GROUPS} to search attributes"
)
-
log.info(f"LDAP search attributes: {search_attributes}")
search_success = connection_app.search(
@@ -302,15 +298,22 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
search_filter=f"(&({LDAP_ATTRIBUTE_FOR_USERNAME}={escape_filter_chars(form_data.user.lower())}){LDAP_SEARCH_FILTERS})",
attributes=search_attributes,
)
-
if not search_success or not connection_app.entries:
raise HTTPException(400, detail="User not found in the LDAP server")
entry = connection_app.entries[0]
- username = str(entry[f"{LDAP_ATTRIBUTE_FOR_USERNAME}"]).lower()
+ entry_username = entry[f"{LDAP_ATTRIBUTE_FOR_USERNAME}"].value
email = entry[
f"{LDAP_ATTRIBUTE_FOR_MAIL}"
].value # retrieve the Attribute value
+
+ username_list = [] # list of usernames from LDAP attribute
+ if isinstance(entry_username, list):
+ username_list = [str(name).lower() for name in entry_username]
+ else:
+ username_list = [str(entry_username).lower()]
+
+ # TODO: support multiple emails if LDAP returns a list
if not email:
raise HTTPException(400, "User does not have a valid email address.")
elif isinstance(email, str):
@@ -320,13 +323,13 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
else:
email = str(email).lower()
- cn = str(entry["cn"])
- user_dn = entry.entry_dn
+ cn = str(entry["cn"]) # common name
+ user_dn = entry.entry_dn # user distinguished name
user_groups = []
if ENABLE_LDAP_GROUP_MANAGEMENT and LDAP_ATTRIBUTE_FOR_GROUPS in entry:
group_dns = entry[LDAP_ATTRIBUTE_FOR_GROUPS]
- log.info(f"LDAP raw group DNs for user {username}: {group_dns}")
+ log.info(f"LDAP raw group DNs for user {username_list}: {group_dns}")
if group_dns:
log.info(f"LDAP group_dns original: {group_dns}")
@@ -377,16 +380,16 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
)
log.info(
- f"LDAP groups for user {username}: {user_groups} (total: {len(user_groups)})"
+ f"LDAP groups for user {username_list}: {user_groups} (total: {len(user_groups)})"
)
else:
- log.info(f"No groups found for user {username}")
+ log.info(f"No groups found for user {username_list}")
elif ENABLE_LDAP_GROUP_MANAGEMENT:
log.warning(
f"LDAP Group Management enabled but {LDAP_ATTRIBUTE_FOR_GROUPS} attribute not found in user entry"
)
- if username == form_data.user.lower():
+ if username_list and form_data.user.lower() in username_list:
connection_user = Connection(
server,
user_dn,
diff --git a/backend/open_webui/routers/channels.py b/backend/open_webui/routers/channels.py
index 0dff67da3e..a0dae72442 100644
--- a/backend/open_webui/routers/channels.py
+++ b/backend/open_webui/routers/channels.py
@@ -5,7 +5,7 @@ from typing import Optional
from fastapi import APIRouter, Depends, HTTPException, Request, status, BackgroundTasks
from pydantic import BaseModel
-
+from pydantic import field_validator
from open_webui.socket.main import (
emit_to_users,
@@ -39,9 +39,10 @@ from open_webui.models.messages import (
)
+from open_webui.utils.files import get_image_base64_from_file_id
+
from open_webui.config import ENABLE_ADMIN_CHAT_ACCESS, ENABLE_ADMIN_EXPORT
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.utils.models import (
@@ -62,10 +63,24 @@ from open_webui.utils.webhook import post_webhook
from open_webui.utils.channels import extract_mentions, replace_mentions
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
+
+############################
+# Channels Enabled Dependency
+############################
+
+
+def check_channels_access(request: Request):
+ """Dependency to ensure channels are globally enabled."""
+ if not request.app.state.config.ENABLE_CHANNELS:
+ raise HTTPException(
+ status_code=status.HTTP_403_FORBIDDEN,
+ detail="Channels are not enabled",
+ )
+
+
############################
# GetChatList
############################
@@ -80,7 +95,11 @@ class ChannelListItemResponse(ChannelModel):
@router.get("/", response_model=list[ChannelListItemResponse])
-async def get_channels(request: Request, user=Depends(get_verified_user)):
+async def get_channels(
+ request: Request,
+ user=Depends(get_verified_user),
+):
+ check_channels_access(request)
if user.role != "admin" and not has_permission(
user.id, "features.channels", request.app.state.config.USER_PERMISSIONS
):
@@ -132,7 +151,11 @@ async def get_channels(request: Request, user=Depends(get_verified_user)):
@router.get("/list", response_model=list[ChannelModel])
-async def get_all_channels(user=Depends(get_verified_user)):
+async def get_all_channels(
+ request: Request,
+ user=Depends(get_verified_user),
+):
+ check_channels_access(request)
if user.role == "admin":
return Channels.get_channels()
return Channels.get_channels_by_user_id(user.id)
@@ -145,8 +168,11 @@ async def get_all_channels(user=Depends(get_verified_user)):
@router.get("/users/{user_id}", response_model=Optional[ChannelModel])
async def get_dm_channel_by_user_id(
- request: Request, user_id: str, user=Depends(get_verified_user)
+ request: Request,
+ user_id: str,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
if user.role != "admin" and not has_permission(
user.id, "features.channels", request.app.state.config.USER_PERMISSIONS
):
@@ -214,8 +240,11 @@ async def get_dm_channel_by_user_id(
@router.post("/create", response_model=Optional[ChannelModel])
async def create_new_channel(
- request: Request, form_data: CreateChannelForm, user=Depends(get_verified_user)
+ request: Request,
+ form_data: CreateChannelForm,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
if user.role != "admin" and not has_permission(
user.id, "features.channels", request.app.state.config.USER_PERMISSIONS
):
@@ -294,7 +323,12 @@ class ChannelFullResponse(ChannelResponse):
@router.get("/{id}", response_model=Optional[ChannelFullResponse])
-async def get_channel_by_id(id: str, user=Depends(get_verified_user)):
+async def get_channel_by_id(
+ request: Request,
+ id: str,
+ user=Depends(get_verified_user),
+):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -381,6 +415,7 @@ PAGE_ITEM_COUNT = 30
@router.get("/{id}/members", response_model=UserListResponse)
async def get_channel_members_by_id(
+ request: Request,
id: str,
query: Optional[str] = None,
order_by: Optional[str] = None,
@@ -388,6 +423,7 @@ async def get_channel_members_by_id(
page: Optional[int] = 1,
user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
@@ -470,10 +506,12 @@ class UpdateActiveMemberForm(BaseModel):
@router.post("/{id}/members/active", response_model=bool)
async def update_is_active_member_by_id_and_user_id(
+ request: Request,
id: str,
form_data: UpdateActiveMemberForm,
user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -506,6 +544,7 @@ async def add_members_by_id(
form_data: UpdateMembersForm,
user=Depends(get_verified_user),
):
+ check_channels_access(request)
if user.role != "admin" and not has_permission(
user.id, "features.channels", request.app.state.config.USER_PERMISSIONS
):
@@ -554,6 +593,7 @@ async def remove_members_by_id(
form_data: RemoveMembersForm,
user=Depends(get_verified_user),
):
+ check_channels_access(request)
if user.role != "admin" and not has_permission(
user.id, "features.channels", request.app.state.config.USER_PERMISSIONS
):
@@ -591,8 +631,12 @@ async def remove_members_by_id(
@router.post("/{id}/update", response_model=Optional[ChannelModel])
async def update_channel_by_id(
- request: Request, id: str, form_data: ChannelForm, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ form_data: ChannelForm,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
if user.role != "admin" and not has_permission(
user.id, "features.channels", request.app.state.config.USER_PERMISSIONS
):
@@ -629,8 +673,11 @@ async def update_channel_by_id(
@router.delete("/{id}/delete", response_model=bool)
async def delete_channel_by_id(
- request: Request, id: str, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
if user.role != "admin" and not has_permission(
user.id, "features.channels", request.app.state.config.USER_PERMISSIONS
):
@@ -666,13 +713,27 @@ async def delete_channel_by_id(
class MessageUserResponse(MessageResponse):
- pass
+ data: bool | None = None
+
+ @field_validator("data", mode="before")
+ def convert_data_to_bool(cls, v):
+ # No data or not a dict → False
+ if not isinstance(v, dict):
+ return False
+
+ # True if ANY value in the dict is non-empty
+ return any(bool(val) for val in v.values())
@router.get("/{id}/messages", response_model=list[MessageUserResponse])
async def get_channel_messages(
- id: str, skip: int = 0, limit: int = 50, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ skip: int = 0,
+ limit: int = 50,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -734,8 +795,12 @@ PAGE_ITEM_COUNT_PINNED = 20
@router.get("/{id}/messages/pinned", response_model=list[MessageWithReactionsResponse])
async def get_pinned_channel_messages(
- id: str, page: int = 1, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ page: int = 1,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -906,6 +971,10 @@ async def model_response_handler(request, channel, message, user):
for file in thread_message_files:
if file.get("type", "") == "image":
images.append(file.get("url", ""))
+ elif file.get("content_type", "").startswith("image/"):
+ image = get_image_base64_from_file_id(file.get("id", ""))
+ if image:
+ images.append(image)
thread_history_string = "\n\n".join(thread_history)
system_message = {
@@ -1075,9 +1144,19 @@ async def post_new_message(
background_tasks: BackgroundTasks,
user=Depends(get_verified_user),
):
+ check_channels_access(request)
try:
message, channel = await new_message_handler(request, id, form_data, user)
+ try:
+ if files := message.data.get("files", []):
+ for file in files:
+ Channels.set_file_message_id_in_channel_by_id(
+ channel.id, file.get("id", ""), message.id
+ )
+ except Exception as e:
+ log.debug(e)
+
active_user_ids = get_user_ids_from_room(f"channel:{channel.id}")
async def background_handler():
@@ -1108,10 +1187,14 @@ async def post_new_message(
############################
-@router.get("/{id}/messages/{message_id}", response_model=Optional[MessageUserResponse])
+@router.get("/{id}/messages/{message_id}", response_model=Optional[MessageResponse])
async def get_channel_message(
- id: str, message_id: str, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ message_id: str,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -1142,7 +1225,7 @@ async def get_channel_message(
status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
)
- return MessageUserResponse(
+ return MessageResponse(
**{
**message.model_dump(),
"user": UserNameResponse(
@@ -1152,6 +1235,52 @@ async def get_channel_message(
)
+############################
+# GetChannelMessageData
+############################
+
+
+@router.get("/{id}/messages/{message_id}/data", response_model=Optional[dict])
+async def get_channel_message_data(
+ request: Request,
+ id: str,
+ message_id: str,
+ user=Depends(get_verified_user),
+):
+ check_channels_access(request)
+ channel = Channels.get_channel_by_id(id)
+ if not channel:
+ raise HTTPException(
+ status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND
+ )
+
+ if channel.type in ["group", "dm"]:
+ if not Channels.is_user_channel_member(channel.id, user.id):
+ raise HTTPException(
+ status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
+ )
+ else:
+ if user.role != "admin" and not has_access(
+ user.id, type="read", access_control=channel.access_control
+ ):
+ raise HTTPException(
+ status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
+ )
+
+ message = Messages.get_message_by_id(message_id)
+ if not message:
+ raise HTTPException(
+ status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND
+ )
+
+ if message.channel_id != id:
+ raise HTTPException(
+ status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+ )
+
+ return message.data
+
+
############################
# PinChannelMessage
############################
@@ -1165,8 +1294,13 @@ class PinMessageForm(BaseModel):
"/{id}/messages/{message_id}/pin", response_model=Optional[MessageUserResponse]
)
async def pin_channel_message(
- id: str, message_id: str, form_data: PinMessageForm, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ message_id: str,
+ form_data: PinMessageForm,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -1224,12 +1358,14 @@ async def pin_channel_message(
"/{id}/messages/{message_id}/thread", response_model=list[MessageUserResponse]
)
async def get_channel_thread_messages(
+ request: Request,
id: str,
message_id: str,
skip: int = 0,
limit: int = 50,
user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -1282,8 +1418,13 @@ async def get_channel_thread_messages(
"/{id}/messages/{message_id}/update", response_model=Optional[MessageModel]
)
async def update_message_by_id(
- id: str, message_id: str, form_data: MessageForm, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ message_id: str,
+ form_data: MessageForm,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -1357,8 +1498,13 @@ class ReactionForm(BaseModel):
@router.post("/{id}/messages/{message_id}/reactions/add", response_model=bool)
async def add_reaction_to_message(
- id: str, message_id: str, form_data: ReactionForm, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ message_id: str,
+ form_data: ReactionForm,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -1426,8 +1572,13 @@ async def add_reaction_to_message(
@router.post("/{id}/messages/{message_id}/reactions/remove", response_model=bool)
async def remove_reaction_by_id_and_user_id_and_name(
- id: str, message_id: str, form_data: ReactionForm, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ message_id: str,
+ form_data: ReactionForm,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
@@ -1498,8 +1649,12 @@ async def remove_reaction_by_id_and_user_id_and_name(
@router.delete("/{id}/messages/{message_id}/delete", response_model=bool)
async def delete_message_by_id(
- id: str, message_id: str, user=Depends(get_verified_user)
+ request: Request,
+ id: str,
+ message_id: str,
+ user=Depends(get_verified_user),
):
+ check_channels_access(request)
channel = Channels.get_channel_by_id(id)
if not channel:
raise HTTPException(
diff --git a/backend/open_webui/routers/chats.py b/backend/open_webui/routers/chats.py
index 78cd8bdb1a..8dde946a4d 100644
--- a/backend/open_webui/routers/chats.py
+++ b/backend/open_webui/routers/chats.py
@@ -3,10 +3,12 @@ import logging
from typing import Optional
+from open_webui.utils.misc import get_message_list
from open_webui.socket.main import get_event_emitter
from open_webui.models.chats import (
ChatForm,
ChatImportForm,
+ ChatUsageStatsListResponse,
ChatsImportForm,
ChatResponse,
Chats,
@@ -17,7 +19,6 @@ from open_webui.models.folders import Folders
from open_webui.config import ENABLE_ADMIN_CHAT_ACCESS, ENABLE_ADMIN_EXPORT
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
from fastapi import APIRouter, Depends, HTTPException, Request, status
from pydantic import BaseModel
@@ -26,7 +27,6 @@ from open_webui.utils.auth import get_admin_user, get_verified_user
from open_webui.utils.access_control import has_permission
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
@@ -66,6 +66,132 @@ def get_session_user_chat_list(
)
+############################
+# GetChatUsageStats
+# EXPERIMENTAL: may be removed in future releases
+############################
+
+
+@router.get("/stats/usage", response_model=ChatUsageStatsListResponse)
+def get_session_user_chat_usage_stats(
+ items_per_page: Optional[int] = 50,
+ page: Optional[int] = 1,
+ user=Depends(get_verified_user),
+):
+ try:
+ limit = items_per_page
+ skip = (page - 1) * limit
+
+ result = Chats.get_chats_by_user_id(user.id, skip=skip, limit=limit)
+
+ chats = result.items
+ total = result.total
+
+ chat_stats = []
+ for chat in chats:
+ messages_map = chat.chat.get("history", {}).get("messages", {})
+ message_id = chat.chat.get("history", {}).get("currentId")
+
+ if messages_map and message_id:
+ try:
+ history_models = {}
+ history_message_count = len(messages_map)
+ history_user_messages = []
+ history_assistant_messages = []
+
+ for message in messages_map.values():
+ if message.get("role", "") == "user":
+ history_user_messages.append(message)
+ elif message.get("role", "") == "assistant":
+ history_assistant_messages.append(message)
+ model = message.get("model", None)
+ if model:
+ if model not in history_models:
+ history_models[model] = 0
+ history_models[model] += 1
+
+ average_user_message_content_length = (
+ sum(
+ len(message.get("content", ""))
+ for message in history_user_messages
+ )
+ / len(history_user_messages)
+ if len(history_user_messages) > 0
+ else 0
+ )
+ average_assistant_message_content_length = (
+ sum(
+ len(message.get("content", ""))
+ for message in history_assistant_messages
+ )
+ / len(history_assistant_messages)
+ if len(history_assistant_messages) > 0
+ else 0
+ )
+
+ response_times = []
+ for message in history_assistant_messages:
+ user_message_id = message.get("parentId", None)
+ if user_message_id and user_message_id in messages_map:
+ user_message = messages_map[user_message_id]
+ response_time = message.get(
+ "timestamp", 0
+ ) - user_message.get("timestamp", 0)
+
+ response_times.append(response_time)
+
+ average_response_time = (
+ sum(response_times) / len(response_times)
+ if len(response_times) > 0
+ else 0
+ )
+
+ message_list = get_message_list(messages_map, message_id)
+ message_count = len(message_list)
+
+ models = {}
+ for message in reversed(message_list):
+ if message.get("role") == "assistant":
+ model = message.get("model", None)
+ if model:
+ if model not in models:
+ models[model] = 0
+ models[model] += 1
+
+ annotation = message.get("annotation", {})
+
+ chat_stats.append(
+ {
+ "id": chat.id,
+ "models": models,
+ "message_count": message_count,
+ "history_models": history_models,
+ "history_message_count": history_message_count,
+ "history_user_message_count": len(history_user_messages),
+ "history_assistant_message_count": len(
+ history_assistant_messages
+ ),
+ "average_response_time": average_response_time,
+ "average_user_message_content_length": average_user_message_content_length,
+ "average_assistant_message_content_length": average_assistant_message_content_length,
+ "tags": chat.meta.get("tags", []),
+ "last_message_at": message_list[-1].get("timestamp", None),
+ "updated_at": chat.updated_at,
+ "created_at": chat.created_at,
+ }
+ )
+ except Exception as e:
+ pass
+
+ return ChatUsageStatsListResponse(items=chat_stats, total=total)
+
+ except Exception as e:
+ log.exception(e)
+ raise HTTPException(
+ status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+ )
+
+
############################
# DeleteAllChats
############################
diff --git a/backend/open_webui/routers/configs.py b/backend/open_webui/routers/configs.py
index 0eb88e767e..3ac9949eb3 100644
--- a/backend/open_webui/routers/configs.py
+++ b/backend/open_webui/routers/configs.py
@@ -18,7 +18,6 @@ from open_webui.utils.tools import (
from open_webui.utils.mcp.client import MCPClient
from open_webui.models.oauth_sessions import OAuthSessions
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.utils.oauth import (
get_discovery_urls,
@@ -32,7 +31,6 @@ from mcp.shared.auth import OAuthMetadata
router = APIRouter()
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
############################
diff --git a/backend/open_webui/routers/evaluations.py b/backend/open_webui/routers/evaluations.py
index 3e5e14801c..cdcefe6ba7 100644
--- a/backend/open_webui/routers/evaluations.py
+++ b/backend/open_webui/routers/evaluations.py
@@ -4,6 +4,7 @@ from pydantic import BaseModel
from open_webui.models.users import Users, UserModel
from open_webui.models.feedbacks import (
+ FeedbackIdResponse,
FeedbackModel,
FeedbackResponse,
FeedbackForm,
@@ -64,6 +65,12 @@ async def get_all_feedbacks(user=Depends(get_admin_user)):
return feedbacks
+@router.get("/feedbacks/all/ids", response_model=list[FeedbackIdResponse])
+async def get_all_feedback_ids(user=Depends(get_admin_user)):
+ feedbacks = Feedbacks.get_all_feedbacks()
+ return feedbacks
+
+
@router.delete("/feedbacks/all")
async def delete_all_feedbacks(user=Depends(get_admin_user)):
success = Feedbacks.delete_all_feedbacks()
@@ -71,7 +78,7 @@ async def delete_all_feedbacks(user=Depends(get_admin_user)):
@router.get("/feedbacks/all/export", response_model=list[FeedbackModel])
-async def get_all_feedbacks(user=Depends(get_admin_user)):
+async def export_all_feedbacks(user=Depends(get_admin_user)):
feedbacks = Feedbacks.get_all_feedbacks()
return feedbacks
diff --git a/backend/open_webui/routers/files.py b/backend/open_webui/routers/files.py
index 8af921bc7a..723a150197 100644
--- a/backend/open_webui/routers/files.py
+++ b/backend/open_webui/routers/files.py
@@ -24,9 +24,9 @@ from fastapi import (
from fastapi.responses import FileResponse, StreamingResponse
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
+from open_webui.models.channels import Channels
from open_webui.models.users import Users
from open_webui.models.files import (
FileForm,
@@ -34,11 +34,11 @@ from open_webui.models.files import (
FileModelResponse,
Files,
)
+from open_webui.models.chats import Chats
from open_webui.models.knowledge import Knowledges
from open_webui.models.groups import Groups
-from open_webui.routers.knowledge import get_knowledge, get_knowledge_list
from open_webui.routers.retrieval import ProcessFileForm, process_file
from open_webui.routers.audio import transcribe
@@ -47,11 +47,10 @@ from open_webui.storage.provider import Storage
from open_webui.utils.auth import get_admin_user, get_verified_user
from open_webui.utils.access_control import has_access
-
+from open_webui.utils.misc import strict_match_mime_type
from pydantic import BaseModel
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
@@ -73,9 +72,9 @@ def has_access_to_file(
detail=ERROR_MESSAGES.NOT_FOUND,
)
+ # Check if the file is associated with any knowledge bases the user has access to
knowledge_bases = Knowledges.get_knowledges_by_file_id(file_id)
user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user.id)}
-
for knowledge_base in knowledge_bases:
if knowledge_base.user_id == user.id or has_access(
user.id, access_type, knowledge_base.access_control, user_group_ids
@@ -91,6 +90,17 @@ def has_access_to_file(
if knowledge_base.id == knowledge_base_id:
return True
+ # Check if the file is associated with any channels the user has access to
+ channels = Channels.get_channels_by_file_id_and_user_id(file_id, user.id)
+ if access_type == "read" and channels:
+ return True
+
+ # Check if the file is associated with any chats the user has access to
+ # TODO: Granular access control for chats
+ chats = Chats.get_shared_chats_by_file_id(file_id)
+ if chats:
+ return True
+
return False
@@ -104,17 +114,9 @@ def process_uploaded_file(request, file, file_path, file_item, file_metadata, us
if file.content_type:
stt_supported_content_types = getattr(
request.app.state.config, "STT_SUPPORTED_CONTENT_TYPES", []
- )
+ ) or ["audio/*", "video/webm"]
- if any(
- fnmatch(file.content_type, content_type)
- for content_type in (
- stt_supported_content_types
- if stt_supported_content_types
- and any(t.strip() for t in stt_supported_content_types)
- else ["audio/*", "video/webm"]
- )
- ):
+ if strict_match_mime_type(stt_supported_content_types, file.content_type):
file_path = Storage.get_file(file_path)
result = transcribe(request, file_path, file_metadata, user)
@@ -138,6 +140,7 @@ def process_uploaded_file(request, file, file_path, file_item, file_metadata, us
f"File type {file.content_type} is not provided, but trying to process anyway"
)
process_file(request, ProcessFileForm(file_id=file_item.id), user=user)
+
except Exception as e:
log.error(f"Error processing file: {file_item.id}")
Files.update_file_data_by_id(
@@ -179,7 +182,7 @@ def upload_file_handler(
user=Depends(get_verified_user),
background_tasks: Optional[BackgroundTasks] = None,
):
- log.info(f"file.content_type: {file.content_type}")
+ log.info(f"file.content_type: {file.content_type} {process}")
if isinstance(metadata, str):
try:
@@ -247,6 +250,13 @@ def upload_file_handler(
),
)
+ if "channel_id" in file_metadata:
+ channel = Channels.get_channel_by_id_and_user_id(
+ file_metadata["channel_id"], user.id
+ )
+ if channel:
+ Channels.add_file_to_channel_by_id(channel.id, file_item.id, user.id)
+
if process:
if background_tasks and process_in_background:
background_tasks.add_task(
diff --git a/backend/open_webui/routers/folders.py b/backend/open_webui/routers/folders.py
index fe2bf367bf..32911fa509 100644
--- a/backend/open_webui/routers/folders.py
+++ b/backend/open_webui/routers/folders.py
@@ -21,7 +21,6 @@ from open_webui.models.knowledge import Knowledges
from open_webui.config import UPLOAD_DIR
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.constants import ERROR_MESSAGES
@@ -34,7 +33,6 @@ from open_webui.utils.access_control import has_permission
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
diff --git a/backend/open_webui/routers/functions.py b/backend/open_webui/routers/functions.py
index c8f131553c..82321cb546 100644
--- a/backend/open_webui/routers/functions.py
+++ b/backend/open_webui/routers/functions.py
@@ -23,12 +23,10 @@ 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
from pydantic import BaseModel, HttpUrl
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
router = APIRouter()
diff --git a/backend/open_webui/routers/groups.py b/backend/open_webui/routers/groups.py
index 7d2efcf899..423f6b1c67 100755
--- a/backend/open_webui/routers/groups.py
+++ b/backend/open_webui/routers/groups.py
@@ -17,11 +17,9 @@ 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()
diff --git a/backend/open_webui/routers/images.py b/backend/open_webui/routers/images.py
index 8aabf0f73b..91bc3f2d40 100644
--- a/backend/open_webui/routers/images.py
+++ b/backend/open_webui/routers/images.py
@@ -16,7 +16,9 @@ from fastapi.responses import FileResponse
from open_webui.config import CACHE_DIR
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, SRC_LOG_LEVELS
+from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS
+
+from open_webui.models.chats import Chats
from open_webui.routers.files import upload_file_handler, get_file_content_by_id
from open_webui.utils.auth import get_admin_user, get_verified_user
from open_webui.utils.headers import include_user_info_headers
@@ -31,7 +33,6 @@ from open_webui.utils.images.comfyui import (
from pydantic import BaseModel
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["IMAGES"])
IMAGE_CACHE_DIR = CACHE_DIR / "image" / "generations"
IMAGE_CACHE_DIR.mkdir(parents=True, exist_ok=True)
@@ -196,12 +197,12 @@ async def update_config(
set_image_model(request, form_data.IMAGE_GENERATION_MODEL)
if (
form_data.IMAGE_SIZE == "auto"
- and form_data.IMAGE_GENERATION_MODEL != "gpt-image-1"
+ and not form_data.IMAGE_GENERATION_MODEL.startswith("gpt-image")
):
raise HTTPException(
status_code=400,
detail=ERROR_MESSAGES.INCORRECT_FORMAT(
- " (auto is only allowed with gpt-image-1)."
+ " (auto is only allowed with gpt-image models)."
),
)
@@ -380,6 +381,7 @@ 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"},
{"id": "gpt-image-1", "name": "GPT-IMAGE 1"},
+ {"id": "gpt-image-1.5", "name": "GPT-IMAGE 1.5"},
]
elif request.app.state.config.IMAGE_GENERATION_ENGINE == "gemini":
return [
@@ -510,14 +512,29 @@ def upload_image(request, image_data, content_type, metadata, user):
process=False,
user=user,
)
+
+ if file_item and file_item.id:
+ # If chat_id and message_id are provided in metadata, link the file to the chat message
+ chat_id = metadata.get("chat_id")
+ message_id = metadata.get("message_id")
+
+ if chat_id and message_id:
+ Chats.insert_chat_files(
+ chat_id=chat_id,
+ message_id=message_id,
+ file_ids=[file_item.id],
+ user_id=user.id,
+ )
+
url = request.app.url_path_for("get_file_content_by_id", id=file_item.id)
- return url
+ return file_item, url
@router.post("/generations")
async def image_generations(
request: Request,
form_data: CreateImageForm,
+ metadata: Optional[dict] = None,
user=Depends(get_verified_user),
):
# if IMAGE_SIZE = 'auto', default WidthxHeight to the 512x512 default
@@ -535,6 +552,9 @@ async def image_generations(
size = form_data.size
width, height = tuple(map(int, size.split("x")))
+
+ metadata = metadata or {}
+
model = get_image_model(request)
r = None
@@ -564,7 +584,9 @@ async def image_generations(
),
**(
{}
- if "gpt-image-1" in request.app.state.config.IMAGE_GENERATION_MODEL
+ if request.app.state.config.IMAGE_GENERATION_MODEL.startswith(
+ "gpt-image"
+ )
else {"response_format": "b64_json"}
),
**(
@@ -593,7 +615,9 @@ async def image_generations(
else:
image_data, content_type = get_image_data(image["b64_json"])
- url = upload_image(request, image_data, content_type, data, user)
+ _, url = upload_image(
+ request, image_data, content_type, {**data, **metadata}, user
+ )
images.append({"url": url})
return images
@@ -643,7 +667,9 @@ async def image_generations(
image_data, content_type = get_image_data(
image["bytesBase64Encoded"]
)
- url = upload_image(request, image_data, content_type, data, user)
+ _, url = upload_image(
+ request, image_data, content_type, {**data, **metadata}, user
+ )
images.append({"url": url})
elif model.endswith(":generateContent"):
for image in res["candidates"]:
@@ -652,8 +678,12 @@ async def image_generations(
image_data, content_type = get_image_data(
part["inlineData"]["data"]
)
- url = upload_image(
- request, image_data, content_type, data, user
+ _, url = upload_image(
+ request,
+ image_data,
+ content_type,
+ {**data, **metadata},
+ user,
)
images.append({"url": url})
@@ -703,11 +733,11 @@ async def image_generations(
}
image_data, content_type = get_image_data(image["url"], headers)
- url = upload_image(
+ _, url = upload_image(
request,
image_data,
content_type,
- form_data.model_dump(exclude_none=True),
+ {**form_data.model_dump(exclude_none=True), **metadata},
user,
)
images.append({"url": url})
@@ -750,11 +780,11 @@ async def image_generations(
for image in res["images"]:
image_data, content_type = get_image_data(image)
- url = upload_image(
+ _, url = upload_image(
request,
image_data,
content_type,
- {**data, "info": res["info"]},
+ {**data, "info": res["info"], **metadata},
user,
)
images.append({"url": url})
@@ -781,10 +811,13 @@ class EditImageForm(BaseModel):
async def image_edits(
request: Request,
form_data: EditImageForm,
+ metadata: Optional[dict] = None,
user=Depends(get_verified_user),
):
size = None
width, height = None, None
+ metadata = metadata or {}
+
if (
request.app.state.config.IMAGE_EDIT_SIZE
and "x" in request.app.state.config.IMAGE_EDIT_SIZE
@@ -867,7 +900,7 @@ async def image_edits(
**({"size": size} if size else {}),
**(
{}
- if "gpt-image-1" in request.app.state.config.IMAGE_EDIT_MODEL
+ if request.app.state.config.IMAGE_EDIT_MODEL.startswith("gpt-image")
else {"response_format": "b64_json"}
),
}
@@ -902,7 +935,9 @@ async def image_edits(
else:
image_data, content_type = get_image_data(image["b64_json"])
- url = upload_image(request, image_data, content_type, data, user)
+ _, url = upload_image(
+ request, image_data, content_type, {**data, **metadata}, user
+ )
images.append({"url": url})
return images
@@ -955,8 +990,12 @@ async def image_edits(
image_data, content_type = get_image_data(
part["inlineData"]["data"]
)
- url = upload_image(
- request, image_data, content_type, data, user
+ _, url = upload_image(
+ request,
+ image_data,
+ content_type,
+ {**data, **metadata},
+ user,
)
images.append({"url": url})
@@ -1033,11 +1072,11 @@ async def image_edits(
}
image_data, content_type = get_image_data(image_url, headers)
- url = upload_image(
+ _, url = upload_image(
request,
image_data,
content_type,
- form_data.model_dump(exclude_none=True),
+ {**form_data.model_dump(exclude_none=True), **metadata},
user,
)
images.append({"url": url})
diff --git a/backend/open_webui/routers/knowledge.py b/backend/open_webui/routers/knowledge.py
index 3bfc961ac3..467f6f3896 100644
--- a/backend/open_webui/routers/knowledge.py
+++ b/backend/open_webui/routers/knowledge.py
@@ -4,7 +4,9 @@ from fastapi import APIRouter, Depends, HTTPException, status, Request, Query
from fastapi.concurrency import run_in_threadpool
import logging
+from open_webui.models.groups import Groups
from open_webui.models.knowledge import (
+ KnowledgeFileListResponse,
Knowledges,
KnowledgeForm,
KnowledgeResponse,
@@ -25,13 +27,11 @@ from open_webui.utils.auth import get_verified_user
from open_webui.utils.access_control import has_access, has_permission
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.config import BYPASS_ADMIN_ACCESS_CONTROL
from open_webui.models.models import Models, ModelForm
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
@@ -39,41 +39,115 @@ router = APIRouter()
# getKnowledgeBases
############################
-
-@router.get("/", response_model=list[KnowledgeUserResponse])
-async def get_knowledge(user=Depends(get_verified_user)):
- # Return knowledge bases with read access
- knowledge_bases = []
- if user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL:
- knowledge_bases = Knowledges.get_knowledge_bases()
- else:
- knowledge_bases = Knowledges.get_knowledge_bases_by_user_id(user.id, "read")
-
- return [
- KnowledgeUserResponse(
- **knowledge_base.model_dump(),
- files=Knowledges.get_file_metadatas_by_id(knowledge_base.id),
- )
- for knowledge_base in knowledge_bases
- ]
+PAGE_ITEM_COUNT = 30
-@router.get("/list", response_model=list[KnowledgeUserResponse])
-async def get_knowledge_list(user=Depends(get_verified_user)):
- # Return knowledge bases with write access
- knowledge_bases = []
- if user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL:
- knowledge_bases = Knowledges.get_knowledge_bases()
- else:
- knowledge_bases = Knowledges.get_knowledge_bases_by_user_id(user.id, "write")
+class KnowledgeAccessResponse(KnowledgeUserResponse):
+ write_access: Optional[bool] = False
- return [
- KnowledgeUserResponse(
- **knowledge_base.model_dump(),
- files=Knowledges.get_file_metadatas_by_id(knowledge_base.id),
- )
- for knowledge_base in knowledge_bases
- ]
+
+class KnowledgeAccessListResponse(BaseModel):
+ items: list[KnowledgeAccessResponse]
+ total: int
+
+
+@router.get("/", response_model=KnowledgeAccessListResponse)
+async def get_knowledge_bases(page: Optional[int] = 1, user=Depends(get_verified_user)):
+ page = max(page, 1)
+ limit = PAGE_ITEM_COUNT
+ skip = (page - 1) * limit
+
+ filter = {}
+ if not user.role == "admin" or not BYPASS_ADMIN_ACCESS_CONTROL:
+ groups = Groups.get_groups_by_member_id(user.id)
+ if groups:
+ filter["group_ids"] = [group.id for group in groups]
+
+ filter["user_id"] = user.id
+
+ result = Knowledges.search_knowledge_bases(
+ user.id, filter=filter, skip=skip, limit=limit
+ )
+
+ return KnowledgeAccessListResponse(
+ items=[
+ KnowledgeAccessResponse(
+ **knowledge_base.model_dump(),
+ write_access=(
+ user.id == knowledge_base.user_id
+ or has_access(user.id, "write", knowledge_base.access_control)
+ ),
+ )
+ for knowledge_base in result.items
+ ],
+ total=result.total,
+ )
+
+
+@router.get("/search", response_model=KnowledgeAccessListResponse)
+async def search_knowledge_bases(
+ query: Optional[str] = None,
+ view_option: Optional[str] = None,
+ page: Optional[int] = 1,
+ user=Depends(get_verified_user),
+):
+ page = max(page, 1)
+ limit = PAGE_ITEM_COUNT
+ skip = (page - 1) * limit
+
+ filter = {}
+ if query:
+ filter["query"] = query
+ if view_option:
+ filter["view_option"] = view_option
+
+ if not user.role == "admin" or not BYPASS_ADMIN_ACCESS_CONTROL:
+ groups = Groups.get_groups_by_member_id(user.id)
+ if groups:
+ filter["group_ids"] = [group.id for group in groups]
+
+ filter["user_id"] = user.id
+
+ result = Knowledges.search_knowledge_bases(
+ user.id, filter=filter, skip=skip, limit=limit
+ )
+
+ return KnowledgeAccessListResponse(
+ items=[
+ KnowledgeAccessResponse(
+ **knowledge_base.model_dump(),
+ write_access=(
+ user.id == knowledge_base.user_id
+ or has_access(user.id, "write", knowledge_base.access_control)
+ ),
+ )
+ for knowledge_base in result.items
+ ],
+ total=result.total,
+ )
+
+
+@router.get("/search/files", response_model=KnowledgeFileListResponse)
+async def search_knowledge_files(
+ query: Optional[str] = None,
+ page: Optional[int] = 1,
+ user=Depends(get_verified_user),
+):
+ page = max(page, 1)
+ limit = PAGE_ITEM_COUNT
+ skip = (page - 1) * limit
+
+ filter = {}
+ if query:
+ filter["query"] = query
+
+ groups = Groups.get_groups_by_member_id(user.id)
+ if groups:
+ filter["group_ids"] = [group.id for group in groups]
+
+ filter["user_id"] = user.id
+
+ return Knowledges.search_knowledge_files(filter=filter, skip=skip, limit=limit)
############################
@@ -185,7 +259,8 @@ async def reindex_knowledge_files(request: Request, user=Depends(get_verified_us
class KnowledgeFilesResponse(KnowledgeResponse):
- files: list[FileMetadataResponse]
+ files: Optional[list[FileMetadataResponse]] = None
+ write_access: Optional[bool] = False
@router.get("/{id}", response_model=Optional[KnowledgeFilesResponse])
@@ -201,7 +276,10 @@ async def get_knowledge_by_id(id: str, user=Depends(get_verified_user)):
return KnowledgeFilesResponse(
**knowledge.model_dump(),
- files=Knowledges.get_file_metadatas_by_id(knowledge.id),
+ write_access=(
+ user.id == knowledge.user_id
+ or has_access(user.id, "write", knowledge.access_control)
+ ),
)
else:
raise HTTPException(
@@ -264,6 +342,59 @@ async def update_knowledge_by_id(
)
+############################
+# GetKnowledgeFilesById
+############################
+
+
+@router.get("/{id}/files", response_model=KnowledgeFileListResponse)
+async def get_knowledge_files_by_id(
+ id: str,
+ query: Optional[str] = None,
+ view_option: Optional[str] = None,
+ order_by: Optional[str] = None,
+ direction: Optional[str] = None,
+ page: Optional[int] = 1,
+ user=Depends(get_verified_user),
+):
+
+ knowledge = Knowledges.get_knowledge_by_id(id=id)
+ if not knowledge:
+ raise HTTPException(
+ status_code=status.HTTP_400_BAD_REQUEST,
+ detail=ERROR_MESSAGES.NOT_FOUND,
+ )
+
+ if not (
+ user.role == "admin"
+ or knowledge.user_id == user.id
+ or has_access(user.id, "read", knowledge.access_control)
+ ):
+ raise HTTPException(
+ status_code=status.HTTP_400_BAD_REQUEST,
+ detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+ )
+
+ page = max(page, 1)
+
+ limit = 30
+ skip = (page - 1) * limit
+
+ filter = {}
+ if query:
+ filter["query"] = query
+ if view_option:
+ filter["view_option"] = view_option
+ if order_by:
+ filter["order_by"] = order_by
+ if direction:
+ filter["direction"] = direction
+
+ return Knowledges.search_files_by_id(
+ id, user.id, filter=filter, skip=skip, limit=limit
+ )
+
+
############################
# AddFileToKnowledge
############################
@@ -309,11 +440,6 @@ def add_file_to_knowledge_by_id(
detail=ERROR_MESSAGES.FILE_NOT_PROCESSED,
)
- # Add file to knowledge base
- Knowledges.add_file_to_knowledge_by_id(
- knowledge_id=id, file_id=form_data.file_id, user_id=user.id
- )
-
# Add content to the vector database
try:
process_file(
@@ -321,6 +447,11 @@ def add_file_to_knowledge_by_id(
ProcessFileForm(file_id=form_data.file_id, collection_name=id),
user=user,
)
+
+ # Add file to knowledge base
+ Knowledges.add_file_to_knowledge_by_id(
+ knowledge_id=id, file_id=form_data.file_id, user_id=user.id
+ )
except Exception as e:
log.debug(e)
raise HTTPException(
diff --git a/backend/open_webui/routers/memories.py b/backend/open_webui/routers/memories.py
index 8e45a14dfb..9bb1ef518d 100644
--- a/backend/open_webui/routers/memories.py
+++ b/backend/open_webui/routers/memories.py
@@ -7,11 +7,9 @@ from typing import Optional
from open_webui.models.memories import Memories, MemoryModel
from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
from open_webui.utils.auth import get_verified_user
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
diff --git a/backend/open_webui/routers/models.py b/backend/open_webui/routers/models.py
index df5a7377dc..4475b2d78e 100644
--- a/backend/open_webui/routers/models.py
+++ b/backend/open_webui/routers/models.py
@@ -291,12 +291,15 @@ async def get_model_by_id(id: str, user=Depends(get_verified_user)):
@router.get("/model/profile/image")
async def get_model_profile_image(id: str, user=Depends(get_verified_user)):
model = Models.get_model_by_id(id)
+ # Cache-control headers to prevent stale cached images
+ cache_headers = {"Cache-Control": "no-cache, must-revalidate"}
+
if model:
if model.meta.profile_image_url:
if model.meta.profile_image_url.startswith("http"):
return Response(
status_code=status.HTTP_302_FOUND,
- headers={"Location": model.meta.profile_image_url},
+ headers={"Location": model.meta.profile_image_url, **cache_headers},
)
elif model.meta.profile_image_url.startswith("data:image"):
try:
@@ -307,14 +310,17 @@ async def get_model_profile_image(id: str, user=Depends(get_verified_user)):
return StreamingResponse(
image_buffer,
media_type="image/png",
- headers={"Content-Disposition": "inline; filename=image.png"},
+ headers={
+ "Content-Disposition": "inline; filename=image.png",
+ **cache_headers,
+ },
)
except Exception as e:
pass
- return FileResponse(f"{STATIC_DIR}/favicon.png")
+ return FileResponse(f"{STATIC_DIR}/favicon.png", headers=cache_headers)
else:
- return FileResponse(f"{STATIC_DIR}/favicon.png")
+ return FileResponse(f"{STATIC_DIR}/favicon.png", headers=cache_headers)
############################
diff --git a/backend/open_webui/routers/notes.py b/backend/open_webui/routers/notes.py
index 3858c4670f..ee0e46da29 100644
--- a/backend/open_webui/routers/notes.py
+++ b/backend/open_webui/routers/notes.py
@@ -8,20 +8,28 @@ from pydantic import BaseModel
from open_webui.socket.main import sio
-
+from open_webui.models.groups import Groups
from open_webui.models.users import Users, UserResponse
-from open_webui.models.notes import Notes, NoteModel, NoteForm, NoteUserResponse
+from open_webui.models.notes import (
+ NoteListResponse,
+ Notes,
+ NoteModel,
+ NoteForm,
+ NoteUserResponse,
+)
-from open_webui.config import ENABLE_ADMIN_CHAT_ACCESS, ENABLE_ADMIN_EXPORT
+from open_webui.config import (
+ BYPASS_ADMIN_ACCESS_CONTROL,
+ ENABLE_ADMIN_CHAT_ACCESS,
+ ENABLE_ADMIN_EXPORT,
+)
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.utils.auth import get_admin_user, get_verified_user
from open_webui.utils.access_control import has_access, has_permission
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
@@ -30,39 +38,17 @@ router = APIRouter()
############################
-@router.get("/", response_model=list[NoteUserResponse])
-async def get_notes(request: Request, user=Depends(get_verified_user)):
-
- if user.role != "admin" and not has_permission(
- user.id, "features.notes", request.app.state.config.USER_PERMISSIONS
- ):
- raise HTTPException(
- status_code=status.HTTP_401_UNAUTHORIZED,
- detail=ERROR_MESSAGES.UNAUTHORIZED,
- )
-
- notes = [
- NoteUserResponse(
- **{
- **note.model_dump(),
- "user": UserResponse(**Users.get_user_by_id(note.user_id).model_dump()),
- }
- )
- for note in Notes.get_notes_by_permission(user.id, "write")
- ]
-
- return notes
-
-
-class NoteTitleIdResponse(BaseModel):
+class NoteItemResponse(BaseModel):
id: str
title: str
+ data: Optional[dict]
updated_at: int
created_at: int
+ user: Optional[UserResponse] = None
-@router.get("/list", response_model=list[NoteTitleIdResponse])
-async def get_note_list(
+@router.get("/", response_model=list[NoteItemResponse])
+async def get_notes(
request: Request, page: Optional[int] = None, user=Depends(get_verified_user)
):
if user.role != "admin" and not has_permission(
@@ -80,15 +66,64 @@ async def get_note_list(
skip = (page - 1) * limit
notes = [
- NoteTitleIdResponse(**note.model_dump())
- for note in Notes.get_notes_by_permission(
- user.id, "write", skip=skip, limit=limit
+ NoteUserResponse(
+ **{
+ **note.model_dump(),
+ "user": UserResponse(**Users.get_user_by_id(note.user_id).model_dump()),
+ }
)
+ for note in Notes.get_notes_by_user_id(user.id, "read", skip=skip, limit=limit)
]
-
return notes
+@router.get("/search", response_model=NoteListResponse)
+async def search_notes(
+ request: Request,
+ query: Optional[str] = None,
+ view_option: Optional[str] = None,
+ permission: Optional[str] = None,
+ order_by: Optional[str] = None,
+ direction: Optional[str] = None,
+ page: Optional[int] = 1,
+ user=Depends(get_verified_user),
+):
+ if user.role != "admin" and not has_permission(
+ user.id, "features.notes", request.app.state.config.USER_PERMISSIONS
+ ):
+ raise HTTPException(
+ status_code=status.HTTP_401_UNAUTHORIZED,
+ detail=ERROR_MESSAGES.UNAUTHORIZED,
+ )
+
+ limit = None
+ skip = None
+ if page is not None:
+ limit = 60
+ skip = (page - 1) * limit
+
+ filter = {}
+ if query:
+ filter["query"] = query
+ if view_option:
+ filter["view_option"] = view_option
+ if permission:
+ filter["permission"] = permission
+ if order_by:
+ filter["order_by"] = order_by
+ if direction:
+ filter["direction"] = direction
+
+ if not user.role == "admin" or not BYPASS_ADMIN_ACCESS_CONTROL:
+ groups = Groups.get_groups_by_member_id(user.id)
+ if groups:
+ filter["group_ids"] = [group.id for group in groups]
+
+ filter["user_id"] = user.id
+
+ return Notes.search_notes(user.id, filter, skip=skip, limit=limit)
+
+
############################
# CreateNewNote
############################
@@ -98,7 +133,6 @@ async def get_note_list(
async def create_new_note(
request: Request, form_data: NoteForm, user=Depends(get_verified_user)
):
-
if user.role != "admin" and not has_permission(
user.id, "features.notes", request.app.state.config.USER_PERMISSIONS
):
@@ -122,7 +156,11 @@ async def create_new_note(
############################
-@router.get("/{id}", response_model=Optional[NoteModel])
+class NoteResponse(NoteModel):
+ write_access: bool = False
+
+
+@router.get("/{id}", response_model=Optional[NoteResponse])
async def get_note_by_id(request: Request, id: str, user=Depends(get_verified_user)):
if user.role != "admin" and not has_permission(
user.id, "features.notes", request.app.state.config.USER_PERMISSIONS
@@ -146,7 +184,15 @@ async def get_note_by_id(request: Request, id: str, user=Depends(get_verified_us
status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
)
- return note
+ write_access = (
+ user.role == "admin"
+ or (user.id == note.user_id)
+ or has_access(
+ user.id, type="write", access_control=note.access_control, strict=False
+ )
+ )
+
+ return NoteResponse(**note.model_dump(), write_access=write_access)
############################
diff --git a/backend/open_webui/routers/ollama.py b/backend/open_webui/routers/ollama.py
index 7873efafce..b1bd4850fe 100644
--- a/backend/open_webui/routers/ollama.py
+++ b/backend/open_webui/routers/ollama.py
@@ -58,7 +58,6 @@ from open_webui.config import (
)
from open_webui.env import (
ENV,
- SRC_LOG_LEVELS,
MODELS_CACHE_TTL,
AIOHTTP_CLIENT_SESSION_SSL,
AIOHTTP_CLIENT_TIMEOUT,
@@ -68,7 +67,6 @@ from open_webui.env import (
from open_webui.constants import ERROR_MESSAGES
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["OLLAMA"])
##########################################
@@ -1280,7 +1278,12 @@ async def generate_chat_completion(
if model_info:
if model_info.base_model_id:
- payload["model"] = model_info.base_model_id
+ base_model_id = (
+ request.base_model_id
+ if hasattr(request, "base_model_id")
+ else model_info.base_model_id
+ ) # Use request's base_model_id if available
+ payload["model"] = base_model_id
params = model_info.params.model_dump()
diff --git a/backend/open_webui/routers/openai.py b/backend/open_webui/routers/openai.py
index a74a59ca1f..d5bdf505a9 100644
--- a/backend/open_webui/routers/openai.py
+++ b/backend/open_webui/routers/openai.py
@@ -35,7 +35,6 @@ from open_webui.env import (
from open_webui.models.users import UserModel
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.utils.payload import (
@@ -53,7 +52,6 @@ from open_webui.utils.headers import include_user_info_headers
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["OPENAI"])
##########################################
@@ -814,8 +812,13 @@ async def generate_chat_completion(
# Check model info and override the payload
if model_info:
if model_info.base_model_id:
- payload["model"] = model_info.base_model_id
- model_id = model_info.base_model_id
+ base_model_id = (
+ request.base_model_id
+ if hasattr(request, "base_model_id")
+ else model_info.base_model_id
+ ) # Use request's base_model_id if available
+ payload["model"] = base_model_id
+ model_id = base_model_id
params = model_info.params.model_dump()
@@ -891,10 +894,11 @@ async def generate_chat_completion(
del payload["max_tokens"]
# Convert the modified body back to JSON
- if "logit_bias" in payload:
- payload["logit_bias"] = json.loads(
- convert_logit_bias_input_to_json(payload["logit_bias"])
- )
+ if "logit_bias" in payload and payload["logit_bias"]:
+ logit_bias = convert_logit_bias_input_to_json(payload["logit_bias"])
+
+ if logit_bias:
+ payload["logit_bias"] = json.loads(logit_bias)
headers, cookies = await get_headers_and_cookies(
request, url, key, api_config, metadata, user=user
diff --git a/backend/open_webui/routers/pipelines.py b/backend/open_webui/routers/pipelines.py
index f80ea91f84..7a42acffc1 100644
--- a/backend/open_webui/routers/pipelines.py
+++ b/backend/open_webui/routers/pipelines.py
@@ -18,7 +18,7 @@ from pydantic import BaseModel
from starlette.responses import FileResponse
from typing import Optional
-from open_webui.env import SRC_LOG_LEVELS, AIOHTTP_CLIENT_SESSION_SSL
+from open_webui.env import AIOHTTP_CLIENT_SESSION_SSL
from open_webui.config import CACHE_DIR
from open_webui.constants import ERROR_MESSAGES
@@ -28,7 +28,6 @@ from open_webui.routers.openai import get_all_models_responses
from open_webui.utils.auth import get_admin_user
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
##################################
diff --git a/backend/open_webui/routers/retrieval.py b/backend/open_webui/routers/retrieval.py
index b7ed993895..a2c1cc80d5 100644
--- a/backend/open_webui/routers/retrieval.py
+++ b/backend/open_webui/routers/retrieval.py
@@ -14,6 +14,7 @@ from typing import Iterator, List, Optional, Sequence, Union
from fastapi import (
Depends,
FastAPI,
+ Query,
File,
Form,
HTTPException,
@@ -28,8 +29,11 @@ from pydantic import BaseModel
import tiktoken
-from langchain.text_splitter import RecursiveCharacterTextSplitter, TokenTextSplitter
-from langchain_text_splitters import MarkdownHeaderTextSplitter
+from langchain_text_splitters import (
+ RecursiveCharacterTextSplitter,
+ TokenTextSplitter,
+ MarkdownHeaderTextSplitter,
+)
from langchain_core.documents import Document
from open_webui.models.files import FileModel, FileUpdateForm, Files
@@ -84,6 +88,7 @@ from open_webui.retrieval.utils import (
from open_webui.retrieval.vector.utils import filter_metadata
from open_webui.utils.misc import (
calculate_sha256_string,
+ sanitize_text_for_db,
)
from open_webui.utils.auth import get_admin_user, get_verified_user
@@ -99,7 +104,6 @@ from open_webui.config import (
RAG_EMBEDDING_QUERY_PREFIX,
)
from open_webui.env import (
- SRC_LOG_LEVELS,
DEVICE_TYPE,
DOCKER,
SENTENCE_TRANSFORMERS_BACKEND,
@@ -111,7 +115,6 @@ from open_webui.env import (
from open_webui.constants import ERROR_MESSAGES
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["RAG"])
##########################################
#
@@ -148,9 +151,14 @@ def get_rf(
reranking_model: Optional[str] = None,
external_reranker_url: str = "",
external_reranker_api_key: str = "",
+ external_reranker_timeout: str = "",
auto_update: bool = RAG_RERANKING_MODEL_AUTO_UPDATE,
):
rf = None
+ # Convert timeout string to int or None (system default)
+ timeout_value = (
+ int(external_reranker_timeout) if external_reranker_timeout else None
+ )
if reranking_model:
if any(model in reranking_model for model in ["jinaai/jina-colbert-v2"]):
try:
@@ -173,6 +181,7 @@ def get_rf(
url=external_reranker_url,
api_key=external_reranker_api_key,
model=reranking_model,
+ timeout=timeout_value,
)
except Exception as e:
log.error(f"ExternalReranking: {e}")
@@ -475,12 +484,14 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"MINERU_API_MODE": request.app.state.config.MINERU_API_MODE,
"MINERU_API_URL": request.app.state.config.MINERU_API_URL,
"MINERU_API_KEY": request.app.state.config.MINERU_API_KEY,
+ "MINERU_API_TIMEOUT": request.app.state.config.MINERU_API_TIMEOUT,
"MINERU_PARAMS": request.app.state.config.MINERU_PARAMS,
# Reranking settings
"RAG_RERANKING_MODEL": request.app.state.config.RAG_RERANKING_MODEL,
"RAG_RERANKING_ENGINE": request.app.state.config.RAG_RERANKING_ENGINE,
"RAG_EXTERNAL_RERANKER_URL": request.app.state.config.RAG_EXTERNAL_RERANKER_URL,
"RAG_EXTERNAL_RERANKER_API_KEY": request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
+ "RAG_EXTERNAL_RERANKER_TIMEOUT": request.app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT,
# Chunking settings
"TEXT_SPLITTER": request.app.state.config.TEXT_SPLITTER,
"CHUNK_SIZE": request.app.state.config.CHUNK_SIZE,
@@ -507,6 +518,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"BYPASS_WEB_SEARCH_WEB_LOADER": request.app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER,
"OLLAMA_CLOUD_WEB_SEARCH_API_KEY": request.app.state.config.OLLAMA_CLOUD_WEB_SEARCH_API_KEY,
"SEARXNG_QUERY_URL": request.app.state.config.SEARXNG_QUERY_URL,
+ "SEARXNG_LANGUAGE": request.app.state.config.SEARXNG_LANGUAGE,
"YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
"YACY_USERNAME": request.app.state.config.YACY_USERNAME,
"YACY_PASSWORD": request.app.state.config.YACY_PASSWORD,
@@ -536,6 +548,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"SOUGOU_API_SID": request.app.state.config.SOUGOU_API_SID,
"SOUGOU_API_SK": request.app.state.config.SOUGOU_API_SK,
"WEB_LOADER_ENGINE": request.app.state.config.WEB_LOADER_ENGINE,
+ "WEB_LOADER_TIMEOUT": request.app.state.config.WEB_LOADER_TIMEOUT,
"ENABLE_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION,
"PLAYWRIGHT_WS_URL": request.app.state.config.PLAYWRIGHT_WS_URL,
"PLAYWRIGHT_TIMEOUT": request.app.state.config.PLAYWRIGHT_TIMEOUT,
@@ -565,6 +578,7 @@ class WebConfig(BaseModel):
BYPASS_WEB_SEARCH_WEB_LOADER: Optional[bool] = None
OLLAMA_CLOUD_WEB_SEARCH_API_KEY: Optional[str] = None
SEARXNG_QUERY_URL: Optional[str] = None
+ SEARXNG_LANGUAGE: Optional[str] = None
YACY_QUERY_URL: Optional[str] = None
YACY_USERNAME: Optional[str] = None
YACY_PASSWORD: Optional[str] = None
@@ -594,6 +608,7 @@ class WebConfig(BaseModel):
SOUGOU_API_SID: Optional[str] = None
SOUGOU_API_SK: Optional[str] = None
WEB_LOADER_ENGINE: Optional[str] = None
+ WEB_LOADER_TIMEOUT: Optional[str] = None
ENABLE_WEB_LOADER_SSL_VERIFICATION: Optional[bool] = None
PLAYWRIGHT_WS_URL: Optional[str] = None
PLAYWRIGHT_TIMEOUT: Optional[int] = None
@@ -656,6 +671,7 @@ class ConfigForm(BaseModel):
MINERU_API_MODE: Optional[str] = None
MINERU_API_URL: Optional[str] = None
MINERU_API_KEY: Optional[str] = None
+ MINERU_API_TIMEOUT: Optional[str] = None
MINERU_PARAMS: Optional[dict] = None
# Reranking settings
@@ -663,6 +679,7 @@ class ConfigForm(BaseModel):
RAG_RERANKING_ENGINE: Optional[str] = None
RAG_EXTERNAL_RERANKER_URL: Optional[str] = None
RAG_EXTERNAL_RERANKER_API_KEY: Optional[str] = None
+ RAG_EXTERNAL_RERANKER_TIMEOUT: Optional[str] = None
# Chunking settings
TEXT_SPLITTER: Optional[str] = None
@@ -877,6 +894,11 @@ async def update_rag_config(
if form_data.MINERU_API_KEY is not None
else request.app.state.config.MINERU_API_KEY
)
+ request.app.state.config.MINERU_API_TIMEOUT = (
+ form_data.MINERU_API_TIMEOUT
+ if form_data.MINERU_API_TIMEOUT is not None
+ else request.app.state.config.MINERU_API_TIMEOUT
+ )
request.app.state.config.MINERU_PARAMS = (
form_data.MINERU_PARAMS
if form_data.MINERU_PARAMS is not None
@@ -914,6 +936,12 @@ async def update_rag_config(
else request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY
)
+ request.app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT = (
+ form_data.RAG_EXTERNAL_RERANKER_TIMEOUT
+ if form_data.RAG_EXTERNAL_RERANKER_TIMEOUT is not None
+ else request.app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT
+ )
+
log.info(
f"Updating reranking model: {request.app.state.config.RAG_RERANKING_MODEL} to {form_data.RAG_RERANKING_MODEL}"
)
@@ -934,6 +962,7 @@ async def update_rag_config(
request.app.state.config.RAG_RERANKING_MODEL,
request.app.state.config.RAG_EXTERNAL_RERANKER_URL,
request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
+ request.app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT,
)
request.app.state.RERANKING_FUNCTION = get_reranking_function(
@@ -1024,6 +1053,7 @@ async def update_rag_config(
form_data.web.OLLAMA_CLOUD_WEB_SEARCH_API_KEY
)
request.app.state.config.SEARXNG_QUERY_URL = form_data.web.SEARXNG_QUERY_URL
+ request.app.state.config.SEARXNG_LANGUAGE = form_data.web.SEARXNG_LANGUAGE
request.app.state.config.YACY_QUERY_URL = form_data.web.YACY_QUERY_URL
request.app.state.config.YACY_USERNAME = form_data.web.YACY_USERNAME
request.app.state.config.YACY_PASSWORD = form_data.web.YACY_PASSWORD
@@ -1071,6 +1101,8 @@ async def update_rag_config(
# Web loader settings
request.app.state.config.WEB_LOADER_ENGINE = form_data.web.WEB_LOADER_ENGINE
+ request.app.state.config.WEB_LOADER_TIMEOUT = form_data.web.WEB_LOADER_TIMEOUT
+
request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION = (
form_data.web.ENABLE_WEB_LOADER_SSL_VERIFICATION
)
@@ -1145,12 +1177,14 @@ async def update_rag_config(
"MINERU_API_MODE": request.app.state.config.MINERU_API_MODE,
"MINERU_API_URL": request.app.state.config.MINERU_API_URL,
"MINERU_API_KEY": request.app.state.config.MINERU_API_KEY,
+ "MINERU_API_TIMEOUT": request.app.state.config.MINERU_API_TIMEOUT,
"MINERU_PARAMS": request.app.state.config.MINERU_PARAMS,
# Reranking settings
"RAG_RERANKING_MODEL": request.app.state.config.RAG_RERANKING_MODEL,
"RAG_RERANKING_ENGINE": request.app.state.config.RAG_RERANKING_ENGINE,
"RAG_EXTERNAL_RERANKER_URL": request.app.state.config.RAG_EXTERNAL_RERANKER_URL,
"RAG_EXTERNAL_RERANKER_API_KEY": request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
+ "RAG_EXTERNAL_RERANKER_TIMEOUT": request.app.state.config.RAG_EXTERNAL_RERANKER_TIMEOUT,
# Chunking settings
"TEXT_SPLITTER": request.app.state.config.TEXT_SPLITTER,
"CHUNK_SIZE": request.app.state.config.CHUNK_SIZE,
@@ -1177,6 +1211,7 @@ async def update_rag_config(
"BYPASS_WEB_SEARCH_WEB_LOADER": request.app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER,
"OLLAMA_CLOUD_WEB_SEARCH_API_KEY": request.app.state.config.OLLAMA_CLOUD_WEB_SEARCH_API_KEY,
"SEARXNG_QUERY_URL": request.app.state.config.SEARXNG_QUERY_URL,
+ "SEARXNG_LANGUAGE": request.app.state.config.SEARXNG_LANGUAGE,
"YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
"YACY_USERNAME": request.app.state.config.YACY_USERNAME,
"YACY_PASSWORD": request.app.state.config.YACY_PASSWORD,
@@ -1206,6 +1241,7 @@ async def update_rag_config(
"SOUGOU_API_SID": request.app.state.config.SOUGOU_API_SID,
"SOUGOU_API_SK": request.app.state.config.SOUGOU_API_SK,
"WEB_LOADER_ENGINE": request.app.state.config.WEB_LOADER_ENGINE,
+ "WEB_LOADER_TIMEOUT": request.app.state.config.WEB_LOADER_TIMEOUT,
"ENABLE_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION,
"PLAYWRIGHT_WS_URL": request.app.state.config.PLAYWRIGHT_WS_URL,
"PLAYWRIGHT_TIMEOUT": request.app.state.config.PLAYWRIGHT_TIMEOUT,
@@ -1346,7 +1382,7 @@ def save_docs_to_vector_db(
if len(docs) == 0:
raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
- texts = [doc.page_content for doc in docs]
+ texts = [sanitize_text_for_db(doc.page_content) for doc in docs]
metadatas = [
{
**doc.metadata,
@@ -1401,6 +1437,7 @@ def save_docs_to_vector_db(
if request.app.state.config.RAG_EMBEDDING_ENGINE == "azure_openai"
else None
),
+ enable_async=request.app.state.config.ENABLE_ASYNC_EMBEDDING,
)
# Run async embedding in sync context
@@ -1557,6 +1594,7 @@ def process_file(
MINERU_API_MODE=request.app.state.config.MINERU_API_MODE,
MINERU_API_URL=request.app.state.config.MINERU_API_URL,
MINERU_API_KEY=request.app.state.config.MINERU_API_KEY,
+ MINERU_API_TIMEOUT=request.app.state.config.MINERU_API_TIMEOUT,
MINERU_PARAMS=request.app.state.config.MINERU_PARAMS,
)
docs = loader.load(
@@ -1715,44 +1753,53 @@ async def process_text(
@router.post("/process/youtube")
@router.post("/process/web")
async def process_web(
- request: Request, form_data: ProcessUrlForm, user=Depends(get_verified_user)
+ request: Request,
+ form_data: ProcessUrlForm,
+ process: bool = Query(True, description="Whether to process and save the content"),
+ user=Depends(get_verified_user),
):
try:
- collection_name = form_data.collection_name
- if not collection_name:
- collection_name = calculate_sha256_string(form_data.url)[:63]
-
content, docs = await run_in_threadpool(
get_content_from_url, request, form_data.url
)
log.debug(f"text_content: {content}")
- if not request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL:
- await run_in_threadpool(
- save_docs_to_vector_db,
- request,
- docs,
- collection_name,
- overwrite=True,
- user=user,
- )
- else:
- collection_name = None
+ if process:
+ collection_name = form_data.collection_name
+ if not collection_name:
+ collection_name = calculate_sha256_string(form_data.url)[:63]
- return {
- "status": True,
- "collection_name": collection_name,
- "filename": form_data.url,
- "file": {
- "data": {
- "content": content,
+ if not request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL:
+ await run_in_threadpool(
+ save_docs_to_vector_db,
+ request,
+ docs,
+ collection_name,
+ overwrite=True,
+ user=user,
+ )
+ else:
+ collection_name = None
+
+ return {
+ "status": True,
+ "collection_name": collection_name,
+ "filename": form_data.url,
+ "file": {
+ "data": {
+ "content": content,
+ },
+ "meta": {
+ "name": form_data.url,
+ "source": form_data.url,
+ },
},
- "meta": {
- "name": form_data.url,
- "source": form_data.url,
- },
- },
- }
+ }
+ else:
+ return {
+ "status": True,
+ "content": content,
+ }
except Exception as e:
log.exception(e)
raise HTTPException(
@@ -1809,11 +1856,13 @@ def search_web(
raise Exception("No PERPLEXITY_API_KEY found in environment variables")
elif engine == "searxng":
if request.app.state.config.SEARXNG_QUERY_URL:
+ searxng_kwargs = {"language": request.app.state.config.SEARXNG_LANGUAGE}
return search_searxng(
request.app.state.config.SEARXNG_QUERY_URL,
query,
request.app.state.config.WEB_SEARCH_RESULT_COUNT,
request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
+ **searxng_kwargs,
)
else:
raise Exception("No SEARXNG_QUERY_URL found in environment variables")
@@ -2066,16 +2115,38 @@ async def process_web_search(
f"trying to web search with {request.app.state.config.WEB_SEARCH_ENGINE, form_data.queries}"
)
- search_tasks = [
- run_in_threadpool(
- search_web,
- request,
- request.app.state.config.WEB_SEARCH_ENGINE,
- query,
- user,
- )
- for query in form_data.queries
- ]
+ # Use semaphore to limit concurrent requests based on WEB_SEARCH_CONCURRENT_REQUESTS
+ # 0 or None = unlimited (previous behavior), positive number = limited concurrency
+ # Set to 1 for sequential execution (rate-limited APIs like Brave free tier)
+ concurrent_limit = request.app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS
+
+ if concurrent_limit:
+ # Limited concurrency with semaphore
+ semaphore = asyncio.Semaphore(concurrent_limit)
+
+ async def search_with_limit(query):
+ async with semaphore:
+ return await run_in_threadpool(
+ search_web,
+ request,
+ request.app.state.config.WEB_SEARCH_ENGINE,
+ query,
+ user,
+ )
+
+ search_tasks = [search_with_limit(query) for query in form_data.queries]
+ else:
+ # Unlimited parallel execution (previous behavior)
+ search_tasks = [
+ run_in_threadpool(
+ search_web,
+ request,
+ request.app.state.config.WEB_SEARCH_ENGINE,
+ query,
+ user,
+ )
+ for query in form_data.queries
+ ]
search_results = await asyncio.gather(*search_tasks)
diff --git a/backend/open_webui/routers/scim.py b/backend/open_webui/routers/scim.py
index c2ee4d1c35..bd2fd3d4f7 100644
--- a/backend/open_webui/routers/scim.py
+++ b/backend/open_webui/routers/scim.py
@@ -24,10 +24,8 @@ from open_webui.utils.auth import (
get_verified_user,
)
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
router = APIRouter()
diff --git a/backend/open_webui/routers/tasks.py b/backend/open_webui/routers/tasks.py
index 040c2382d7..37a80e2ce0 100644
--- a/backend/open_webui/routers/tasks.py
+++ b/backend/open_webui/routers/tasks.py
@@ -35,11 +35,9 @@ from open_webui.config import (
DEFAULT_MOA_GENERATION_PROMPT_TEMPLATE,
DEFAULT_VOICE_MODE_PROMPT_TEMPLATE,
)
-from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
diff --git a/backend/open_webui/routers/tools.py b/backend/open_webui/routers/tools.py
index aa8d95943a..fdcaf266fa 100644
--- a/backend/open_webui/routers/tools.py
+++ b/backend/open_webui/routers/tools.py
@@ -27,13 +27,11 @@ 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.utils.tools import get_tool_servers
-from open_webui.env import SRC_LOG_LEVELS
from open_webui.config import CACHE_DIR, BYPASS_ADMIN_ACCESS_CONTROL
from open_webui.constants import ERROR_MESSAGES
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
router = APIRouter()
diff --git a/backend/open_webui/routers/users.py b/backend/open_webui/routers/users.py
index 3c1bbb72a8..994e2f2b14 100644
--- a/backend/open_webui/routers/users.py
+++ b/backend/open_webui/routers/users.py
@@ -28,7 +28,7 @@ from open_webui.models.users import (
)
from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS, STATIC_DIR
+from open_webui.env import STATIC_DIR
from open_webui.utils.auth import (
@@ -41,7 +41,6 @@ from open_webui.utils.access_control import get_permissions, has_permission
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
router = APIRouter()
@@ -391,6 +390,7 @@ async def update_user_info_by_session_user(
class UserActiveResponse(UserStatus):
name: str
profile_image_url: Optional[str] = None
+ groups: Optional[list] = []
is_active: bool
model_config = ConfigDict(extra="allow")
@@ -412,11 +412,12 @@ async def get_user_by_id(user_id: str, user=Depends(get_verified_user)):
)
user = Users.get_user_by_id(user_id)
-
if user:
+ groups = Groups.get_groups_by_member_id(user_id)
return UserActiveResponse(
**{
**user.model_dump(),
+ "groups": [{"id": group.id, "name": group.name} for group in groups],
"is_active": Users.is_user_active(user_id),
}
)
diff --git a/backend/open_webui/routers/utils.py b/backend/open_webui/routers/utils.py
index b2a44e5488..22529ab1b9 100644
--- a/backend/open_webui/routers/utils.py
+++ b/backend/open_webui/routers/utils.py
@@ -14,11 +14,9 @@ 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()
diff --git a/backend/open_webui/socket/main.py b/backend/open_webui/socket/main.py
index 638a89715a..72b2761c64 100644
--- a/backend/open_webui/socket/main.py
+++ b/backend/open_webui/socket/main.py
@@ -47,13 +47,11 @@ from open_webui.utils.access_control import has_access, get_users_with_access
from open_webui.env import (
GLOBAL_LOG_LEVEL,
- SRC_LOG_LEVELS,
)
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["SOCKET"])
REDIS = None
diff --git a/backend/open_webui/socket/utils.py b/backend/open_webui/socket/utils.py
index 5739a8027a..327348626a 100644
--- a/backend/open_webui/socket/utils.py
+++ b/backend/open_webui/socket/utils.py
@@ -190,7 +190,11 @@ class YdocManager:
async def remove_user_from_all_documents(self, user_id: str):
if self._redis:
- keys = await self._redis.keys(f"{self._redis_key_prefix}:*")
+ keys = []
+ async for key in self._redis.scan_iter(
+ match=f"{self._redis_key_prefix}:*", count=100
+ ):
+ keys.append(key)
for key in keys:
if key.endswith(":users"):
await self._redis.srem(key, user_id)
diff --git a/backend/open_webui/storage/provider.py b/backend/open_webui/storage/provider.py
index 4292e53827..ce02105bfa 100644
--- a/backend/open_webui/storage/provider.py
+++ b/backend/open_webui/storage/provider.py
@@ -33,11 +33,9 @@ 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):
diff --git a/backend/open_webui/tasks.py b/backend/open_webui/tasks.py
index 3e31438281..d83226ffb7 100644
--- a/backend/open_webui/tasks.py
+++ b/backend/open_webui/tasks.py
@@ -8,11 +8,10 @@ from redis.asyncio import Redis
from fastapi import Request
from typing import Dict, List, Optional
-from open_webui.env import SRC_LOG_LEVELS, REDIS_KEY_PREFIX
+from open_webui.env import REDIS_KEY_PREFIX
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
# A dictionary to keep track of active tasks
tasks: Dict[str, asyncio.Task] = {}
diff --git a/backend/open_webui/utils/auth.py b/backend/open_webui/utils/auth.py
index 23fe517150..6cd5fd2d1b 100644
--- a/backend/open_webui/utils/auth.py
+++ b/backend/open_webui/utils/auth.py
@@ -37,7 +37,6 @@ from open_webui.env import (
WEBUI_SECRET_KEY,
TRUSTED_SIGNATURE_KEY,
STATIC_DIR,
- SRC_LOG_LEVELS,
WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
)
@@ -46,7 +45,6 @@ from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["OAUTH"])
SESSION_SECRET = WEBUI_SECRET_KEY
ALGORITHM = "HS256"
diff --git a/backend/open_webui/utils/chat.py b/backend/open_webui/utils/chat.py
index 8b6a0b9da2..e8ebf845de 100644
--- a/backend/open_webui/utils/chat.py
+++ b/backend/open_webui/utils/chat.py
@@ -55,12 +55,11 @@ from open_webui.utils.filter import (
process_filter_functions,
)
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL, BYPASS_MODEL_ACCESS_CONTROL
+from open_webui.env import GLOBAL_LOG_LEVEL, BYPASS_MODEL_ACCESS_CONTROL
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
async def generate_direct_chat_completion(
diff --git a/backend/open_webui/utils/code_interpreter.py b/backend/open_webui/utils/code_interpreter.py
index f3dcbb81fb..e89b970cb6 100644
--- a/backend/open_webui/utils/code_interpreter.py
+++ b/backend/open_webui/utils/code_interpreter.py
@@ -8,10 +8,8 @@ import aiohttp
import websockets
from pydantic import BaseModel
-from open_webui.env import SRC_LOG_LEVELS
logger = logging.getLogger(__name__)
-logger.setLevel(SRC_LOG_LEVELS["MAIN"])
class ResultModel(BaseModel):
diff --git a/backend/open_webui/utils/db/access_control.py b/backend/open_webui/utils/db/access_control.py
new file mode 100644
index 0000000000..d2e6151e5b
--- /dev/null
+++ b/backend/open_webui/utils/db/access_control.py
@@ -0,0 +1,130 @@
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
+from sqlalchemy.dialects.postgresql import JSONB
+
+
+from sqlalchemy import or_, func, select, and_, text, cast, or_, and_, func
+
+
+def has_permission(db, DocumentModel, query, filter: dict, permission: str = "read"):
+ group_ids = filter.get("group_ids", [])
+ user_id = filter.get("user_id")
+ dialect_name = db.bind.dialect.name
+
+ conditions = []
+
+ # Handle read_only permission separately
+ if permission == "read_only":
+ # For read_only, we want items where:
+ # 1. User has explicit read permission (via groups or user-level)
+ # 2. BUT does NOT have write permission
+ # 3. Public items are NOT considered read_only
+
+ read_conditions = []
+
+ # Group-level read permission
+ if group_ids:
+ group_read_conditions = []
+ for gid in group_ids:
+ if dialect_name == "sqlite":
+ group_read_conditions.append(
+ DocumentModel.access_control["read"]["group_ids"].contains(
+ [gid]
+ )
+ )
+ elif dialect_name == "postgresql":
+ group_read_conditions.append(
+ cast(
+ DocumentModel.access_control["read"]["group_ids"],
+ JSONB,
+ ).contains([gid])
+ )
+
+ if group_read_conditions:
+ read_conditions.append(or_(*group_read_conditions))
+
+ # Combine read conditions
+ if read_conditions:
+ has_read = or_(*read_conditions)
+ else:
+ # If no read conditions, return empty result
+ return query.filter(False)
+
+ # Now exclude items where user has write permission
+ write_exclusions = []
+
+ # Exclude items owned by user (they have implicit write)
+ if user_id:
+ write_exclusions.append(DocumentModel.user_id != user_id)
+
+ # Exclude items where user has explicit write permission via groups
+ if group_ids:
+ group_write_conditions = []
+ for gid in group_ids:
+ if dialect_name == "sqlite":
+ group_write_conditions.append(
+ DocumentModel.access_control["write"]["group_ids"].contains(
+ [gid]
+ )
+ )
+ elif dialect_name == "postgresql":
+ group_write_conditions.append(
+ cast(
+ DocumentModel.access_control["write"]["group_ids"],
+ JSONB,
+ ).contains([gid])
+ )
+
+ if group_write_conditions:
+ # User should NOT have write permission
+ write_exclusions.append(~or_(*group_write_conditions))
+
+ # Exclude public items (items without access_control)
+ write_exclusions.append(DocumentModel.access_control.isnot(None))
+ write_exclusions.append(cast(DocumentModel.access_control, String) != "null")
+
+ # Combine: has read AND does not have write AND not public
+ if write_exclusions:
+ query = query.filter(and_(has_read, *write_exclusions))
+ else:
+ query = query.filter(has_read)
+
+ return query
+
+ # Original logic for other permissions (read, write, etc.)
+ # Public access conditions
+ if group_ids or user_id:
+ conditions.extend(
+ [
+ DocumentModel.access_control.is_(None),
+ cast(DocumentModel.access_control, String) == "null",
+ ]
+ )
+
+ # User-level permission (owner has all permissions)
+ if user_id:
+ conditions.append(DocumentModel.user_id == user_id)
+
+ # Group-level permission
+ if group_ids:
+ group_conditions = []
+ for gid in group_ids:
+ if dialect_name == "sqlite":
+ group_conditions.append(
+ DocumentModel.access_control[permission]["group_ids"].contains(
+ [gid]
+ )
+ )
+ elif dialect_name == "postgresql":
+ group_conditions.append(
+ cast(
+ DocumentModel.access_control[permission]["group_ids"],
+ JSONB,
+ ).contains([gid])
+ )
+ conditions.append(or_(*group_conditions))
+
+ if conditions:
+ query = query.filter(or_(*conditions))
+
+ return query
diff --git a/backend/open_webui/utils/embeddings.py b/backend/open_webui/utils/embeddings.py
index 49ce72c3c5..43cbc56e5f 100644
--- a/backend/open_webui/utils/embeddings.py
+++ b/backend/open_webui/utils/embeddings.py
@@ -6,7 +6,7 @@ from fastapi import Request
from open_webui.models.users import UserModel
from open_webui.models.models import Models
from open_webui.utils.models import check_model_access
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL, BYPASS_MODEL_ACCESS_CONTROL
+from open_webui.env import GLOBAL_LOG_LEVEL, BYPASS_MODEL_ACCESS_CONTROL
from open_webui.routers.openai import embeddings as openai_embeddings
from open_webui.routers.ollama import (
@@ -20,7 +20,6 @@ from open_webui.utils.response import convert_embedding_response_ollama_to_opena
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
async def generate_embeddings(
diff --git a/backend/open_webui/utils/files.py b/backend/open_webui/utils/files.py
index 4f9564b7d4..a37ecf31c6 100644
--- a/backend/open_webui/utils/files.py
+++ b/backend/open_webui/utils/files.py
@@ -10,7 +10,13 @@ from fastapi import (
Request,
UploadFile,
)
+from typing import Optional
+from pathlib import Path
+from open_webui.storage.provider import Storage
+
+from open_webui.models.chats import Chats
+from open_webui.models.files import Files
from open_webui.routers.files import upload_file_handler
import mimetypes
@@ -18,24 +24,57 @@ import base64
import io
import re
+import requests
BASE64_IMAGE_URL_PREFIX = re.compile(r"data:image/\w+;base64,", re.IGNORECASE)
MARKDOWN_IMAGE_URL_PATTERN = re.compile(r"!\[(.*?)\]\((.+?)\)", re.IGNORECASE)
+def get_image_base64_from_url(url: str) -> Optional[str]:
+ try:
+ if url.startswith("http"):
+ # Download the image from the URL
+ response = requests.get(url)
+ response.raise_for_status()
+ image_data = response.content
+ encoded_string = base64.b64encode(image_data).decode("utf-8")
+ content_type = response.headers.get("Content-Type", "image/png")
+ return f"data:{content_type};base64,{encoded_string}"
+ else:
+ file = Files.get_file_by_id(url)
+
+ if not file:
+ return None
+
+ file_path = Storage.get_file(file.path)
+ file_path = Path(file_path)
+
+ if file_path.is_file():
+ with open(file_path, "rb") as image_file:
+ encoded_string = base64.b64encode(image_file.read()).decode("utf-8")
+ content_type, _ = mimetypes.guess_type(file_path.name)
+ return f"data:{content_type};base64,{encoded_string}"
+ else:
+ return None
+
+ except Exception as e:
+ return None
+
+
def get_image_url_from_base64(request, base64_image_string, metadata, user):
if BASE64_IMAGE_URL_PREFIX.match(base64_image_string):
image_url = ""
# Extract base64 image data from the line
image_data, content_type = get_image_data(base64_image_string)
if image_data is not None:
- image_url = upload_image(
+ _, image_url = upload_image(
request,
image_data,
content_type,
metadata,
user,
)
+
return image_url
return None
@@ -113,3 +152,26 @@ def get_file_url_from_base64(request, base64_file_string, metadata, user):
elif "data:audio/wav;base64" in base64_file_string:
return get_audio_url_from_base64(request, base64_file_string, metadata, user)
return None
+
+
+def get_image_base64_from_file_id(id: str) -> Optional[str]:
+ file = Files.get_file_by_id(id)
+ if not file:
+ return None
+
+ try:
+ file_path = Storage.get_file(file.path)
+ file_path = Path(file_path)
+
+ # Check if the file already exists in the cache
+ if file_path.is_file():
+ import base64
+
+ with open(file_path, "rb") as image_file:
+ encoded_string = base64.b64encode(image_file.read()).decode("utf-8")
+ content_type, _ = mimetypes.guess_type(file_path.name)
+ return f"data:{content_type};base64,{encoded_string}"
+ else:
+ return None
+ except Exception as e:
+ return None
diff --git a/backend/open_webui/utils/filter.py b/backend/open_webui/utils/filter.py
index 663b4e3fb7..37349d2902 100644
--- a/backend/open_webui/utils/filter.py
+++ b/backend/open_webui/utils/filter.py
@@ -6,10 +6,8 @@ from open_webui.utils.plugin import (
get_function_module_from_cache,
)
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_function_module(request, function_id, load_from_db=True):
diff --git a/backend/open_webui/utils/images/comfyui.py b/backend/open_webui/utils/images/comfyui.py
index 506723bc92..c1293a0fc6 100644
--- a/backend/open_webui/utils/images/comfyui.py
+++ b/backend/open_webui/utils/images/comfyui.py
@@ -9,11 +9,9 @@ import urllib.request
from typing import Optional
import websocket # NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
-from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["COMFYUI"])
default_headers = {"User-Agent": "Mozilla/5.0"}
diff --git a/backend/open_webui/utils/middleware.py b/backend/open_webui/utils/middleware.py
index 140d2bc85d..05f76b1724 100644
--- a/backend/open_webui/utils/middleware.py
+++ b/backend/open_webui/utils/middleware.py
@@ -60,6 +60,7 @@ from open_webui.utils.webhook import post_webhook
from open_webui.utils.files import (
convert_markdown_base64_images,
get_file_url_from_base64,
+ get_image_base64_from_url,
get_image_url_from_base64,
)
@@ -110,7 +111,6 @@ from open_webui.config import (
CODE_INTERPRETER_BLOCKED_MODULES,
)
from open_webui.env import (
- SRC_LOG_LEVELS,
GLOBAL_LOG_LEVEL,
ENABLE_CHAT_RESPONSE_BASE64_IMAGE_URL_CONVERSION,
CHAT_RESPONSE_STREAM_DELTA_CHUNK_SIZE,
@@ -124,7 +124,6 @@ from open_webui.constants import TASKS
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MAIN"])
DEFAULT_REASONING_TAGS = [
@@ -345,7 +344,7 @@ async def chat_completion_tools_handler(
sources = []
specs = [tool["spec"] for tool in tools.values()]
- tools_specs = json.dumps(specs)
+ tools_specs = json.dumps(specs, ensure_ascii=False)
if request.app.state.config.TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE != "":
template = request.app.state.config.TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE
@@ -716,17 +715,18 @@ async def chat_web_search_handler(
return form_data
-def get_last_images(message_list):
+def get_images_from_messages(message_list):
images = []
+
for message in reversed(message_list):
- images_flag = False
+
+ message_images = []
for file in message.get("files", []):
if file.get("type") == "image":
- images.append(file.get("url"))
- images_flag = True
+ message_images.append(file.get("url"))
- if images_flag:
- break
+ if message_images:
+ images.append(message_images)
return images
@@ -757,10 +757,10 @@ async def chat_image_generation_handler(
):
metadata = extra_params.get("__metadata__", {})
chat_id = metadata.get("chat_id", None)
- if not chat_id:
- return form_data
+ __event_emitter__ = extra_params.get("__event_emitter__", None)
- __event_emitter__ = extra_params["__event_emitter__"]
+ if not chat_id or not isinstance(chat_id, str) or not __event_emitter__:
+ return form_data
if chat_id.startswith("local:"):
message_list = form_data.get("messages", [])
@@ -780,7 +780,16 @@ async def chat_image_generation_handler(
user_message = get_last_user_message(message_list)
prompt = user_message
- input_images = get_last_images(message_list)
+ message_images = get_images_from_messages(message_list)
+
+ # Limit to first 2 sets of images
+ # We may want to change this in the future to allow more images
+ input_images = []
+ for idx, images in enumerate(message_images):
+ if idx >= 2:
+ break
+ for image in images:
+ input_images.append(image)
system_message_content = ""
@@ -790,6 +799,10 @@ async def chat_image_generation_handler(
images = await image_edits(
request=request,
form_data=EditImageForm(**{"prompt": prompt, "image": input_images}),
+ metadata={
+ "chat_id": metadata.get("chat_id", None),
+ "message_id": metadata.get("message_id", None),
+ },
user=user,
)
@@ -815,7 +828,7 @@ async def chat_image_generation_handler(
}
)
- system_message_content = "