Merge branch 'dev' into feat/rate-limit-web-search

.github/pull_request_template.md

@@ -4,14 +4,15 @@
 
 **Before submitting, make sure you've checked the following:**
 
-- [ ] **Target branch:** Please verify that the pull request targets the `dev` branch.
+- [ ] **Target branch:** Verify that the pull request targets the `dev` branch. Not targeting the `dev` branch may lead to immediate closure of the PR.
 - [ ] **Description:** Provide a concise description of the changes made in this pull request.
 - [ ] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description.
-- [ ] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources?
+- [ ] **Documentation:** If necessary, update relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs) like environment variables, the tutorials, or other documentation sources.
 - [ ] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation?
-- [ ] **Testing:** Have you written and run sufficient tests to validate the changes?
+- [ ] **Testing:** Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Take this as an opportunity to make screenshots of the feature/fix and include it in the PR description.
+- [ ] **Agentic AI Code:**: Confirm this Pull Request is **not written by any AI Agent** or has at least gone through additional human review **and** manual testing. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR.
 - [ ] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
-- [ ] **Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following:
+- [ ] **Title Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following:
   - **BREAKING CHANGE**: Significant changes that may affect compatibility
   - **build**: Changes that affect the build system or external dependencies
   - **ci**: Changes to our continuous integration processes or workflows

CHANGELOG.md

@@ -5,6 +5,166 @@ 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).
 
+## [0.6.32] - 2025-09-29
+
+### Added
+
+- ⚡ JSON model import moved to backend processing for significant performance improvements when importing large model files. [#17871](https://github.com/open-webui/open-webui/pull/17871)
+- ⚠️ Visual warnings for group permissions that display when a permission is disabled in a group but remains enabled in the default user role, clarifying inheritance behavior for administrators. [#17848](https://github.com/open-webui/open-webui/pull/17848)
+- 🗄️ Milvus multi-tenancy mode using shared collections with resource ID filtering for improved scalability, mirroring the existing Qdrant implementation and configurable via ENABLE_MILVUS_MULTITENANCY_MODE environment variable. [#17837](https://github.com/open-webui/open-webui/pull/17837)
+- 🛠️ Enhanced tool result processing with improved error handling, better MCP tool result handling, and performance improvements for embedded UI components. [Commit](https://github.com/open-webui/open-webui/commit/4f06f29348b2c9d71c87d1bbe5b748a368f5101f)
+- 👥 New user groups now automatically inherit default group permissions, streamlining the admin setup process by eliminating manual permission configuration. [#17843](https://github.com/open-webui/open-webui/pull/17843)
+- 🗂️ Bulk unarchive functionality for all chats, providing a single backend endpoint to efficiently restore all archived chats at once. [#17857](https://github.com/open-webui/open-webui/pull/17857)
+- 🏷️ Browser tab title toggle setting allows users to control whether chat titles appear in the browser tab or display only "Open WebUI". [#17851](https://github.com/open-webui/open-webui/pull/17851)
+- 💬 Reply-to-message functionality in channels, allowing users to reply directly to specific messages with visual threading and context display. [Commit](https://github.com/open-webui/open-webui/commit/1a18928c94903ad1f1f0391b8ade042c3e60205b)
+- 🔧 Tool server import and export functionality, allowing direct upload of openapi.json and openapi.yaml files as an alternative to URL-based configuration. [#14446](https://github.com/open-webui/open-webui/issues/14446)
+- 🔧 User valve configuration for Functions is now available in the integration menu, providing consistent management alongside Tools. [#17784](https://github.com/open-webui/open-webui/issues/17784)
+- 🔐 Admin permission toggle for controlling public sharing of notes, configurable via USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING environment variable. [#17801](https://github.com/open-webui/open-webui/pull/17801), [Docs:#715](https://github.com/open-webui/docs/pull/715)
+- 🗄️ DISKANN index type support for Milvus vector database with configurable maximum degree and search list size parameters. [#17770](https://github.com/open-webui/open-webui/pull/17770), [Docs:Commit](https://github.com/open-webui/docs/commit/cec50ab4d4b659558ca1ccd4b5e6fc024f05fb83)
+- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌐 Translations for Chinese (Simplified & Traditional) and Bosnian (Latin) were enhanced and expanded.
+
+### Fixed
+
+- 🛠️ MCP tool calls are now correctly routed to the appropriate server when multiple streamable-http MCP servers are enabled, preventing "Tool not found" errors. [#17817](https://github.com/open-webui/open-webui/issues/17817)
+- 🛠️ External tool servers (OpenAPI/MCP) now properly process and return tool results to the model, restoring functionality that was broken in v0.6.31. [#17764](https://github.com/open-webui/open-webui/issues/17764)
+- 🔧 User valve detection now correctly identifies valves in imported tool code, ensuring gear icons appear in the integrations menu for all tools with user valves. [#17765](https://github.com/open-webui/open-webui/issues/17765)
+- 🔐 MCP OAuth discovery now correctly handles multi-tenant configurations by including subpaths in metadata URL discovery. [#17768](https://github.com/open-webui/open-webui/issues/17768)
+- 🗄️ Milvus query operations now correctly use -1 instead of None for unlimited queries, preventing TypeError exceptions. [#17769](https://github.com/open-webui/open-webui/pull/17769), [#17088](https://github.com/open-webui/open-webui/issues/17088)
+- 📁 File upload error messages are now displayed when files are modified during upload, preventing user confusion on Android and Windows devices. [#17777](https://github.com/open-webui/open-webui/pull/17777)
+- 🎨 MessageInput Integrations button hover effect now displays correctly with proper visual feedback. [#17767](https://github.com/open-webui/open-webui/pull/17767)
+- 🎯 "Set as default" label positioning is fixed to ensure it remains clickable in all scenarios, including multi-model configurations. [#17779](https://github.com/open-webui/open-webui/pull/17779)
+- 🎛️ Floating buttons now correctly retrieve message context by using the proper messageId parameter in createMessagesList calls. [#17823](https://github.com/open-webui/open-webui/pull/17823)
+- 📌 Pinned chats are now properly cleared from the sidebar after archiving all chats, ensuring UI consistency without requiring a page refresh. [#17832](https://github.com/open-webui/open-webui/pull/17832)
+- 🗑️ Delete confirmation modals now properly truncate long names for Notes, Prompts, Tools, and Functions to prevent modal overflow. [#17812](https://github.com/open-webui/open-webui/pull/17812)
+- 🌐 Internationalization function calls now use proper Svelte store subscription syntax, preventing "i18n.t is not a function" errors on the model creation page. [#17819](https://github.com/open-webui/open-webui/pull/17819)
+- 🎨 Playground chat interface button layout is corrected to prevent vertical text rendering for Assistant/User role buttons. [#17819](https://github.com/open-webui/open-webui/pull/17819)
+- 🏷️ UI text truncation is improved across multiple components including usernames in admin panels, arena model names, model tags, and filter tags to prevent layout overflow issues. [#17805](https://github.com/open-webui/open-webui/pull/17805), [#17803](https://github.com/open-webui/open-webui/pull/17803), [#17791](https://github.com/open-webui/open-webui/pull/17791), [#17796](https://github.com/open-webui/open-webui/pull/17796)
+
+## [0.6.31] - 2025-09-25
+
+### Added
+
+- 🔌 MCP (streamable HTTP) server support was added alongside existing OpenAPI server integration, allowing users to connect both server types through an improved server configuration interface. [#15932](https://github.com/open-webui/open-webui/issues/15932) [#16651](https://github.com/open-webui/open-webui/pull/16651), [Commit](https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406), [Commit](https://github.com/open-webui/open-webui/commit/777e81f7a8aca957a359d51df8388e5af4721a68), [Commit](https://github.com/open-webui/open-webui/commit/de7f7b3d855641450f8e5aac34fbae0665e0b80e), [Commit](https://github.com/open-webui/open-webui/commit/f1bbf3a91e4713039364b790e886e59b401572d0), [Commit](https://github.com/open-webui/open-webui/commit/c55afc42559c32a6f0c8beb0f1bb18e9360ab8af), [Commit](https://github.com/open-webui/open-webui/commit/61f20acf61f4fe30c0e5b0180949f6e1a8cf6524)
+- 🔐 To enable MCP server authentication, OAuth 2.1 dynamic client registration was implemented with secure automatic client registration, encrypted session management, and seamless authentication flows. [Commit](https://github.com/open-webui/open-webui/commit/972be4eda5a394c111e849075f94099c9c0dd9aa), [Commit](https://github.com/open-webui/open-webui/commit/77e971dd9fbeee806e2864e686df5ec75e82104b), [Commit](https://github.com/open-webui/open-webui/commit/879abd7feea3692a2f157da4a458d30f27217508), [Commit](https://github.com/open-webui/open-webui/commit/422d38fd114b1ebd8a7dbb114d64e14791e67d7a), [Docs:#709](https://github.com/open-webui/docs/pull/709)
+- 🛠️ External & Built-In Tools can now support rich UI element embedding ([Docs](https://docs.openwebui.com/features/plugin/tools/development)), allowing tools to return HTML content and interactive iframes that display directly within chat conversations with configurable security settings. [Commit](https://github.com/open-webui/open-webui/commit/07c5b25bc8b63173f406feb3ba183d375fedee6a), [Commit](https://github.com/open-webui/open-webui/commit/a5d8882bba7933a2c2c31c0a1405aba507c370bb), [Commit](https://github.com/open-webui/open-webui/commit/7be5b7f50f498de97359003609fc5993a172f084), [Commit](https://github.com/open-webui/open-webui/commit/a89ffccd7e96705a4a40e845289f4fcf9c4ae596)
+- 📝 Note editor now supports drag-and-drop reordering of list items with visual drag handles, making list organization more intuitive and efficient. [Commit](https://github.com/open-webui/open-webui/commit/e4e97e727e9b4971f1c363b1280ca3a101599d88), [Commit](https://github.com/open-webui/open-webui/commit/aeb5288a3c7a6e9e0a47b807cc52f870c1b7dbe6)
+- 🔍 Search modal was enhanced with quick action buttons for starting new conversations and creating notes, with intelligent content pre-population from search queries. [Commit](https://github.com/open-webui/open-webui/commit/aa6f63a335e172fec1dc94b2056541f52c1167a6), [Commit](https://github.com/open-webui/open-webui/commit/612a52d7bb7dbe9fa0bbbc8ac0a552d2b9801146), [Commit](https://github.com/open-webui/open-webui/commit/b03529b006f3148e895b1094584e1ab129ecac5b)
+- 🛠️ Tool user valve configuration interface was added to the integrations menu, displaying clickable gear icon buttons with tooltips for tools that support user-specific settings, making personal tool configurations easily accessible. [Commit](https://github.com/open-webui/open-webui/commit/27d61307cdce97ed11a05ec13fc300249d6022cd)
+- 👥 Channel access control was enhanced to require write permissions for posting, editing, and deleting messages, while read-only users can view content but cannot contribute. [#17543](https://github.com/open-webui/open-webui/pull/17543)
+- 💬 Channel models now support image processing, allowing AI assistants to view and analyze images shared in conversation threads. [Commit](https://github.com/open-webui/open-webui/commit/9f0010e234a6f40782a66021435d3c02b9c23639)
+- 🌐 Attach Webpage button was added to the message input menu, providing a user-friendly modal interface for attaching web content and YouTube videos as an alternative to the existing URL syntax. [#17534](https://github.com/open-webui/open-webui/pull/17534)
+- 🔐 Redis session storage support was added for OAuth redirects, providing better state handling in multi-pod Kubernetes deployments and resolving CSRF mismatch errors. [#17223](https://github.com/open-webui/open-webui/pull/17223), [#15373](https://github.com/open-webui/open-webui/issues/15373)
+- 🔍 Ollama Cloud web search integration was added as a new search engine option, providing access to web search functionality through Ollama's cloud infrastructure. [Commit](https://github.com/open-webui/open-webui/commit/e06489d92baca095b8f376fbef223298c7772579), [Commit](https://github.com/open-webui/open-webui/commit/4b6d34438bcfc45463dc7a9cb984794b32c1f0a1), [Commit](https://github.com/open-webui/open-webui/commit/05c46008da85357dc6890b846789dfaa59f4a520), [Commit](https://github.com/open-webui/open-webui/commit/fe65fe0b97ec5a8fff71592ff04a25c8e123d108), [Docs:#708](https://github.com/open-webui/docs/pull/708)
+- 🔍 Perplexity Websearch API integration was added as a new search engine option, providing access to the new websearch functionality provided by Perplexity. [#17756](https://github.com/open-webui/open-webui/issues/17756), [Commit](https://github.com/open-webui/open-webui/pull/17747/commits/7f411dd5cc1c29733216f79e99eeeed0406a2afe)
+- ☁️ OneDrive integration was improved to support separate client IDs for personal and business authentication, enabling both integrations to work simultaneously. [#17619](https://github.com/open-webui/open-webui/pull/17619), [Docs](https://docs.openwebui.com/tutorials/integrations/onedrive-sharepoint), [Docs](https://docs.openwebui.com/getting-started/env-configuration/#onedrive)
+- 📝 Pending user overlay content now supports markdown formatting, enabling rich text display for custom messages similar to banner functionality. [#17681](https://github.com/open-webui/open-webui/pull/17681)
+- 🎨 Image generation model selection was centralized to enable dynamic model override in function calls, allowing pipes and tools to specify different models than the global default while maintaining backward compatibility. [#17689](https://github.com/open-webui/open-webui/pull/17689)
+- 🎨 Interface design was modernized with updated visual styling, improved spacing, and refined component layouts across modals, sidebar, settings, and navigation elements. [Commit](https://github.com/open-webui/open-webui/commit/27a91cc80a24bda0a3a188bc3120a8ab57b00881), [Commit](https://github.com/open-webui/open-webui/commit/4ad743098615f9c58daa9df392f31109aeceeb16), [Commit](https://github.com/open-webui/open-webui/commit/fd7385c3921eb59af76a26f4c475aedb38ce2406)
+- 📊 Notes query performance was optimized through database-level filtering and separated access control logic, reducing memory usage and eliminating N+1 query problems for better scalability. [#17607](https://github.com/open-webui/open-webui/pull/17607) [Commit](https://github.com/open-webui/open-webui/pull/17747/commits/da661756fa7eec754270e6dd8c67cbf74a28a17f)
+- ⚡ Page loading performance was optimized by deferring API requests until components are actually opened, including ChangelogModal, ModelSelector, RecursiveFolder, ArchivedChatsModal, and SearchModal. [#17542](https://github.com/open-webui/open-webui/pull/17542), [#17555](https://github.com/open-webui/open-webui/pull/17555), [#17557](https://github.com/open-webui/open-webui/pull/17557), [#17541](https://github.com/open-webui/open-webui/pull/17541), [#17640](https://github.com/open-webui/open-webui/pull/17640)
+- ⚡ Bundle size was reduced by 1.58MB through optimized highlight.js language support, improving page loading speed and reducing bandwidth usage. [#17645](https://github.com/open-webui/open-webui/pull/17645)
+- ⚡ Editor collaboration functionality was refactored to reduce package size by 390KB and minimize compilation errors, improving build performance and reliability. [#17593](https://github.com/open-webui/open-webui/pull/17593)
+- ♿ Enhanced user interface accessibility through the addition of unique element IDs, improving targeting for testing, styling, and assistive technologies while providing better semantic markup for screen readers and accessibility tools. [#17746](https://github.com/open-webui/open-webui/pull/17746)
+- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌐 Translations for Portuguese (Brazil), Chinese (Simplified and Traditional), Korean, Irish, Spanish, Finnish, French, Kabyle, Russian, and Catalan were enhanced and improved.
+
+### Fixed
+
+- 🛡️ SVG content security was enhanced by implementing DOMPurify sanitization to prevent XSS attacks through malicious SVG elements, ensuring safe rendering of user-generated SVG content. [Commit](https://github.com/open-webui/open-webui/pull/17747/commits/750a659a9fee7687e667d9d755e17b8a0c77d557)
+- ☁️ OneDrive attachment menu rendering issues were resolved by restructuring the submenu interface from dropdown to tabbed navigation, preventing menu items from being hidden or clipped due to overflow constraints. [#17554](https://github.com/open-webui/open-webui/issues/17554), [Commit](https://github.com/open-webui/open-webui/pull/17747/commits/90e4b49b881b644465831cc3028bb44f0f7a2196)
+- 💬 Attached conversation references now persist throughout the entire chat session, ensuring models can continue querying referenced conversations after multiple conversation turns. [#17750](https://github.com/open-webui/open-webui/issues/17750)
+- 🔍 Search modal text box focus issues after pinning or unpinning chats were resolved, allowing users to properly exit the search interface by clicking outside the text box. [#17743](https://github.com/open-webui/open-webui/issues/17743)
+- 🔍 Search function chat list is now properly updated in real-time when chats are created or deleted, eliminating stale search results and preview loading failures. [#17741](https://github.com/open-webui/open-webui/issues/17741)
+- 💬 Chat jitter and delayed code block expansion in multi-model sessions were resolved by reverting dynamic CodeEditor loading, restoring stable rendering behavior. [#17715](https://github.com/open-webui/open-webui/pull/17715), [#17684](https://github.com/open-webui/open-webui/issues/17684)
+- 📎 File upload handling was improved to properly recognize uploaded files even when no accompanying text message is provided, resolving issues where attachments were ignored in custom prompts. [#17492](https://github.com/open-webui/open-webui/issues/17492)
+- 💬 Chat conversation referencing within projects was restored by including foldered chats in the reference menu, allowing users to properly quote conversations from within their project scope. [#17530](https://github.com/open-webui/open-webui/issues/17530)
+- 🔍 RAG query generation is now skipped when all attached files are set to full context mode, preventing unnecessary retrieval operations and improving system efficiency. [#17744](https://github.com/open-webui/open-webui/pull/17744)
+- 💾 Memory leaks in file handling and HTTP connections are prevented through proper resource cleanup, ensuring stable memory usage during large file downloads and processing operations. [#17608](https://github.com/open-webui/open-webui/pull/17608)
+- 🔐 OAuth access token refresh errors are resolved by properly implementing async/await patterns, preventing "coroutine object has no attribute get" failures during token expiry. [#17585](https://github.com/open-webui/open-webui/issues/17585), [#17678](https://github.com/open-webui/open-webui/issues/17678)
+- ⚙️ Valve behavior was improved to properly handle default values and array types, ensuring only explicitly set values are persisted while maintaining consistent distinction between custom and default valve states. [#17664](https://github.com/open-webui/open-webui/pull/17664)
+- 🔍 Hybrid search functionality was enhanced to handle inconsistent parameter types and prevent failures when collection results are None, empty, or in unexpected formats. [#17617](https://github.com/open-webui/open-webui/pull/17617)
+- 📁 Empty folder deletion is now allowed regardless of chat deletion permission restrictions, resolving cases where users couldn't remove folders after deleting all contained chats. [#17683](https://github.com/open-webui/open-webui/pull/17683)
+- 📝 Rich text editor console errors were resolved by adding proper error handling when the TipTap editor view is not available or not yet mounted. [#17697](https://github.com/open-webui/open-webui/issues/17697)
+- 🗒️ Hidden models are now properly excluded from the notes section dropdown and default model selection, preventing users from accessing models they shouldn't see. [#17722](https://github.com/open-webui/open-webui/pull/17722)
+- 🖼️ AI-generated image download filenames now use a clean, translatable "Generated Image" format instead of potentially problematic response text, improving file management and compatibility. [#17721](https://github.com/open-webui/open-webui/pull/17721)
+- 🎨 Toggle switch display issues in the Integrations interface are fixed, preventing background highlighting and obscuring on hover. [#17564](https://github.com/open-webui/open-webui/issues/17564)
+
+### Changed
+
+- 👥 Channel permissions now require write access for message posting, editing, and deletion, with existing user groups defaulting to read-only access requiring manual admin migration to write permissions for full participation.
+- ☁️ OneDrive environment variable configuration was updated to use separate ONEDRIVE_CLIENT_ID_PERSONAL and ONEDRIVE_CLIENT_ID_BUSINESS variables for better client ID separation, while maintaining backward compatibility with the legacy ONEDRIVE_CLIENT_ID variable. [Docs](https://docs.openwebui.com/tutorials/integrations/onedrive-sharepoint), [Docs](https://docs.openwebui.com/getting-started/env-configuration/#onedrive)
+
+## [0.6.30] - 2025-09-17
+
+### Added
+
+- 🔑 Microsoft Entra ID authentication type support was added for Azure OpenAI connections, enabling enhanced security and streamlined authentication workflows.
+
+### Fixed
+
+- ☁️ OneDrive integration was fixed after recent breakage, restoring reliable account connectivity and file access.
+
+## [0.6.29] - 2025-09-17
+
+### Added
+
+- 🎨 The chat input menu has been completely overhauled with a revolutionary new design, consolidating attachments under a unified '+' button, organizing integrations into a streamlined options menu, and introducing powerful, interactive selectors for attaching chats, notes, and knowledge base items. [Commit](https://github.com/open-webui/open-webui/commit/a68342d5a887e36695e21f8c2aec593b159654ff), [Commit](https://github.com/open-webui/open-webui/commit/96b8aaf83ff341fef432649366bc5155bac6cf20), [Commit](https://github.com/open-webui/open-webui/commit/4977e6d50f7b931372c96dd5979ca635d58aeb78), [Commit](https://github.com/open-webui/open-webui/commit/d973db829f7ec98b8f8fe7d3b2822d588e79f94e), [Commit](https://github.com/open-webui/open-webui/commit/d4c628de09654df76653ad9bce9cb3263e2f27c8), [Commit](https://github.com/open-webui/open-webui/commit/cd740f436db4ea308dbede14ef7ff56e8126f51b), [Commit](https://github.com/open-webui/open-webui/commit/5c2db102d06b5c18beb248d795682ff422e9b6d1), [Commit](https://github.com/open-webui/open-webui/commit/031cf38655a1a2973194d2eaa0fbbd17aca8ee92), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/3ed0a6d11fea1a054e0bc8aa8dfbe417c7c53e51), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/eadec9e86e01bc8f9fb90dfe7a7ae4fc3bfa6420), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/c03ca7270e64e3a002d321237160c0ddaf2bb129), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/b53ddfbd19aa94e9cbf7210acb31c3cfafafa5fe), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/c923461882fcde30ae297a95e91176c95b9b72e1)
+- 🤖 AI models can now be mentioned in channels to automatically generate responses, enabling multi-model conversations where mentioned models participate directly in threaded discussions with full context awareness. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/4fe97d8794ee18e087790caab9e5d82886006145)
+- 💬 The Channels feature now utilizes the modern rich text editor, including support for '/', '@', and '#' command suggestions. [Commit](https://github.com/open-webui/open-webui/commit/06c1426e14ac0dfaf723485dbbc9723a4d89aba9), [Commit](https://github.com/open-webui/open-webui/commit/02f7c3258b62970ce79716f75d15467a96565054)
+- 📎 Channel message input now supports direct paste functionality for images and files from the clipboard, streamlining content sharing workflows. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/6549fc839f86c40c26c2ef4dedcaf763a9304418)
+- ⚙️ Models can now be configured with default features (Web Search, Image Generation) and filters that automatically activate when a user selects the model. [Commit](https://github.com/open-webui/open-webui/commit/9a555478273355a5177bfc7f7211c64778e4c8de), [Commit](https://github.com/open-webui/open-webui/commit/384a53b339820068e92f7eaea0d9f3e0536c19c2), [Commit](https://github.com/open-webui/open-webui/commit/d7f43bfc1a30c065def8c50d77c2579c1a3c5c67), [Commit](https://github.com/open-webui/open-webui/commit/6a67a2217cc5946ad771e479e3a37ac213210748)
+- 💬 The ability to reference other chats as context within a conversation was added via the attachment menu. [Commit](https://github.com/open-webui/open-webui/commit/e097bbdf11ae4975c622e086df00d054291cdeb3), [Commit](https://github.com/open-webui/open-webui/commit/f3cd2ffb18e7dedbe88430f9ae7caa6b3cfd79d0), [Commit](https://github.com/open-webui/open-webui/commit/74263c872c5d574a9bb0944d7984f748dc772dba), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/aa8ab349ed2fcb46d1cf994b9c0de2ec2ea35d0d), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/025eef754f0d46789981defd473d001e3b1d0ca2)
+- 🎨 The command suggestion UI for prompts ('/'), models ('@'), and knowledge ('#') was completely overhauled with a more responsive and keyboard-navigable interface. [Commit](https://github.com/open-webui/open-webui/commit/6b69c4da0fb9329ccf7024483960e070cf52ccab), [Commit](https://github.com/open-webui/open-webui/commit/06a6855f844456eceaa4d410c93379460e208202), [Commit](https://github.com/open-webui/open-webui/commit/c55f5578280b936cf581a743df3703e3db1afd54), [Commit](https://github.com/open-webui/open-webui/commit/f68d1ba394d4423d369f827894cde99d760b2402)
+- 👥 User and channel suggestions were added to the mention system, enabling '@' mentions for users and models, and '#' mentions for channels with searchable user lookup and clickable navigation. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/bbd1d2b58c89b35daea234f1fc9208f2af840899), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/aef1e06f0bb72065a25579c982dd49157e320268), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/779db74d7e9b7b00d099b7d65cfbc8a831e74690)
+- 📁 Folder functionality was enhanced with custom background image support, improved drag-and-drop capabilities for moving folders to root level, and better menu interactions. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/2a234829f5dfdfde27fdfd30591caa908340efb4), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/2b1ee8b0dc5f7c0caaafdd218f20705059fa72e2), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/b1e5bc8e490745f701909c19b6a444b67c04660e), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/3e584132686372dfeef187596a7c557aa5f48308)
+- ☁️ OneDrive integration configuration now supports selecting between personal and work/school account types via ENABLE_ONEDRIVE_PERSONAL and ENABLE_ONEDRIVE_BUSINESS environment variables. [#17354](https://github.com/open-webui/open-webui/pull/17354), [Commit](https://github.com/open-webui/open-webui/commit/e1e3009a30f9808ce06582d81a60e391f5ca09ec), [Docs:#697](https://github.com/open-webui/docs/pull/697)
+- ⚡ Mermaid.js is now dynamically loaded on demand, significantly reducing first-screen loading time and improving initial page performance. [#17476](https://github.com/open-webui/open-webui/issues/17476), [#17477](https://github.com/open-webui/open-webui/pull/17477)
+- ⚡ Azure MSAL browser library is now dynamically loaded on demand, reducing initial bundle size by 730KB and improving first-screen loading speed. [#17479](https://github.com/open-webui/open-webui/pull/17479)
+- ⚡ CodeEditor component is now dynamically loaded on demand, reducing initial bundle size by 1MB and improving first-screen loading speed. [#17498](https://github.com/open-webui/open-webui/pull/17498)
+- ⚡ Hugging Face Transformers library is now dynamically loaded on demand, reducing initial bundle size by 1.9MB and improving first-screen loading speed. [#17499](https://github.com/open-webui/open-webui/pull/17499)
+- ⚡ jsPDF and html2canvas-pro libraries are now dynamically loaded on demand, reducing initial bundle size by 980KB and improving first-screen loading speed. [#17502](https://github.com/open-webui/open-webui/pull/17502)
+- ⚡ Leaflet mapping library is now dynamically loaded on demand, reducing initial bundle size by 454KB and improving first-screen loading speed. [#17503](https://github.com/open-webui/open-webui/pull/17503)
+- 📊 OpenTelemetry metrics collection was enhanced to properly handle HTTP 500 errors and ensure metrics are recorded even during exceptions. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/b14617a653c6bdcfd3102c12f971924fd1faf572)
+- 🔒 OAuth token retrieval logic was refactored, improving the reliability and consistency of authentication handling across the backend. [Commit](https://github.com/open-webui/open-webui/commit/6c0a5fa91cdbf6ffb74667ee61ca96bebfdfbc50)
+- 💻 Code block output processing was improved to handle Python execution results more reliably, along with refined visual styling and button layouts. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/0e5320c39e308ff97f2ca9e289618af12479eb6e)
+- ⚡ Message input processing was optimized to skip unnecessary text variable handling when input is empty, improving performance. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/e1386fe80b77126a12dabc4ad058abe9b024b275)
+- 📄 Individual chat PDF export was added to the sidebar chat menu, allowing users to export single conversations as PDF documents with both stylized and plain text options. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/d041d58bb619689cd04a391b4f8191b23941ca62)
+- 🛠️ Function validation was enhanced with improved valve validation and better error handling during function loading and synchronization. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/e66e0526ed6a116323285f79f44237538b6c75e6), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/8edfd29102e0a61777b23d3575eaa30be37b59a5)
+- 🔔 Notification toast interaction was enhanced with drag detection to prevent accidental clicks and added keyboard support for accessibility. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/621e7679c427b6f0efa85f95235319238bf171ad)
+- 🗓️ Improved date and time formatting dynamically adapts to the selected language, ensuring consistent localization across the UI. [#17409](https://github.com/open-webui/open-webui/pull/17409), [Commit](https://github.com/open-webui/open-webui/commit/2227f24bd6d861b1fad8d2cabacf7d62ce137d0c)
+- 🔒 Feishu SSO integration was added, allowing users to authenticate via Feishu. [#17284](https://github.com/open-webui/open-webui/pull/17284), [Docs:#685](https://github.com/open-webui/docs/pull/685)
+- 🔠 Toggle filters in the chat input options menu are now sorted alphabetically for easier navigation. [Commit](https://github.com/open-webui/open-webui/commit/ca853ca4656180487afcd84230d214f91db52533)
+- 🎨 Long chat titles in the sidebar are now truncated to prevent text overflow and maintain a clean layout. [#17356](https://github.com/open-webui/open-webui/pull/17356)
+- 🎨 Temporary chat interface design was refined with improved layout and visual consistency. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/67549dcadd670285d491bd41daf3d081a70fd094), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/2ca34217e68f3b439899c75881dfb050f49c9eb2), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/fb02ec52a5df3f58b53db4ab3a995c15f83503cd)
+- 🎨 Download icon consistency was improved across the entire interface by standardizing the icon component used in menus, functions, tools, and export features. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/596be451ece7e11b5cd25465d49670c27a1cb33f)
+- 🎨 Settings interface was enhanced with improved iconography and reorganized the 'Chats' section into 'Data Controls' for better clarity. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/8bf0b40fdd978b5af6548a6e1fb3aabd90bcd5cd)
+- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security.
+- 🌐 Translations for Finnish, German, Kabyle, Portuguese (Brazil), Simplified Chinese, Spanish (Spain), and Traditional Chinese (Taiwan) were enhanced and expanded.
+
+### Fixed
+
+- 📚 Knowledge base permission logic was corrected to ensure private collection owners can access their own content when embedding bypass is enabled. [#17432](https://github.com/open-webui/open-webui/issues/17432), [Commit](https://github.com/open-webui/open-webui/commit/a51f0c30ec1472d71487eab3e15d0351a2716b12)
+- ⚙️ Connection URL editing in Admin Settings now properly saves changes instead of reverting to original values, fixing issues with both Ollama and OpenAI-compatible endpoints. [#17435](https://github.com/open-webui/open-webui/issues/17435), [Commit](https://github.com/open-webui/open-webui/commit/e4c864de7eb0d577843a80688677ce3659d1f81f)
+- 📊 Usage information collection from Google models was corrected to handle providers that send usage data alongside content chunks instead of separately. [#17421](https://github.com/open-webui/open-webui/pull/17421), [Commit](https://github.com/open-webui/open-webui/commit/c2f98a4cd29ed738f395fef09c42ab8e73cd46a0)
+- ⚙️ Settings modal scrolling issue was resolved by moving image compression controls to a dedicated modal, preventing the main settings from becoming scrollable out of view. [#17474](https://github.com/open-webui/open-webui/issues/17474), [Commit](https://github.com/open-webui/open-webui/commit/fed5615c19b0045a55b0be426b468a57bfda4b66)
+- 📁 Folder click behavior was improved to prevent accidental actions by implementing proper double-click detection and timing delays for folder expansion and selection. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/19e3214997170eea6ee92452e8c778e04a28e396)
+- 🔐 Access control component reliability was improved with better null checking and error handling for group permissions and private access scenarios. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/c8780a7f934c5e49a21b438f2f30232f83cf75d2), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/32015c392dbc6b7367a6a91d9e173e675ea3402c)
+- 🔗 The citation modal now correctly displays and links to external web page sources in addition to internal documents. [Commit](https://github.com/open-webui/open-webui/commit/9208a84185a7e59524f00a7576667d493c3ac7d4)
+- 🔗 Web and YouTube attachment handling was fixed, ensuring their content is now reliably processed and included in the chat context for retrieval. [Commit](https://github.com/open-webui/open-webui/commit/210197fd438b52080cda5d6ce3d47b92cdc264c8)
+- 📂 Large file upload failures are resolved by correcting the processing logic for scenarios where document embedding is bypassed. [Commit](https://github.com/open-webui/open-webui/commit/051b6daa8299fd332503bd584563556e2ae6adab)
+- 🌐 Rich text input placeholder text now correctly updates when the interface language is switched, ensuring proper localization. [#17473](https://github.com/open-webui/open-webui/pull/17473), [Commit](https://github.com/open-webui/open-webui/commit/77358031f5077e6efe5cc08d8d4e5831c7cd1cd9)
+- 📊 Llama.cpp server timing metrics are now correctly parsed and displayed by fixing a typo in the response handling. [#17350](https://github.com/open-webui/open-webui/issues/17350), [Commit](https://github.com/open-webui/open-webui/commit/cf72f5503f39834b9da44ebbb426a3674dad0caa)
+- 🛠️ Filter functions with file_handler configuration now properly handle messages without file attachments, preventing runtime errors. [#17423](https://github.com/open-webui/open-webui/pull/17423)
+- 🔔 Channel notification delivery was fixed to properly handle background task execution and user access checking. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/1077b2ac8b96e49c2ad2620e76eb65bbb2a3a1f3)
+
+### Changed
+
+- 📝 Prompt template variables are now optional by default instead of being forced as required, allowing flexible workflows with optional metadata fields. [#17447](https://github.com/open-webui/open-webui/issues/17447), [Commit](https://github.com/open-webui/open-webui/commit/d5824b1b495fcf86e57171769bcec2a0f698b070), [Docs:#696](https://github.com/open-webui/docs/pull/696)
+- 🛠️ Direct external tool servers now require explicit user selection from the input interface instead of being automatically included in conversations, providing better control over tool usage. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/0f04227c34ca32746c43a9323e2df32299fcb6af), [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/99bba12de279dd55c55ded35b2e4f819af1c9ab5)
+- 📺 Widescreen mode option was removed from Channels interface, with all channel layouts now using full-width display. [Commit](https://github.com/open-webui/open-webui/pull/17420/commits/d46b7b8f1b99a8054b55031fe935c8a16d5ec956)
+- 🎛️ The plain textarea input option was deprecated, and the custom text editor is now the standard for all chat inputs. [Commit](https://github.com/open-webui/open-webui/commit/153afd832ccd12a1e5fd99b085008d080872c161)
+
 ## [0.6.28] - 2025-09-10
 
 ### Added

LICENSE_NOTICE

@@ -0,0 +1,11 @@
+# Open WebUI Multi-License Notice
+
+This repository contains code governed by multiple licenses based on the date and origin of contribution:
+
+1. All code committed prior to commit a76068d69cd59568b920dfab85dc573dbbb8f131 is licensed under the MIT License (see LICENSE_HISTORY).
+
+2. All code committed from commit a76068d69cd59568b920dfab85dc573dbbb8f131 up to and including commit 60d84a3aae9802339705826e9095e272e3c83623 is licensed under the BSD 3-Clause License (see LICENSE_HISTORY).
+
+3. All code contributed or modified after commit 60d84a3aae9802339705826e9095e272e3c83623 is licensed under the Open WebUI License (see LICENSE).
+
+For details on which commits are covered by which license, refer to LICENSE_HISTORY.

README.md

@@ -248,7 +248,7 @@ Discover upcoming features on our roadmap in the [Open WebUI Documentation](http
 
 ## License 📜
 
-This project is licensed under the [Open WebUI License](LICENSE), a revised BSD-3-Clause license. You receive all the same rights as the classic BSD-3 license: you can use, modify, and distribute the software, including in proprietary and commercial products, with minimal restrictions. The only additional requirement is to preserve the "Open WebUI" branding, as detailed in the LICENSE file. For full terms, see the [LICENSE](LICENSE) document. 📄
+This project contains code under multiple licenses. The current codebase includes components licensed under the Open WebUI License with an additional requirement to preserve the "Open WebUI" branding, as well as prior contributions under their respective original licenses. For a detailed record of license changes and the applicable terms for each section of the code, please refer to [LICENSE_HISTORY](./LICENSE_HISTORY). For complete and updated licensing details, please see the [LICENSE](./LICENSE) and [LICENSE_HISTORY](./LICENSE_HISTORY) files.
 
 ## Support 💬
 

backend/open_webui/config.py

@@ -222,10 +222,11 @@ class PersistentConfig(Generic[T]):
 
 
 class AppConfig:
-    _state: dict[str, PersistentConfig]
     _redis: Union[redis.Redis, redis.cluster.RedisCluster] = None
     _redis_key_prefix: str
 
+    _state: dict[str, PersistentConfig]
+
     def __init__(
         self,
         redis_url: Optional[str] = None,
@@ -233,9 +234,8 @@ class AppConfig:
         redis_cluster: Optional[bool] = False,
         redis_key_prefix: str = "open-webui",
     ):
-        super().__setattr__("_state", {})
-        super().__setattr__("_redis_key_prefix", redis_key_prefix)
         if redis_url:
+            super().__setattr__("_redis_key_prefix", redis_key_prefix)
             super().__setattr__(
                 "_redis",
                 get_redis_connection(
@@ -246,6 +246,8 @@ class AppConfig:
                 ),
             )
 
+        super().__setattr__("_state", {})
+
     def __setattr__(self, key, value):
         if isinstance(value, PersistentConfig):
             self._state[key] = value
@@ -603,8 +605,8 @@ def load_oauth_providers():
     OAUTH_PROVIDERS.clear()
     if GOOGLE_CLIENT_ID.value and GOOGLE_CLIENT_SECRET.value:
 
-        def google_oauth_register(client: OAuth):
+        def google_oauth_register(oauth: OAuth):
-            client.register(
+            return oauth.register(
                 name="google",
                 client_id=GOOGLE_CLIENT_ID.value,
                 client_secret=GOOGLE_CLIENT_SECRET.value,
@@ -631,8 +633,8 @@ def load_oauth_providers():
         and MICROSOFT_CLIENT_TENANT_ID.value
     ):
 
-        def microsoft_oauth_register(client: OAuth):
+        def microsoft_oauth_register(oauth: OAuth):
-            client.register(
+            return oauth.register(
                 name="microsoft",
                 client_id=MICROSOFT_CLIENT_ID.value,
                 client_secret=MICROSOFT_CLIENT_SECRET.value,
@@ -656,8 +658,8 @@ def load_oauth_providers():
 
     if GITHUB_CLIENT_ID.value and GITHUB_CLIENT_SECRET.value:
 
-        def github_oauth_register(client: OAuth):
+        def github_oauth_register(oauth: OAuth):
-            client.register(
+            return oauth.register(
                 name="github",
                 client_id=GITHUB_CLIENT_ID.value,
                 client_secret=GITHUB_CLIENT_SECRET.value,
@@ -688,7 +690,7 @@ def load_oauth_providers():
         and OPENID_PROVIDER_URL.value
     ):
 
-        def oidc_oauth_register(client: OAuth):
+        def oidc_oauth_register(oauth: OAuth):
             client_kwargs = {
                 "scope": OAUTH_SCOPES.value,
                 **(
@@ -714,7 +716,7 @@ def load_oauth_providers():
                     % ("S256", OAUTH_CODE_CHALLENGE_METHOD.value)
                 )
 
-            client.register(
+            return oauth.register(
                 name="oidc",
                 client_id=OAUTH_CLIENT_ID.value,
                 client_secret=OAUTH_CLIENT_SECRET.value,
@@ -731,8 +733,8 @@ def load_oauth_providers():
 
     if FEISHU_CLIENT_ID.value and FEISHU_CLIENT_SECRET.value:
 
-        def feishu_oauth_register(client: OAuth):
+        def feishu_oauth_register(oauth: OAuth):
-            client.register(
+            return oauth.register(
                 name="feishu",
                 client_id=FEISHU_CLIENT_ID.value,
                 client_secret=FEISHU_CLIENT_SECRET.value,
@@ -1215,6 +1217,11 @@ USER_PERMISSIONS_WORKSPACE_MODELS_ALLOW_PUBLIC_SHARING = (
     == "true"
 )
 
+USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING = (
+    os.environ.get("USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING", "False").lower()
+    == "true"
+)
+
 USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_PUBLIC_SHARING = (
     os.environ.get(
         "USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_PUBLIC_SHARING", "False"
@@ -1352,6 +1359,7 @@ DEFAULT_USER_PERMISSIONS = {
         "public_knowledge": USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ALLOW_PUBLIC_SHARING,
         "public_prompts": USER_PERMISSIONS_WORKSPACE_PROMPTS_ALLOW_PUBLIC_SHARING,
         "public_tools": USER_PERMISSIONS_WORKSPACE_TOOLS_ALLOW_PUBLIC_SHARING,
+        "public_notes": USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING,
     },
     "chat": {
         "controls": USER_PERMISSIONS_CHAT_CONTROLS,
@@ -1997,16 +2005,23 @@ if VECTOR_DB == "chroma":
 # this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (sentence-transformers/all-MiniLM-L6-v2)
 
 # Milvus
-
 MILVUS_URI = os.environ.get("MILVUS_URI", f"{DATA_DIR}/vector_db/milvus.db")
 MILVUS_DB = os.environ.get("MILVUS_DB", "default")
 MILVUS_TOKEN = os.environ.get("MILVUS_TOKEN", None)
-
 MILVUS_INDEX_TYPE = os.environ.get("MILVUS_INDEX_TYPE", "HNSW")
 MILVUS_METRIC_TYPE = os.environ.get("MILVUS_METRIC_TYPE", "COSINE")
 MILVUS_HNSW_M = int(os.environ.get("MILVUS_HNSW_M", "16"))
 MILVUS_HNSW_EFCONSTRUCTION = int(os.environ.get("MILVUS_HNSW_EFCONSTRUCTION", "100"))
 MILVUS_IVF_FLAT_NLIST = int(os.environ.get("MILVUS_IVF_FLAT_NLIST", "128"))
+MILVUS_DISKANN_MAX_DEGREE = int(os.environ.get("MILVUS_DISKANN_MAX_DEGREE", "56"))
+MILVUS_DISKANN_SEARCH_LIST_SIZE = int(
+    os.environ.get("MILVUS_DISKANN_SEARCH_LIST_SIZE", "100")
+)
+ENABLE_MILVUS_MULTITENANCY_MODE = (
+    os.environ.get("ENABLE_MILVUS_MULTITENANCY_MODE", "false").lower() == "true"
+)
+# Hyphens not allowed, need to use underscores in collection names
+MILVUS_COLLECTION_PREFIX = os.environ.get("MILVUS_COLLECTION_PREFIX", "open_webui")
 
 # Qdrant
 QDRANT_URI = os.environ.get("QDRANT_URI", None)
@@ -2169,10 +2184,20 @@ ENABLE_ONEDRIVE_INTEGRATION = PersistentConfig(
     os.getenv("ENABLE_ONEDRIVE_INTEGRATION", "False").lower() == "true",
 )
 
-ONEDRIVE_CLIENT_ID = PersistentConfig(
+
-    "ONEDRIVE_CLIENT_ID",
+ENABLE_ONEDRIVE_PERSONAL = (
-    "onedrive.client_id",
+    os.environ.get("ENABLE_ONEDRIVE_PERSONAL", "True").lower() == "true"
-    os.environ.get("ONEDRIVE_CLIENT_ID", ""),
+)
+ENABLE_ONEDRIVE_BUSINESS = (
+    os.environ.get("ENABLE_ONEDRIVE_BUSINESS", "True").lower() == "true"
+)
+
+ONEDRIVE_CLIENT_ID = os.environ.get("ONEDRIVE_CLIENT_ID", "")
+ONEDRIVE_CLIENT_ID_PERSONAL = os.environ.get(
+    "ONEDRIVE_CLIENT_ID_PERSONAL", ONEDRIVE_CLIENT_ID
+)
+ONEDRIVE_CLIENT_ID_BUSINESS = os.environ.get(
+    "ONEDRIVE_CLIENT_ID_BUSINESS", ONEDRIVE_CLIENT_ID
 )
 
 ONEDRIVE_SHAREPOINT_URL = PersistentConfig(
@@ -2285,6 +2310,18 @@ DOCLING_SERVER_URL = PersistentConfig(
     os.getenv("DOCLING_SERVER_URL", "http://docling:5001"),
 )
 
+docling_params = os.getenv("DOCLING_PARAMS", "")
+try:
+    docling_params = json.loads(docling_params)
+except json.JSONDecodeError:
+    docling_params = {}
+
+DOCLING_PARAMS = PersistentConfig(
+    "DOCLING_PARAMS",
+    "rag.docling_params",
+    docling_params,
+)
+
 DOCLING_DO_OCR = PersistentConfig(
     "DOCLING_DO_OCR",
     "rag.docling_do_ocr",
@@ -2778,6 +2815,12 @@ WEB_SEARCH_TRUST_ENV = PersistentConfig(
 )
 
 
+OLLAMA_CLOUD_WEB_SEARCH_API_KEY = PersistentConfig(
+    "OLLAMA_CLOUD_WEB_SEARCH_API_KEY",
+    "rag.web.search.ollama_cloud_api_key",
+    os.getenv("OLLAMA_CLOUD_API_KEY", ""),
+)
+
 SEARXNG_QUERY_URL = PersistentConfig(
     "SEARXNG_QUERY_URL",
     "rag.web.search.searxng_query_url",
@@ -3353,6 +3396,19 @@ AUDIO_TTS_OPENAI_API_KEY = PersistentConfig(
     os.getenv("AUDIO_TTS_OPENAI_API_KEY", OPENAI_API_KEY),
 )
 
+audio_tts_openai_params = os.getenv("AUDIO_TTS_OPENAI_PARAMS", "")
+try:
+    audio_tts_openai_params = json.loads(audio_tts_openai_params)
+except json.JSONDecodeError:
+    audio_tts_openai_params = {}
+
+AUDIO_TTS_OPENAI_PARAMS = PersistentConfig(
+    "AUDIO_TTS_OPENAI_PARAMS",
+    "audio.tts.openai.params",
+    audio_tts_openai_params,
+)
+
+
 AUDIO_TTS_API_KEY = PersistentConfig(
     "AUDIO_TTS_API_KEY",
     "audio.tts.api_key",

backend/open_webui/env.py

@@ -474,6 +474,10 @@ ENABLE_OAUTH_ID_TOKEN_COOKIE = (
     os.environ.get("ENABLE_OAUTH_ID_TOKEN_COOKIE", "True").lower() == "true"
 )
 
+OAUTH_CLIENT_INFO_ENCRYPTION_KEY = os.environ.get(
+    "OAUTH_CLIENT_INFO_ENCRYPTION_KEY", WEBUI_SECRET_KEY
+)
+
 OAUTH_SESSION_TOKEN_ENCRYPTION_KEY = os.environ.get(
     "OAUTH_SESSION_TOKEN_ENCRYPTION_KEY", WEBUI_SECRET_KEY
 )
@@ -547,16 +551,16 @@ else:
 
 
 CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = os.environ.get(
-    "CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES", "10"
+    "CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES", "30"
 )
 
 if CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES == "":
-    CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = 10
+    CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = 30
 else:
     try:
         CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = int(CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES)
     except Exception:
-        CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = 10
+        CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = 30
 
 
 ####################################

backend/open_webui/functions.py

@@ -19,6 +19,7 @@ from fastapi import (
 from starlette.responses import Response, StreamingResponse
 
 
+from open_webui.constants import ERROR_MESSAGES
 from open_webui.socket.main import (
     get_event_call,
     get_event_emitter,
@@ -60,8 +61,20 @@ def get_function_module_by_id(request: Request, pipe_id: str):
     function_module, _, _ = get_function_module_from_cache(request, pipe_id)
 
     if hasattr(function_module, "valves") and hasattr(function_module, "Valves"):
+        Valves = function_module.Valves
         valves = Functions.get_function_valves_by_id(pipe_id)
-        function_module.valves = function_module.Valves(**(valves if valves else {}))
+
+        if valves:
+            try:
+                function_module.valves = Valves(
+                    **{k: v for k, v in valves.items() if v is not None}
+                )
+            except Exception as e:
+                log.exception(f"Error loading valves for function {pipe_id}: {e}")
+                raise e
+        else:
+            function_module.valves = Valves()
+
     return function_module
 
 
@@ -70,8 +83,13 @@ async def get_function_models(request):
     pipe_models = []
 
     for pipe in pipes:
+        try:
             function_module = get_function_module_by_id(request, pipe.id)
 
+            has_user_valves = False
+            if hasattr(function_module, "UserValves"):
+                has_user_valves = True
+
             # Check if function is a manifold
             if hasattr(function_module, "pipes"):
                 sub_pipes = []
@@ -110,6 +128,7 @@ async def get_function_models(request):
                             "created": pipe.created_at,
                             "owned_by": "openai",
                             "pipe": pipe_flag,
+                            "has_user_valves": has_user_valves,
                         }
                     )
             else:
@@ -127,8 +146,12 @@ async def get_function_models(request):
                         "created": pipe.created_at,
                         "owned_by": "openai",
                         "pipe": pipe_flag,
+                        "has_user_valves": has_user_valves,
                     }
                 )
+        except Exception as e:
+            log.exception(e)
+            continue
 
     return pipe_models
 
@@ -222,7 +245,7 @@ async def generate_function_chat_completion(
     oauth_token = None
     try:
         if request.cookies.get("oauth_session_id", None):
-            oauth_token = request.app.state.oauth_manager.get_oauth_token(
+            oauth_token = await request.app.state.oauth_manager.get_oauth_token(
                 user.id,
                 request.cookies.get("oauth_session_id", None),
             )

backend/open_webui/main.py

@@ -8,6 +8,7 @@ import shutil
 import sys
 import time
 import random
+import re
 from uuid import uuid4
 
 
@@ -50,6 +51,11 @@ from starlette.middleware.sessions import SessionMiddleware
 from starlette.responses import Response, StreamingResponse
 from starlette.datastructures import Headers
 
+from starsessions import (
+    SessionMiddleware as StarSessionsMiddleware,
+    SessionAutoloadMiddleware,
+)
+from starsessions.stores.redis import RedisStore
 
 from open_webui.utils import logger
 from open_webui.utils.audit import AuditLevel, AuditLoggingMiddleware
@@ -110,9 +116,6 @@ from open_webui.config import (
     OLLAMA_API_CONFIGS,
     # OpenAI
     ENABLE_OPENAI_API,
-    ONEDRIVE_CLIENT_ID,
-    ONEDRIVE_SHAREPOINT_URL,
-    ONEDRIVE_SHAREPOINT_TENANT_ID,
     OPENAI_API_BASE_URLS,
     OPENAI_API_KEYS,
     OPENAI_API_CONFIGS,
@@ -172,13 +175,14 @@ from open_webui.config import (
     AUDIO_STT_AZURE_LOCALES,
     AUDIO_STT_AZURE_BASE_URL,
     AUDIO_STT_AZURE_MAX_SPEAKERS,
-    AUDIO_TTS_API_KEY,
     AUDIO_TTS_ENGINE,
     AUDIO_TTS_MODEL,
+    AUDIO_TTS_VOICE,
     AUDIO_TTS_OPENAI_API_BASE_URL,
     AUDIO_TTS_OPENAI_API_KEY,
+    AUDIO_TTS_OPENAI_PARAMS,
+    AUDIO_TTS_API_KEY,
     AUDIO_TTS_SPLIT_ON,
-    AUDIO_TTS_VOICE,
     AUDIO_TTS_AZURE_SPEECH_REGION,
     AUDIO_TTS_AZURE_SPEECH_BASE_URL,
     AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT,
@@ -244,6 +248,7 @@ from open_webui.config import (
     EXTERNAL_DOCUMENT_LOADER_API_KEY,
     TIKA_SERVER_URL,
     DOCLING_SERVER_URL,
+    DOCLING_PARAMS,
     DOCLING_DO_OCR,
     DOCLING_FORCE_OCR,
     DOCLING_OCR_ENGINE,
@@ -272,6 +277,7 @@ from open_webui.config import (
     WEB_SEARCH_CONCURRENT_REQUESTS,
     WEB_SEARCH_TRUST_ENV,
     WEB_SEARCH_DOMAIN_FILTER_LIST,
+    OLLAMA_CLOUD_WEB_SEARCH_API_KEY,
     JINA_API_KEY,
     SEARCHAPI_API_KEY,
     SEARCHAPI_ENGINE,
@@ -303,14 +309,17 @@ from open_webui.config import (
     GOOGLE_PSE_ENGINE_ID,
     GOOGLE_DRIVE_CLIENT_ID,
     GOOGLE_DRIVE_API_KEY,
-    ONEDRIVE_CLIENT_ID,
+    ENABLE_ONEDRIVE_INTEGRATION,
+    ONEDRIVE_CLIENT_ID_PERSONAL,
+    ONEDRIVE_CLIENT_ID_BUSINESS,
     ONEDRIVE_SHAREPOINT_URL,
     ONEDRIVE_SHAREPOINT_TENANT_ID,
+    ENABLE_ONEDRIVE_PERSONAL,
+    ENABLE_ONEDRIVE_BUSINESS,
     ENABLE_RAG_HYBRID_SEARCH,
     ENABLE_RAG_LOCAL_WEB_FETCH,
     ENABLE_WEB_LOADER_SSL_VERIFICATION,
     ENABLE_GOOGLE_DRIVE_INTEGRATION,
-    ENABLE_ONEDRIVE_INTEGRATION,
     UPLOAD_DIR,
     EXTERNAL_WEB_SEARCH_URL,
     EXTERNAL_WEB_SEARCH_API_KEY,
@@ -448,6 +457,7 @@ from open_webui.utils.models import (
     get_all_models,
     get_all_base_models,
     check_model_access,
+    get_filtered_models,
 )
 from open_webui.utils.chat import (
     generate_chat_completion as chat_completion_handler,
@@ -466,7 +476,12 @@ from open_webui.utils.auth import (
     get_verified_user,
 )
 from open_webui.utils.plugin import install_tool_and_function_dependencies
-from open_webui.utils.oauth import OAuthManager
+from open_webui.utils.oauth import (
+    OAuthManager,
+    OAuthClientManager,
+    decrypt_data,
+    OAuthClientInformationFull,
+)
 from open_webui.utils.security_headers import SecurityHeadersMiddleware
 from open_webui.utils.redis import get_redis_connection
 
@@ -596,9 +611,14 @@ app = FastAPI(
     lifespan=lifespan,
 )
 
+# For Open WebUI OIDC/OAuth2
 oauth_manager = OAuthManager(app)
 app.state.oauth_manager = oauth_manager
 
+# For Integrations
+oauth_client_manager = OAuthClientManager(app)
+app.state.oauth_client_manager = oauth_client_manager
+
 app.state.instance_id = None
 app.state.config = AppConfig(
     redis_url=REDIS_URL,
@@ -817,6 +837,7 @@ app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = EXTERNAL_DOCUMENT_LOADER_URL
 app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY = EXTERNAL_DOCUMENT_LOADER_API_KEY
 app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
 app.state.config.DOCLING_SERVER_URL = DOCLING_SERVER_URL
+app.state.config.DOCLING_PARAMS = DOCLING_PARAMS
 app.state.config.DOCLING_DO_OCR = DOCLING_DO_OCR
 app.state.config.DOCLING_FORCE_OCR = DOCLING_FORCE_OCR
 app.state.config.DOCLING_OCR_ENGINE = DOCLING_OCR_ENGINE
@@ -882,6 +903,8 @@ app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER = BYPASS_WEB_SEARCH_WEB_LOADER
 
 app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = ENABLE_GOOGLE_DRIVE_INTEGRATION
 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.YACY_QUERY_URL = YACY_QUERY_URL
 app.state.config.YACY_USERNAME = YACY_USERNAME
@@ -1076,11 +1099,15 @@ app.state.config.AUDIO_STT_AZURE_LOCALES = AUDIO_STT_AZURE_LOCALES
 app.state.config.AUDIO_STT_AZURE_BASE_URL = AUDIO_STT_AZURE_BASE_URL
 app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS = AUDIO_STT_AZURE_MAX_SPEAKERS
 
-app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
-app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
 app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE
+
 app.state.config.TTS_MODEL = AUDIO_TTS_MODEL
 app.state.config.TTS_VOICE = AUDIO_TTS_VOICE
+
+app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
+app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
+app.state.config.TTS_OPENAI_PARAMS = AUDIO_TTS_OPENAI_PARAMS
+
 app.state.config.TTS_API_KEY = AUDIO_TTS_API_KEY
 app.state.config.TTS_SPLIT_ON = AUDIO_TTS_SPLIT_ON
 
@@ -1151,12 +1178,32 @@ class RedirectMiddleware(BaseHTTPMiddleware):
             path = request.url.path
             query_params = dict(parse_qs(urlparse(str(request.url)).query))
 
+            redirect_params = {}
+
             # Check for the specific watch path and the presence of 'v' parameter
             if path.endswith("/watch") and "v" in query_params:
                 # Extract the first 'v' parameter
-                video_id = query_params["v"][0]
+                youtube_video_id = query_params["v"][0]
-                encoded_video_id = urlencode({"youtube": video_id})
+                redirect_params["youtube"] = youtube_video_id
-                redirect_url = f"/?{encoded_video_id}"
+
+            if "shared" in query_params and len(query_params["shared"]) > 0:
+                # PWA share_target support
+
+                text = query_params["shared"][0]
+                if text:
+                    urls = re.match(r"https://\S+", text)
+                    if urls:
+                        from open_webui.retrieval.loaders.youtube import _parse_video_id
+
+                        if youtube_video_id := _parse_video_id(urls[0]):
+                            redirect_params["youtube"] = youtube_video_id
+                        else:
+                            redirect_params["load-url"] = urls[0]
+                    else:
+                        redirect_params["q"] = text
+
+            if redirect_params:
+                redirect_url = f"/?{urlencode(redirect_params)}"
                 return RedirectResponse(url=redirect_url)
 
         # Proceed with the normal flow of other requests
@@ -1291,33 +1338,6 @@ if audit_level != AuditLevel.NONE:
 async def get_models(
     request: Request, refresh: bool = False, user=Depends(get_verified_user)
 ):
-    def get_filtered_models(models, user):
-        filtered_models = []
-        for model in models:
-            if model.get("arena"):
-                if has_access(
-                    user.id,
-                    type="read",
-                    access_control=model.get("info", {})
-                    .get("meta", {})
-                    .get("access_control", {}),
-                ):
-                    filtered_models.append(model)
-                continue
-
-            model_info = Models.get_model_by_id(model["id"])
-            if model_info:
-                if (
-                    (user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL)
-                    or user.id == model_info.user_id
-                    or has_access(
-                        user.id, type="read", access_control=model_info.access_control
-                    )
-                ):
-                    filtered_models.append(model)
-
-        return filtered_models
-
     all_models = await get_all_models(request, refresh=refresh, user=user)
 
     models = []
@@ -1353,11 +1373,6 @@ async def get_models(
             )
         )
 
-    # Filter out models that the user does not have access to
-    if (
-        user.role == "user"
-        or (user.role == "admin" and not BYPASS_ADMIN_ACCESS_CONTROL)
-    ) and not BYPASS_MODEL_ACCESS_CONTROL:
     models = get_filtered_models(models, user)
 
     log.debug(
@@ -1487,7 +1502,7 @@ async def chat_completion(
         }
 
         if metadata.get("chat_id") and (user and user.role != "admin"):
-            if metadata["chat_id"] != "local":
+            if not metadata["chat_id"].startswith("local:"):
                 chat = Chats.get_chat_by_id_and_user_id(metadata["chat_id"], user.id)
                 if chat is None:
                     raise HTTPException(
@@ -1514,6 +1529,7 @@ async def chat_completion(
             response = await chat_completion_handler(request, form_data, user)
             if metadata.get("chat_id") and metadata.get("message_id"):
                 try:
+                    if not metadata["chat_id"].startswith("local:"):
                         Chats.upsert_message_to_chat_by_id_and_message_id(
                             metadata["chat_id"],
                             metadata["message_id"],
@@ -1541,6 +1557,7 @@ async def chat_completion(
             if metadata.get("chat_id") and metadata.get("message_id"):
                 # Update the chat message with the error
                 try:
+                    if not metadata["chat_id"].startswith("local:"):
                         Chats.upsert_message_to_chat_by_id_and_message_id(
                             metadata["chat_id"],
                             metadata["message_id"],
@@ -1562,6 +1579,14 @@ async def chat_completion(
 
                 except:
                     pass
+        finally:
+            try:
+                if mcp_clients := metadata.get("mcp_clients"):
+                    for client in mcp_clients.values():
+                        await client.disconnect()
+            except Exception as e:
+                log.debug(f"Error cleaning up: {e}")
+                pass
 
     if (
         metadata.get("session_id")
@@ -1730,6 +1755,14 @@ async def get_app_config(request: Request):
                     "enable_admin_chat_access": ENABLE_ADMIN_CHAT_ACCESS,
                     "enable_google_drive_integration": app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
                     "enable_onedrive_integration": app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
+                    **(
+                        {
+                            "enable_onedrive_personal": ENABLE_ONEDRIVE_PERSONAL,
+                            "enable_onedrive_business": ENABLE_ONEDRIVE_BUSINESS,
+                        }
+                        if app.state.config.ENABLE_ONEDRIVE_INTEGRATION
+                        else {}
+                    ),
                 }
                 if user is not None
                 else {}
@@ -1767,7 +1800,8 @@ async def get_app_config(request: Request):
                     "api_key": GOOGLE_DRIVE_API_KEY.value,
                 },
                 "onedrive": {
-                    "client_id": ONEDRIVE_CLIENT_ID.value,
+                    "client_id_personal": ONEDRIVE_CLIENT_ID_PERSONAL,
+                    "client_id_business": ONEDRIVE_CLIENT_ID_BUSINESS,
                     "sharepoint_url": ONEDRIVE_SHAREPOINT_URL.value,
                     "sharepoint_tenant_id": ONEDRIVE_SHAREPOINT_TENANT_ID.value,
                 },
@@ -1887,17 +1921,76 @@ async def get_current_usage(user=Depends(get_verified_user)):
 # OAuth Login & Callback
 ############################
 
-# SessionMiddleware is used by authlib for oauth
+
-if len(OAUTH_PROVIDERS) > 0:
+# Initialize OAuth client manager with any MCP tool servers using OAuth 2.1
+if len(app.state.config.TOOL_SERVER_CONNECTIONS) > 0:
+    for tool_server_connection in app.state.config.TOOL_SERVER_CONNECTIONS:
+        if tool_server_connection.get("type", "openapi") == "mcp":
+            server_id = tool_server_connection.get("info", {}).get("id")
+            auth_type = tool_server_connection.get("auth_type", "none")
+            if server_id and auth_type == "oauth_2.1":
+                oauth_client_info = tool_server_connection.get("info", {}).get(
+                    "oauth_client_info", ""
+                )
+
+                oauth_client_info = decrypt_data(oauth_client_info)
+                app.state.oauth_client_manager.add_client(
+                    f"mcp:{server_id}", OAuthClientInformationFull(**oauth_client_info)
+                )
+
+try:
+    if REDIS_URL:
+        redis_session_store = RedisStore(
+            url=REDIS_URL,
+            prefix=(f"{REDIS_KEY_PREFIX}:session:" if REDIS_KEY_PREFIX else "session:"),
+        )
+
+        app.add_middleware(SessionAutoloadMiddleware)
+        app.add_middleware(
+            StarSessionsMiddleware,
+            store=redis_session_store,
+            cookie_name="owui-session",
+            cookie_same_site=WEBUI_SESSION_COOKIE_SAME_SITE,
+            cookie_https_only=WEBUI_SESSION_COOKIE_SECURE,
+        )
+        log.info("Using Redis for session")
+    else:
+        raise ValueError("No Redis URL provided")
+except Exception as e:
     app.add_middleware(
         SessionMiddleware,
         secret_key=WEBUI_SECRET_KEY,
-        session_cookie="oui-session",
+        session_cookie="owui-session",
         same_site=WEBUI_SESSION_COOKIE_SAME_SITE,
         https_only=WEBUI_SESSION_COOKIE_SECURE,
     )
 
 
+@app.get("/oauth/clients/{client_id}/authorize")
+async def oauth_client_authorize(
+    client_id: str,
+    request: Request,
+    response: Response,
+    user=Depends(get_verified_user),
+):
+    return await oauth_client_manager.handle_authorize(request, client_id=client_id)
+
+
+@app.get("/oauth/clients/{client_id}/callback")
+async def oauth_client_callback(
+    client_id: str,
+    request: Request,
+    response: Response,
+    user=Depends(get_verified_user),
+):
+    return await oauth_client_manager.handle_callback(
+        request,
+        client_id=client_id,
+        user_id=user.id if user else None,
+        response=response,
+    )
+
+
 @app.get("/oauth/{provider}/login")
 async def oauth_login(provider: str, request: Request):
     return await oauth_manager.handle_login(request, provider)
@@ -1909,8 +2002,9 @@ async def oauth_login(provider: str, request: Request):
 #    - This is considered insecure in general, as OAuth providers do not always verify email addresses
 # 3. If there is no user, and ENABLE_OAUTH_SIGNUP is true, create a user
 #    - Email addresses are considered unique, so we fail registration if the email address is already taken
-@app.get("/oauth/{provider}/callback")
+@app.get("/oauth/{provider}/login/callback")
-async def oauth_callback(provider: str, request: Request, response: Response):
+@app.get("/oauth/{provider}/callback")  # Legacy endpoint
+async def oauth_login_callback(provider: str, request: Request, response: Response):
     return await oauth_manager.handle_callback(request, provider, response)
 
 
@@ -1940,6 +2034,11 @@ async def get_manifest_json():
                     "purpose": "maskable",
                 },
             ],
+            "share_target": {
+                "action": "/",
+                "method": "GET",
+                "params": {"text": "shared"},
+            },
         }
 
 

backend/open_webui/migrations/versions/a5c220713937_add_reply_to_id_column_to_message.py

@@ -0,0 +1,34 @@
+"""Add reply_to_id column to message
+
+Revision ID: a5c220713937
+Revises: 38d63c18f30f
+Create Date: 2025-09-27 02:24:18.058455
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision: str = "a5c220713937"
+down_revision: Union[str, None] = "38d63c18f30f"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Add 'reply_to_id' column to the 'message' table for replying to messages
+    op.add_column(
+        "message",
+        sa.Column("reply_to_id", sa.Text(), nullable=True),
+    )
+    pass
+
+
+def downgrade() -> None:
+    # Remove 'reply_to_id' column from the 'message' table
+    op.drop_column("message", "reply_to_id")
+
+    pass

backend/open_webui/models/channels.py

@@ -57,6 +57,10 @@ class ChannelModel(BaseModel):
 ####################
 
 
+class ChannelResponse(ChannelModel):
+    write_access: bool = False
+
+
 class ChannelForm(BaseModel):
     name: str
     description: Optional[str] = None

backend/open_webui/models/chats.py

@@ -366,6 +366,15 @@ class ChatTable:
         except Exception:
             return False
 
+    def unarchive_all_chats_by_user_id(self, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Chat).filter_by(user_id=user_id).update({"archived": False})
+                db.commit()
+                return True
+        except Exception:
+            return False
+
     def update_chat_share_id_by_id(
         self, id: str, share_id: Optional[str]
     ) -> Optional[ChatModel]:
@@ -492,11 +501,16 @@ class ChatTable:
         self,
         user_id: str,
         include_archived: bool = False,
+        include_folders: bool = False,
         skip: Optional[int] = None,
         limit: Optional[int] = None,
     ) -> list[ChatTitleIdResponse]:
         with get_db() as db:
-            query = db.query(Chat).filter_by(user_id=user_id).filter_by(folder_id=None)
+            query = db.query(Chat).filter_by(user_id=user_id)
+
+            if not include_folders:
+                query = query.filter_by(folder_id=None)
+
             query = query.filter(or_(Chat.pinned == False, Chat.pinned == None))
 
             if not include_archived:
@@ -805,7 +819,7 @@ class ChatTable:
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
     def get_chats_by_folder_id_and_user_id(
-        self, folder_id: str, user_id: str
+        self, folder_id: str, user_id: str, skip: int = 0, limit: int = 60
     ) -> list[ChatModel]:
         with get_db() as db:
             query = db.query(Chat).filter_by(folder_id=folder_id, user_id=user_id)
@@ -814,6 +828,11 @@ class ChatTable:
 
             query = query.order_by(Chat.updated_at.desc())
 
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
             all_chats = query.all()
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
@@ -943,6 +962,16 @@ class ChatTable:
 
             return count
 
+    def count_chats_by_folder_id_and_user_id(self, folder_id: str, user_id: str) -> int:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(user_id=user_id)
+
+            query = query.filter_by(folder_id=folder_id)
+            count = query.count()
+
+            log.info(f"Count of chats for folder '{folder_id}': {count}")
+            return count
+
     def delete_tag_by_id_and_user_id_and_tag_name(
         self, id: str, user_id: str, tag_name: str
     ) -> bool:

backend/open_webui/models/files.py

@@ -130,6 +130,17 @@ class FilesTable:
             except Exception:
                 return None
 
+    def get_file_by_id_and_user_id(self, id: str, user_id: str) -> Optional[FileModel]:
+        with get_db() as db:
+            try:
+                file = db.query(File).filter_by(id=id, user_id=user_id).first()
+                if file:
+                    return FileModel.model_validate(file)
+                else:
+                    return None
+            except Exception:
+                return None
+
     def get_file_metadata_by_id(self, id: str) -> Optional[FileMetadataResponse]:
         with get_db() as db:
             try:

backend/open_webui/models/folders.py

@@ -50,6 +50,20 @@ class FolderModel(BaseModel):
     model_config = ConfigDict(from_attributes=True)
 
 
+class FolderMetadataResponse(BaseModel):
+    icon: Optional[str] = None
+
+
+class FolderNameIdResponse(BaseModel):
+    id: str
+    name: str
+    meta: Optional[FolderMetadataResponse] = None
+    parent_id: Optional[str] = None
+    is_expanded: bool = False
+    created_at: int
+    updated_at: int
+
+
 ####################
 # Forms
 ####################

backend/open_webui/models/messages.py

@@ -5,6 +5,7 @@ from typing import Optional
 
 from open_webui.internal.db import Base, get_db
 from open_webui.models.tags import TagModel, Tag, Tags
+from open_webui.models.users import Users, UserNameResponse
 
 
 from pydantic import BaseModel, ConfigDict
@@ -43,6 +44,7 @@ class Message(Base):
     user_id = Column(Text)
     channel_id = Column(Text, nullable=True)
 
+    reply_to_id = Column(Text, nullable=True)
     parent_id = Column(Text, nullable=True)
 
     content = Column(Text)
@@ -60,6 +62,7 @@ class MessageModel(BaseModel):
     user_id: str
     channel_id: Optional[str] = None
 
+    reply_to_id: Optional[str] = None
     parent_id: Optional[str] = None
 
     content: str
@@ -77,6 +80,7 @@ class MessageModel(BaseModel):
 
 class MessageForm(BaseModel):
     content: str
+    reply_to_id: Optional[str] = None
     parent_id: Optional[str] = None
     data: Optional[dict] = None
     meta: Optional[dict] = None
@@ -88,7 +92,15 @@ class Reactions(BaseModel):
     count: int
 
 
-class MessageResponse(MessageModel):
+class MessageUserResponse(MessageModel):
+    user: Optional[UserNameResponse] = None
+
+
+class MessageReplyToResponse(MessageUserResponse):
+    reply_to_message: Optional[MessageUserResponse] = None
+
+
+class MessageResponse(MessageReplyToResponse):
     latest_reply_at: Optional[int]
     reply_count: int
     reactions: list[Reactions]
@@ -107,6 +119,7 @@ class MessageTable:
                     "id": id,
                     "user_id": user_id,
                     "channel_id": channel_id,
+                    "reply_to_id": form_data.reply_to_id,
                     "parent_id": form_data.parent_id,
                     "content": form_data.content,
                     "data": form_data.data,
@@ -128,19 +141,32 @@ class MessageTable:
             if not message:
                 return None
 
-            reactions = self.get_reactions_by_message_id(id)
+            reply_to_message = (
-            replies = self.get_replies_by_message_id(id)
+                self.get_message_by_id(message.reply_to_id)
+                if message.reply_to_id
+                else None
+            )
 
-            return MessageResponse(
+            reactions = self.get_reactions_by_message_id(id)
-                **{
+            thread_replies = self.get_thread_replies_by_message_id(id)
+
+            user = Users.get_user_by_id(message.user_id)
+            return MessageResponse.model_validate(
+                {
                     **MessageModel.model_validate(message).model_dump(),
-                    "latest_reply_at": replies[0].created_at if replies else None,
+                    "user": user.model_dump() if user else None,
-                    "reply_count": len(replies),
+                    "reply_to_message": (
+                        reply_to_message.model_dump() if reply_to_message else None
+                    ),
+                    "latest_reply_at": (
+                        thread_replies[0].created_at if thread_replies else None
+                    ),
+                    "reply_count": len(thread_replies),
                     "reactions": reactions,
                 }
             )
 
-    def get_replies_by_message_id(self, id: str) -> list[MessageModel]:
+    def get_thread_replies_by_message_id(self, id: str) -> list[MessageReplyToResponse]:
         with get_db() as db:
             all_messages = (
                 db.query(Message)
@@ -148,7 +174,27 @@ class MessageTable:
                 .order_by(Message.created_at.desc())
                 .all()
             )
-            return [MessageModel.model_validate(message) for message in all_messages]
+
+            messages = []
+            for message in all_messages:
+                reply_to_message = (
+                    self.get_message_by_id(message.reply_to_id)
+                    if message.reply_to_id
+                    else None
+                )
+                messages.append(
+                    MessageReplyToResponse.model_validate(
+                        {
+                            **MessageModel.model_validate(message).model_dump(),
+                            "reply_to_message": (
+                                reply_to_message.model_dump()
+                                if reply_to_message
+                                else None
+                            ),
+                        }
+                    )
+                )
+            return messages
 
     def get_reply_user_ids_by_message_id(self, id: str) -> list[str]:
         with get_db() as db:
@@ -159,7 +205,7 @@ class MessageTable:
 
     def get_messages_by_channel_id(
         self, channel_id: str, skip: int = 0, limit: int = 50
-    ) -> list[MessageModel]:
+    ) -> list[MessageReplyToResponse]:
         with get_db() as db:
             all_messages = (
                 db.query(Message)
@@ -169,11 +215,31 @@ class MessageTable:
                 .limit(limit)
                 .all()
             )
-            return [MessageModel.model_validate(message) for message in all_messages]
+
+            messages = []
+            for message in all_messages:
+                reply_to_message = (
+                    self.get_message_by_id(message.reply_to_id)
+                    if message.reply_to_id
+                    else None
+                )
+                messages.append(
+                    MessageReplyToResponse.model_validate(
+                        {
+                            **MessageModel.model_validate(message).model_dump(),
+                            "reply_to_message": (
+                                reply_to_message.model_dump()
+                                if reply_to_message
+                                else None
+                            ),
+                        }
+                    )
+                )
+            return messages
 
     def get_messages_by_parent_id(
         self, channel_id: str, parent_id: str, skip: int = 0, limit: int = 50
-    ) -> list[MessageModel]:
+    ) -> list[MessageReplyToResponse]:
         with get_db() as db:
             message = db.get(Message, parent_id)
 
@@ -193,7 +259,26 @@ class MessageTable:
             if len(all_messages) < limit:
                 all_messages.append(message)
 
-            return [MessageModel.model_validate(message) for message in all_messages]
+            messages = []
+            for message in all_messages:
+                reply_to_message = (
+                    self.get_message_by_id(message.reply_to_id)
+                    if message.reply_to_id
+                    else None
+                )
+                messages.append(
+                    MessageReplyToResponse.model_validate(
+                        {
+                            **MessageModel.model_validate(message).model_dump(),
+                            "reply_to_message": (
+                                reply_to_message.model_dump()
+                                if reply_to_message
+                                else None
+                            ),
+                        }
+                    )
+                )
+            return messages
 
     def update_message_by_id(
         self, id: str, form_data: MessageForm
@@ -201,8 +286,14 @@ class MessageTable:
         with get_db() as db:
             message = db.get(Message, id)
             message.content = form_data.content
-            message.data = form_data.data
+            message.data = {
-            message.meta = form_data.meta
+                **(message.data if message.data else {}),
+                **(form_data.data if form_data.data else {}),
+            }
+            message.meta = {
+                **(message.meta if message.meta else {}),
+                **(form_data.meta if form_data.meta else {}),
+            }
             message.updated_at = int(time.time_ns())
             db.commit()
             db.refresh(message)

backend/open_webui/models/notes.py

@@ -2,6 +2,7 @@ import json
 import time
 import uuid
 from typing import Optional
+from functools import lru_cache
 
 from open_webui.internal.db import Base, get_db
 from open_webui.models.groups import Groups
@@ -110,20 +111,72 @@ class NoteTable:
             return [NoteModel.model_validate(note) for note in notes]
 
     def get_notes_by_user_id(
+        self,
+        user_id: str,
+        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())
+
+            if skip is not None:
+                query = query.offset(skip)
+            if limit is not None:
+                query = query.limit(limit)
+
+            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]:
-        notes = self.get_notes(skip=skip, limit=limit)
+        with get_db() as db:
-        user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user_id)}
+            user_groups = Groups.get_groups_by_member_id(user_id)
-        return [
+            user_group_ids = {group.id for group in user_groups}
-            note
+
-            for note in notes
+            # Order newest-first. We stream to keep memory usage low.
-            if note.user_id == user_id
+            query = (
-            or has_access(user_id, permission, note.access_control, user_group_ids)
+                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:

backend/open_webui/models/oauth_sessions.py

@@ -176,6 +176,26 @@ class OAuthSessionTable:
             log.error(f"Error getting OAuth session by ID: {e}")
             return None
 
+    def get_session_by_provider_and_user_id(
+        self, provider: str, user_id: str
+    ) -> Optional[OAuthSessionModel]:
+        """Get OAuth session by provider and user ID"""
+        try:
+            with get_db() as db:
+                session = (
+                    db.query(OAuthSession)
+                    .filter_by(provider=provider, user_id=user_id)
+                    .first()
+                )
+                if session:
+                    session.token = self._decrypt_token(session.token)
+                    return OAuthSessionModel.model_validate(session)
+
+                return None
+        except Exception as e:
+            log.error(f"Error getting OAuth session by provider and user ID: {e}")
+            return None
+
     def get_sessions_by_user_id(self, user_id: str) -> List[OAuthSessionModel]:
         """Get all OAuth sessions for a user"""
         try:

backend/open_webui/models/tools.py

@@ -95,6 +95,8 @@ class ToolResponse(BaseModel):
 class ToolUserResponse(ToolResponse):
     user: Optional[UserResponse] = None
 
+    model_config = ConfigDict(extra="allow")
+
 
 class ToolForm(BaseModel):
     id: str

backend/open_webui/models/users.py

@@ -107,11 +107,21 @@ class UserInfoResponse(BaseModel):
     role: str
 
 
+class UserIdNameResponse(BaseModel):
+    id: str
+    name: str
+
+
 class UserInfoListResponse(BaseModel):
     users: list[UserInfoResponse]
     total: int
 
 
+class UserIdNameListResponse(BaseModel):
+    users: list[UserIdNameResponse]
+    total: int
+
+
 class UserResponse(BaseModel):
     id: str
     name: str
@@ -210,7 +220,7 @@ class UsersTable:
         filter: Optional[dict] = None,
         skip: Optional[int] = None,
         limit: Optional[int] = None,
-    ) -> UserListResponse:
+    ) -> dict:
         with get_db() as db:
             query = db.query(User)
 

backend/open_webui/retrieval/loaders/main.py

@@ -346,11 +346,9 @@ class Loader:
             self.engine == "document_intelligence"
             and self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT") != ""
             and (
-                file_ext in ["pdf", "xls", "xlsx", "docx", "ppt", "pptx"]
+                file_ext in ["pdf", "docx", "ppt", "pptx"]
                 or file_content_type
                 in [
-                    "application/vnd.ms-excel",
-                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                     "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                     "application/vnd.ms-powerpoint",
                     "application/vnd.openxmlformats-officedocument.presentationml.presentation",

backend/open_webui/retrieval/utils.py

@@ -127,7 +127,13 @@ def query_doc_with_hybrid_search(
     hybrid_bm25_weight: float,
 ) -> dict:
     try:
-        if not collection_result.documents[0]:
+        if (
+            not collection_result
+            or not hasattr(collection_result, "documents")
+            or not collection_result.documents
+            or len(collection_result.documents) == 0
+            or not collection_result.documents[0]
+        ):
             log.warning(f"query_doc_with_hybrid_search:no_docs {collection_name}")
             return {"documents": [], "metadatas": [], "distances": []}
 
@@ -621,6 +627,7 @@ def get_sources_from_items(
 
                 if knowledge_base and (
                     user.role == "admin"
+                    or knowledge_base.user_id == user.id
                     or has_access(user.id, "read", knowledge_base.access_control)
                 ):
 

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

@@ -11,7 +11,7 @@ from open_webui.retrieval.vector.main import (
     SearchResult,
     GetResult,
 )
-from open_webui.retrieval.vector.utils import stringify_metadata
+from open_webui.retrieval.vector.utils import process_metadata
 
 from open_webui.config import (
     CHROMA_DATA_PATH,
@@ -146,7 +146,7 @@ class ChromaClient(VectorDBBase):
         ids = [item["id"] for item in items]
         documents = [item["text"] for item in items]
         embeddings = [item["vector"] for item in items]
-        metadatas = [stringify_metadata(item["metadata"]) for item in items]
+        metadatas = [process_metadata(item["metadata"]) for item in items]
 
         for batch in create_batches(
             api=self.client,
@@ -166,7 +166,7 @@ class ChromaClient(VectorDBBase):
         ids = [item["id"] for item in items]
         documents = [item["text"] for item in items]
         embeddings = [item["vector"] for item in items]
-        metadatas = [stringify_metadata(item["metadata"]) for item in items]
+        metadatas = [process_metadata(item["metadata"]) for item in items]
 
         collection.upsert(
             ids=ids, documents=documents, embeddings=embeddings, metadatas=metadatas

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

@@ -3,7 +3,7 @@ from typing import Optional
 import ssl
 from elasticsearch.helpers import bulk, scan
 
-from open_webui.retrieval.vector.utils import stringify_metadata
+from open_webui.retrieval.vector.utils import process_metadata
 from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
@@ -245,7 +245,7 @@ class ElasticsearchClient(VectorDBBase):
                         "collection": collection_name,
                         "vector": item["vector"],
                         "text": item["text"],
-                        "metadata": stringify_metadata(item["metadata"]),
+                        "metadata": process_metadata(item["metadata"]),
                     },
                 }
                 for item in batch
@@ -266,7 +266,7 @@ class ElasticsearchClient(VectorDBBase):
                         "collection": collection_name,
                         "vector": item["vector"],
                         "text": item["text"],
-                        "metadata": stringify_metadata(item["metadata"]),
+                        "metadata": process_metadata(item["metadata"]),
                     },
                     "doc_as_upsert": True,
                 }

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

@@ -6,7 +6,7 @@ import json
 import logging
 from typing import Optional
 
-from open_webui.retrieval.vector.utils import stringify_metadata
+from open_webui.retrieval.vector.utils import process_metadata
 from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
@@ -22,6 +22,8 @@ from open_webui.config import (
     MILVUS_HNSW_M,
     MILVUS_HNSW_EFCONSTRUCTION,
     MILVUS_IVF_FLAT_NLIST,
+    MILVUS_DISKANN_MAX_DEGREE,
+    MILVUS_DISKANN_SEARCH_LIST_SIZE,
 )
 from open_webui.env import SRC_LOG_LEVELS
 
@@ -131,12 +133,18 @@ class MilvusClient(VectorDBBase):
         elif index_type == "IVF_FLAT":
             index_creation_params = {"nlist": MILVUS_IVF_FLAT_NLIST}
             log.info(f"IVF_FLAT params: {index_creation_params}")
+        elif index_type == "DISKANN":
+            index_creation_params = {
+                "max_degree": MILVUS_DISKANN_MAX_DEGREE,
+                "search_list_size": MILVUS_DISKANN_SEARCH_LIST_SIZE,
+            }
+            log.info(f"DISKANN params: {index_creation_params}")
         elif index_type in ["FLAT", "AUTOINDEX"]:
             log.info(f"Using {index_type} index with no specific build-time params.")
         else:
             log.warning(
                 f"Unsupported MILVUS_INDEX_TYPE: '{index_type}'. "
-                f"Supported types: HNSW, IVF_FLAT, FLAT, AUTOINDEX. "
+                f"Supported types: HNSW, IVF_FLAT, DISKANN, FLAT, AUTOINDEX. "
                 f"Milvus will use its default for the collection if this type is not directly supported for index creation."
             )
             # For unsupported types, pass the type directly to Milvus; it might handle it or use a default.
@@ -189,7 +197,7 @@ class MilvusClient(VectorDBBase):
         )
         return self._result_to_search_result(result)
 
-    def query(self, collection_name: str, filter: dict, limit: Optional[int] = None):
+    def query(self, collection_name: str, filter: dict, limit: int = -1):
         connections.connect(uri=MILVUS_URI, token=MILVUS_TOKEN, db_name=MILVUS_DB)
 
         # Construct the filter string for querying
@@ -222,7 +230,7 @@ class MilvusClient(VectorDBBase):
                     "data",
                     "metadata",
                 ],
-                limit=limit,  # Pass the limit directly; None means no limit.
+                limit=limit,  # Pass the limit directly; -1 means no limit.
             )
 
             while True:
@@ -249,7 +257,7 @@ class MilvusClient(VectorDBBase):
         )
         # Using query with a trivial filter to get all items.
         # This will use the paginated query logic.
-        return self.query(collection_name=collection_name, filter={}, limit=None)
+        return self.query(collection_name=collection_name, filter={}, limit=-1)
 
     def insert(self, collection_name: str, items: list[VectorItem]):
         # Insert the items into the collection, if the collection does not exist, it will be created.
@@ -281,7 +289,7 @@ class MilvusClient(VectorDBBase):
                     "id": item["id"],
                     "vector": item["vector"],
                     "data": {"text": item["text"]},
-                    "metadata": stringify_metadata(item["metadata"]),
+                    "metadata": process_metadata(item["metadata"]),
                 }
                 for item in items
             ],
@@ -317,7 +325,7 @@ class MilvusClient(VectorDBBase):
                     "id": item["id"],
                     "vector": item["vector"],
                     "data": {"text": item["text"]},
-                    "metadata": stringify_metadata(item["metadata"]),
+                    "metadata": process_metadata(item["metadata"]),
                 }
                 for item in items
             ],

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

@@ -0,0 +1,282 @@
+import logging
+from typing import Optional, Tuple, List, Dict, Any
+
+from open_webui.config import (
+    MILVUS_URI,
+    MILVUS_TOKEN,
+    MILVUS_DB,
+    MILVUS_COLLECTION_PREFIX,
+    MILVUS_INDEX_TYPE,
+    MILVUS_METRIC_TYPE,
+    MILVUS_HNSW_M,
+    MILVUS_HNSW_EFCONSTRUCTION,
+    MILVUS_IVF_FLAT_NLIST,
+)
+from open_webui.env import SRC_LOG_LEVELS
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from pymilvus import (
+    connections,
+    utility,
+    Collection,
+    CollectionSchema,
+    FieldSchema,
+    DataType,
+)
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+RESOURCE_ID_FIELD = "resource_id"
+
+
+class MilvusClient(VectorDBBase):
+    def __init__(self):
+        # Milvus collection names can only contain numbers, letters, and underscores.
+        self.collection_prefix = MILVUS_COLLECTION_PREFIX.replace("-", "_")
+        connections.connect(
+            alias="default",
+            uri=MILVUS_URI,
+            token=MILVUS_TOKEN,
+            db_name=MILVUS_DB,
+        )
+
+        # Main collection types for multi-tenancy
+        self.MEMORY_COLLECTION = f"{self.collection_prefix}_memories"
+        self.KNOWLEDGE_COLLECTION = f"{self.collection_prefix}_knowledge"
+        self.FILE_COLLECTION = f"{self.collection_prefix}_files"
+        self.WEB_SEARCH_COLLECTION = f"{self.collection_prefix}_web_search"
+        self.HASH_BASED_COLLECTION = f"{self.collection_prefix}_hash_based"
+        self.shared_collections = [
+            self.MEMORY_COLLECTION,
+            self.KNOWLEDGE_COLLECTION,
+            self.FILE_COLLECTION,
+            self.WEB_SEARCH_COLLECTION,
+            self.HASH_BASED_COLLECTION,
+        ]
+
+    def _get_collection_and_resource_id(self, collection_name: str) -> Tuple[str, str]:
+        """
+        Maps the traditional collection name to multi-tenant collection and resource ID.
+
+        WARNING: This mapping relies on current Open WebUI naming conventions for
+        collection names. If Open WebUI changes how it generates collection names
+        (e.g., "user-memory-" prefix, "file-" prefix, web search patterns, or hash
+        formats), this mapping will break and route data to incorrect collections.
+        POTENTIALLY CAUSING HUGE DATA CORRUPTION, DATA CONSISTENCY ISSUES AND INCORRECT
+        DATA MAPPING INSIDE THE DATABASE.
+        """
+        resource_id = collection_name
+
+        if collection_name.startswith("user-memory-"):
+            return self.MEMORY_COLLECTION, resource_id
+        elif collection_name.startswith("file-"):
+            return self.FILE_COLLECTION, resource_id
+        elif collection_name.startswith("web-search-"):
+            return self.WEB_SEARCH_COLLECTION, resource_id
+        elif len(collection_name) == 63 and all(
+            c in "0123456789abcdef" for c in collection_name
+        ):
+            return self.HASH_BASED_COLLECTION, resource_id
+        else:
+            return self.KNOWLEDGE_COLLECTION, resource_id
+
+    def _create_shared_collection(self, mt_collection_name: str, dimension: int):
+        fields = [
+            FieldSchema(
+                name="id",
+                dtype=DataType.VARCHAR,
+                is_primary=True,
+                auto_id=False,
+                max_length=36,
+            ),
+            FieldSchema(name="vector", dtype=DataType.FLOAT_VECTOR, dim=dimension),
+            FieldSchema(name="text", dtype=DataType.VARCHAR, max_length=65535),
+            FieldSchema(name="metadata", dtype=DataType.JSON),
+            FieldSchema(name=RESOURCE_ID_FIELD, dtype=DataType.VARCHAR, max_length=255),
+        ]
+        schema = CollectionSchema(fields, "Shared collection for multi-tenancy")
+        collection = Collection(mt_collection_name, schema)
+
+        index_params = {
+            "metric_type": MILVUS_METRIC_TYPE,
+            "index_type": MILVUS_INDEX_TYPE,
+            "params": {},
+        }
+        if MILVUS_INDEX_TYPE == "HNSW":
+            index_params["params"] = {
+                "M": MILVUS_HNSW_M,
+                "efConstruction": MILVUS_HNSW_EFCONSTRUCTION,
+            }
+        elif MILVUS_INDEX_TYPE == "IVF_FLAT":
+            index_params["params"] = {"nlist": MILVUS_IVF_FLAT_NLIST}
+
+        collection.create_index("vector", index_params)
+        collection.create_index(RESOURCE_ID_FIELD)
+        log.info(f"Created shared collection: {mt_collection_name}")
+        return collection
+
+    def _ensure_collection(self, mt_collection_name: str, dimension: int):
+        if not utility.has_collection(mt_collection_name):
+            self._create_shared_collection(mt_collection_name, dimension)
+
+    def has_collection(self, collection_name: str) -> bool:
+        mt_collection, resource_id = self._get_collection_and_resource_id(
+            collection_name
+        )
+        if not utility.has_collection(mt_collection):
+            return False
+
+        collection = Collection(mt_collection)
+        collection.load()
+        res = collection.query(expr=f"{RESOURCE_ID_FIELD} == '{resource_id}'", limit=1)
+        return len(res) > 0
+
+    def upsert(self, collection_name: str, items: List[VectorItem]):
+        if not items:
+            return
+        mt_collection, resource_id = self._get_collection_and_resource_id(
+            collection_name
+        )
+        dimension = len(items[0]["vector"])
+        self._ensure_collection(mt_collection, dimension)
+        collection = Collection(mt_collection)
+
+        entities = [
+            {
+                "id": item["id"],
+                "vector": item["vector"],
+                "text": item["text"],
+                "metadata": item["metadata"],
+                RESOURCE_ID_FIELD: resource_id,
+            }
+            for item in items
+        ]
+        collection.insert(entities)
+        collection.flush()
+
+    def search(
+        self, collection_name: str, vectors: List[List[float]], limit: int
+    ) -> Optional[SearchResult]:
+        if not vectors:
+            return None
+
+        mt_collection, resource_id = self._get_collection_and_resource_id(
+            collection_name
+        )
+        if not utility.has_collection(mt_collection):
+            return None
+
+        collection = Collection(mt_collection)
+        collection.load()
+
+        search_params = {"metric_type": MILVUS_METRIC_TYPE, "params": {}}
+        results = collection.search(
+            data=vectors,
+            anns_field="vector",
+            param=search_params,
+            limit=limit,
+            expr=f"{RESOURCE_ID_FIELD} == '{resource_id}'",
+            output_fields=["id", "text", "metadata"],
+        )
+
+        ids, documents, metadatas, distances = [], [], [], []
+        for hits in results:
+            batch_ids, batch_docs, batch_metadatas, batch_dists = [], [], [], []
+            for hit in hits:
+                batch_ids.append(hit.entity.get("id"))
+                batch_docs.append(hit.entity.get("text"))
+                batch_metadatas.append(hit.entity.get("metadata"))
+                batch_dists.append(hit.distance)
+            ids.append(batch_ids)
+            documents.append(batch_docs)
+            metadatas.append(batch_metadatas)
+            distances.append(batch_dists)
+
+        return SearchResult(
+            ids=ids, documents=documents, metadatas=metadatas, distances=distances
+        )
+
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[List[str]] = None,
+        filter: Optional[Dict[str, Any]] = None,
+    ):
+        mt_collection, resource_id = self._get_collection_and_resource_id(
+            collection_name
+        )
+        if not utility.has_collection(mt_collection):
+            return
+
+        collection = Collection(mt_collection)
+
+        # Build expression
+        expr = [f"{RESOURCE_ID_FIELD} == '{resource_id}'"]
+        if ids:
+            # Milvus expects a string list for 'in' operator
+            id_list_str = ", ".join([f"'{id_val}'" for id_val in ids])
+            expr.append(f"id in [{id_list_str}]")
+
+        if filter:
+            for key, value in filter.items():
+                expr.append(f"metadata['{key}'] == '{value}'")
+
+        collection.delete(" and ".join(expr))
+
+    def reset(self):
+        for collection_name in self.shared_collections:
+            if utility.has_collection(collection_name):
+                utility.drop_collection(collection_name)
+
+    def delete_collection(self, collection_name: str):
+        mt_collection, resource_id = self._get_collection_and_resource_id(
+            collection_name
+        )
+        if not utility.has_collection(mt_collection):
+            return
+
+        collection = Collection(mt_collection)
+        collection.delete(f"{RESOURCE_ID_FIELD} == '{resource_id}'")
+
+    def query(
+        self, collection_name: str, filter: Dict[str, Any], limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        mt_collection, resource_id = self._get_collection_and_resource_id(
+            collection_name
+        )
+        if not utility.has_collection(mt_collection):
+            return None
+
+        collection = Collection(mt_collection)
+        collection.load()
+
+        expr = [f"{RESOURCE_ID_FIELD} == '{resource_id}'"]
+        if filter:
+            for key, value in filter.items():
+                if isinstance(value, str):
+                    expr.append(f"metadata['{key}'] == '{value}'")
+                else:
+                    expr.append(f"metadata['{key}'] == {value}")
+
+        results = collection.query(
+            expr=" and ".join(expr),
+            output_fields=["id", "text", "metadata"],
+            limit=limit,
+        )
+
+        ids = [res["id"] for res in results]
+        documents = [res["text"] for res in results]
+        metadatas = [res["metadata"] for res in results]
+
+        return GetResult(ids=[ids], documents=[documents], metadatas=[metadatas])
+
+    def get(self, collection_name: str) -> Optional[GetResult]:
+        return self.query(collection_name, filter={}, limit=None)
+
+    def insert(self, collection_name: str, items: List[VectorItem]):
+        return self.upsert(collection_name, items)

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

@@ -2,7 +2,7 @@ from opensearchpy import OpenSearch
 from opensearchpy.helpers import bulk
 from typing import Optional
 
-from open_webui.retrieval.vector.utils import stringify_metadata
+from open_webui.retrieval.vector.utils import process_metadata
 from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
@@ -201,7 +201,7 @@ class OpenSearchClient(VectorDBBase):
                     "_source": {
                         "vector": item["vector"],
                         "text": item["text"],
-                        "metadata": stringify_metadata(item["metadata"]),
+                        "metadata": process_metadata(item["metadata"]),
                     },
                 }
                 for item in batch
@@ -223,7 +223,7 @@ class OpenSearchClient(VectorDBBase):
                     "doc": {
                         "vector": item["vector"],
                         "text": item["text"],
-                        "metadata": stringify_metadata(item["metadata"]),
+                        "metadata": process_metadata(item["metadata"]),
                     },
                     "doc_as_upsert": True,
                 }

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

@@ -27,7 +27,7 @@ from sqlalchemy.ext.mutable import MutableDict
 from sqlalchemy.exc import NoSuchTableError
 
 
-from open_webui.retrieval.vector.utils import stringify_metadata
+from open_webui.retrieval.vector.utils import process_metadata
 from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
@@ -265,7 +265,7 @@ class PgvectorClient(VectorDBBase):
                         vector=vector,
                         collection_name=collection_name,
                         text=item["text"],
-                        vmetadata=stringify_metadata(item["metadata"]),
+                        vmetadata=process_metadata(item["metadata"]),
                     )
                     new_items.append(new_chunk)
                 self.session.bulk_save_objects(new_items)
@@ -323,7 +323,7 @@ class PgvectorClient(VectorDBBase):
                     if existing:
                         existing.vector = vector
                         existing.text = item["text"]
-                        existing.vmetadata = stringify_metadata(item["metadata"])
+                        existing.vmetadata = process_metadata(item["metadata"])
                         existing.collection_name = (
                             collection_name  # Update collection_name if necessary
                         )
@@ -333,7 +333,7 @@ class PgvectorClient(VectorDBBase):
                             vector=vector,
                             collection_name=collection_name,
                             text=item["text"],
-                            vmetadata=stringify_metadata(item["metadata"]),
+                            vmetadata=process_metadata(item["metadata"]),
                         )
                         self.session.add(new_chunk)
                 self.session.commit()

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

@@ -32,7 +32,7 @@ from open_webui.config import (
     PINECONE_CLOUD,
 )
 from open_webui.env import SRC_LOG_LEVELS
-from open_webui.retrieval.vector.utils import stringify_metadata
+from open_webui.retrieval.vector.utils import process_metadata
 
 
 NO_LIMIT = 10000  # Reasonable limit to avoid overwhelming the system
@@ -185,7 +185,7 @@ class PineconeClient(VectorDBBase):
             point = {
                 "id": item["id"],
                 "values": item["vector"],
-                "metadata": stringify_metadata(metadata),
+                "metadata": process_metadata(metadata),
             }
             points.append(point)
         return points

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

@@ -105,6 +105,13 @@ class QdrantClient(VectorDBBase):
 
         Returns:
             tuple: (collection_name, tenant_id)
+
+        WARNING: This mapping relies on current Open WebUI naming conventions for
+        collection names. If Open WebUI changes how it generates collection names
+        (e.g., "user-memory-" prefix, "file-" prefix, web search patterns, or hash
+        formats), this mapping will break and route data to incorrect collections.
+        POTENTIALLY CAUSING HUGE DATA CORRUPTION, DATA CONSISTENCY ISSUES AND INCORRECT
+        DATA MAPPING INSIDE THE DATABASE.
         """
         # Check for user memory collections
         tenant_id = collection_name

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

@@ -1,4 +1,4 @@
-from open_webui.retrieval.vector.utils import stringify_metadata
+from open_webui.retrieval.vector.utils import process_metadata
 from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
@@ -185,7 +185,7 @@ class S3VectorClient(VectorDBBase):
                 metadata["text"] = item["text"]
 
                 # Convert metadata to string format for consistency
-                metadata = stringify_metadata(metadata)
+                metadata = process_metadata(metadata)
 
                 # Filter metadata to comply with S3 Vector API limit of 10 keys
                 metadata = self._filter_metadata(metadata, item["id"])
@@ -256,7 +256,7 @@ class S3VectorClient(VectorDBBase):
                 metadata["text"] = item["text"]
 
                 # Convert metadata to string format for consistency
-                metadata = stringify_metadata(metadata)
+                metadata = process_metadata(metadata)
 
                 # Filter metadata to comply with S3 Vector API limit of 10 keys
                 metadata = self._filter_metadata(metadata, item["id"])

backend/open_webui/retrieval/vector/factory.py

@@ -1,6 +1,10 @@
 from open_webui.retrieval.vector.main import VectorDBBase
 from open_webui.retrieval.vector.type import VectorType
-from open_webui.config import VECTOR_DB, ENABLE_QDRANT_MULTITENANCY_MODE
+from open_webui.config import (
+    VECTOR_DB,
+    ENABLE_QDRANT_MULTITENANCY_MODE,
+    ENABLE_MILVUS_MULTITENANCY_MODE,
+)
 
 
 class Vector:
@@ -12,6 +16,13 @@ class Vector:
         """
         match vector_type:
             case VectorType.MILVUS:
+                if ENABLE_MILVUS_MULTITENANCY_MODE:
+                    from open_webui.retrieval.vector.dbs.milvus_multitenancy import (
+                        MilvusClient,
+                    )
+
+                    return MilvusClient()
+                else:
                     from open_webui.retrieval.vector.dbs.milvus import MilvusClient
 
                     return MilvusClient()

backend/open_webui/retrieval/vector/utils.py

@@ -1,10 +1,24 @@
 from datetime import datetime
 
+KEYS_TO_EXCLUDE = ["content", "pages", "tables", "paragraphs", "sections", "figures"]
 
-def stringify_metadata(
+
+def filter_metadata(metadata: dict[str, any]) -> dict[str, any]:
+    metadata = {
+        key: value for key, value in metadata.items() if key not in KEYS_TO_EXCLUDE
+    }
+    return metadata
+
+
+def process_metadata(
     metadata: dict[str, any],
 ) -> dict[str, any]:
     for key, value in metadata.items():
+        # Remove large fields
+        if key in KEYS_TO_EXCLUDE:
+            del metadata[key]
+
+        # Convert non-serializable fields to strings
         if (
             isinstance(value, datetime)
             or isinstance(value, list)

backend/open_webui/retrieval/web/ollama.py

@@ -0,0 +1,51 @@
+import logging
+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"])
+
+
+def search_ollama_cloud(
+    url: str,
+    api_key: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    """Search using Ollama Search API and return the results as a list of SearchResult objects.
+
+    Args:
+        api_key (str): A Ollama Search API key
+        query (str): The query to search for
+        count (int): Number of results to return
+        filter_list (Optional[list[str]]): List of domains to filter results by
+    """
+    log.info(f"Searching with Ollama for query: {query}")
+
+    headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
+    payload = {"query": query, "max_results": count}
+
+    try:
+        response = requests.post(f"{url}/api/web_search", headers=headers, json=payload)
+        response.raise_for_status()
+        data = response.json()
+
+        results = data.get("results", [])
+        log.info(f"Found {len(results)} results")
+
+        return [
+            SearchResult(
+                link=result.get("url", ""),
+                title=result.get("title", ""),
+                snippet=result.get("content", ""),
+            )
+            for result in results
+        ]
+    except Exception as e:
+        log.error(f"Error searching Ollama: {e}")
+        return []

backend/open_webui/retrieval/web/perplexity_search.py

@@ -0,0 +1,64 @@
+import logging
+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
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def search_perplexity_search(
+    api_key: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    """Search using Perplexity API and return the results as a list of SearchResult objects.
+
+    Args:
+      api_key (str): A Perplexity API key
+      query (str): The query to search for
+      count (int): Maximum number of results to return
+      filter_list (Optional[list[str]]): List of domains to filter results
+
+    """
+
+    # Handle PersistentConfig object
+    if hasattr(api_key, "__str__"):
+        api_key = str(api_key)
+
+    try:
+        url = "https://api.perplexity.ai/search"
+
+        # Create payload for the API call
+        payload = {
+            "query": query,
+            "max_results": count,
+        }
+
+        headers = {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+        }
+
+        # Make the API request
+        response = requests.request("POST", url, json=payload, headers=headers)
+        # Parse the JSON response
+        json_response = response.json()
+
+        # Extract citations from the response
+        results = json_response.get("results", [])
+
+        return [
+            SearchResult(
+                link=result["url"], title=result["title"], snippet=result["snippet"]
+            )
+            for result in results
+        ]
+
+    except Exception as e:
+        log.error(f"Error searching with Perplexity Search API: {e}")
+        return []

backend/open_webui/routers/audio.py

@@ -3,6 +3,7 @@ import json
 import logging
 import os
 import uuid
+import html
 from functools import lru_cache
 from pydub import AudioSegment
 from pydub.silence import split_on_silence
@@ -153,6 +154,7 @@ def set_faster_whisper_model(model: str, auto_update: bool = False):
 class TTSConfigForm(BaseModel):
     OPENAI_API_BASE_URL: str
     OPENAI_API_KEY: str
+    OPENAI_PARAMS: Optional[dict] = None
     API_KEY: str
     ENGINE: str
     MODEL: str
@@ -189,6 +191,7 @@ async def get_audio_config(request: Request, user=Depends(get_admin_user)):
         "tts": {
             "OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
             "OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
+            "OPENAI_PARAMS": request.app.state.config.TTS_OPENAI_PARAMS,
             "API_KEY": request.app.state.config.TTS_API_KEY,
             "ENGINE": request.app.state.config.TTS_ENGINE,
             "MODEL": request.app.state.config.TTS_MODEL,
@@ -221,6 +224,7 @@ async def update_audio_config(
 ):
     request.app.state.config.TTS_OPENAI_API_BASE_URL = form_data.tts.OPENAI_API_BASE_URL
     request.app.state.config.TTS_OPENAI_API_KEY = form_data.tts.OPENAI_API_KEY
+    request.app.state.config.TTS_OPENAI_PARAMS = form_data.tts.OPENAI_PARAMS
     request.app.state.config.TTS_API_KEY = form_data.tts.API_KEY
     request.app.state.config.TTS_ENGINE = form_data.tts.ENGINE
     request.app.state.config.TTS_MODEL = form_data.tts.MODEL
@@ -261,12 +265,13 @@ async def update_audio_config(
 
     return {
         "tts": {
-            "OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
-            "OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
-            "API_KEY": request.app.state.config.TTS_API_KEY,
             "ENGINE": request.app.state.config.TTS_ENGINE,
             "MODEL": request.app.state.config.TTS_MODEL,
             "VOICE": request.app.state.config.TTS_VOICE,
+            "OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
+            "OPENAI_PARAMS": request.app.state.config.TTS_OPENAI_PARAMS,
+            "API_KEY": request.app.state.config.TTS_API_KEY,
             "SPLIT_ON": request.app.state.config.TTS_SPLIT_ON,
             "AZURE_SPEECH_REGION": request.app.state.config.TTS_AZURE_SPEECH_REGION,
             "AZURE_SPEECH_BASE_URL": request.app.state.config.TTS_AZURE_SPEECH_BASE_URL,
@@ -336,6 +341,11 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             async with aiohttp.ClientSession(
                 timeout=timeout, trust_env=True
             ) as session:
+                payload = {
+                    **payload,
+                    **(request.app.state.config.TTS_OPENAI_PARAMS or {}),
+                }
+
                 r = await session.post(
                     url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
                     json=payload,
@@ -458,7 +468,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
 
         try:
             data = f"""<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="{locale}">
-                <voice name="{language}">{payload["input"]}</voice>
+                <voice name="{language}">{html.escape(payload["input"])}</voice>
             </speak>"""
             timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
             async with aiohttp.ClientSession(
@@ -550,7 +560,7 @@ def transcription_handler(request, file_path, metadata):
     metadata = metadata or {}
 
     languages = [
-        metadata.get("language", None) if WHISPER_LANGUAGE == "" else WHISPER_LANGUAGE,
+        metadata.get("language", None) if not WHISPER_LANGUAGE else WHISPER_LANGUAGE,
         None,  # Always fallback to None in case transcription fails
     ]
 

backend/open_webui/routers/channels.py

@@ -10,7 +10,13 @@ from pydantic import BaseModel
 from open_webui.socket.main import sio, get_user_ids_from_room
 from open_webui.models.users import Users, UserNameResponse
 
-from open_webui.models.channels import Channels, ChannelModel, ChannelForm
+from open_webui.models.groups import Groups
+from open_webui.models.channels import (
+    Channels,
+    ChannelModel,
+    ChannelForm,
+    ChannelResponse,
+)
 from open_webui.models.messages import (
     Messages,
     MessageModel,
@@ -24,9 +30,17 @@ from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import SRC_LOG_LEVELS
 
 
+from open_webui.utils.models import (
+    get_all_models,
+    get_filtered_models,
+)
+from open_webui.utils.chat import generate_chat_completion
+
+
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.utils.access_control import has_access, get_users_with_access
 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"])
@@ -72,7 +86,7 @@ async def create_new_channel(form_data: ChannelForm, user=Depends(get_admin_user
 ############################
 
 
-@router.get("/{id}", response_model=Optional[ChannelModel])
+@router.get("/{id}", response_model=Optional[ChannelResponse])
 async def get_channel_by_id(id: str, user=Depends(get_verified_user)):
     channel = Channels.get_channel_by_id(id)
     if not channel:
@@ -87,7 +101,16 @@ async def get_channel_by_id(id: str, user=Depends(get_verified_user)):
             status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
         )
 
-    return ChannelModel(**channel.model_dump())
+    write_access = has_access(
+        user.id, type="write", access_control=channel.access_control, strict=False
+    )
+
+    return ChannelResponse(
+        **{
+            **channel.model_dump(),
+            "write_access": write_access or user.role == "admin",
+        }
+    )
 
 
 ############################
@@ -144,7 +167,7 @@ async def delete_channel_by_id(id: str, user=Depends(get_admin_user)):
 
 
 class MessageUserResponse(MessageResponse):
-    user: UserNameResponse
+    pass
 
 
 @router.get("/{id}/messages", response_model=list[MessageUserResponse])
@@ -173,15 +196,17 @@ async def get_channel_messages(
             user = Users.get_user_by_id(message.user_id)
             users[message.user_id] = user
 
-        replies = Messages.get_replies_by_message_id(message.id)
+        thread_replies = Messages.get_thread_replies_by_message_id(message.id)
-        latest_reply_at = replies[0].created_at if replies else None
+        latest_thread_reply_at = (
+            thread_replies[0].created_at if thread_replies else None
+        )
 
         messages.append(
             MessageUserResponse(
                 **{
                     **message.model_dump(),
-                    "reply_count": len(replies),
+                    "reply_count": len(thread_replies),
-                    "latest_reply_at": latest_reply_at,
+                    "latest_reply_at": latest_thread_reply_at,
                     "reactions": Messages.get_reactions_by_message_id(message.id),
                     "user": UserNameResponse(**users[message.user_id].model_dump()),
                 }
@@ -200,14 +225,11 @@ async def send_notification(name, webui_url, channel, message, active_user_ids):
     users = get_users_with_access("read", channel.access_control)
 
     for user in users:
-        if user.id in active_user_ids:
+        if user.id not in active_user_ids:
-            continue
-        else:
             if user.settings:
                 webhook_url = user.settings.ui.get("notifications", {}).get(
                     "webhook_url", None
                 )
-
                 if webhook_url:
                     await post_webhook(
                         name,
@@ -221,14 +243,169 @@ async def send_notification(name, webui_url, channel, message, active_user_ids):
                         },
                     )
 
+    return True
 
-@router.post("/{id}/messages/post", response_model=Optional[MessageModel])
+
-async def post_new_message(
+async def model_response_handler(request, channel, message, user):
-    request: Request,
+    MODELS = {
-    id: str,
+        model["id"]: model
-    form_data: MessageForm,
+        for model in get_filtered_models(await get_all_models(request, user=user), user)
-    background_tasks: BackgroundTasks,
+    }
-    user=Depends(get_verified_user),
+
+    mentions = extract_mentions(message.content)
+    message_content = replace_mentions(message.content)
+
+    model_mentions = {}
+
+    # check if the message is a reply to a message sent by a model
+    if (
+        message.reply_to_message
+        and message.reply_to_message.meta
+        and message.reply_to_message.meta.get("model_id", None)
+    ):
+        model_id = message.reply_to_message.meta.get("model_id", None)
+        model_mentions[model_id] = {"id": model_id, "id_type": "M"}
+
+    # check if any of the mentions are models
+    for mention in mentions:
+        if mention["id_type"] == "M" and mention["id"] not in model_mentions:
+            model_mentions[mention["id"]] = mention
+
+    if not model_mentions:
+        return False
+
+    for mention in model_mentions.values():
+        model_id = mention["id"]
+        model = MODELS.get(model_id, None)
+
+        if model:
+            try:
+                # reverse to get in chronological order
+                thread_messages = Messages.get_messages_by_parent_id(
+                    channel.id,
+                    message.parent_id if message.parent_id else message.id,
+                )[::-1]
+
+                response_message, channel = await new_message_handler(
+                    request,
+                    channel.id,
+                    MessageForm(
+                        **{
+                            "parent_id": (
+                                message.parent_id if message.parent_id else message.id
+                            ),
+                            "content": f"",
+                            "data": {},
+                            "meta": {
+                                "model_id": model_id,
+                                "model_name": model.get("name", model_id),
+                            },
+                        }
+                    ),
+                    user,
+                )
+
+                thread_history = []
+                images = []
+                message_users = {}
+
+                for thread_message in thread_messages:
+                    message_user = None
+                    if thread_message.user_id not in message_users:
+                        message_user = Users.get_user_by_id(thread_message.user_id)
+                        message_users[thread_message.user_id] = message_user
+                    else:
+                        message_user = message_users[thread_message.user_id]
+
+                    if thread_message.meta and thread_message.meta.get(
+                        "model_id", None
+                    ):
+                        # If the message was sent by a model, use the model name
+                        message_model_id = thread_message.meta.get("model_id", None)
+                        message_model = MODELS.get(message_model_id, None)
+                        username = (
+                            message_model.get("name", message_model_id)
+                            if message_model
+                            else message_model_id
+                        )
+                    else:
+                        username = message_user.name if message_user else "Unknown"
+
+                    thread_history.append(
+                        f"{username}: {replace_mentions(thread_message.content)}"
+                    )
+
+                    thread_message_files = thread_message.data.get("files", [])
+                    for file in thread_message_files:
+                        if file.get("type", "") == "image":
+                            images.append(file.get("url", ""))
+
+                system_message = {
+                    "role": "system",
+                    "content": f"You are {model.get('name', model_id)}, participating in a threaded conversation. Be concise and conversational."
+                    + (
+                        f"Here's the thread history:\n\n{''.join([f'{msg}' for msg in thread_history])}\n\nContinue the conversation naturally as {model.get('name', model_id)}, addressing the most recent message while being aware of the full context."
+                        if thread_history
+                        else ""
+                    ),
+                }
+
+                content = f"{user.name if user else 'User'}: {message_content}"
+                if images:
+                    content = [
+                        {
+                            "type": "text",
+                            "text": content,
+                        },
+                        *[
+                            {
+                                "type": "image_url",
+                                "image_url": {
+                                    "url": image,
+                                },
+                            }
+                            for image in images
+                        ],
+                    ]
+
+                form_data = {
+                    "model": model_id,
+                    "messages": [
+                        system_message,
+                        {"role": "user", "content": content},
+                    ],
+                    "stream": False,
+                }
+
+                res = await generate_chat_completion(
+                    request,
+                    form_data=form_data,
+                    user=user,
+                )
+
+                if res:
+                    await update_message_by_id(
+                        channel.id,
+                        response_message.id,
+                        MessageForm(
+                            **{
+                                "content": res["choices"][0]["message"]["content"],
+                                "meta": {
+                                    "done": True,
+                                },
+                            }
+                        ),
+                        user,
+                    )
+            except Exception as e:
+                log.info(e)
+                pass
+
+    return True
+
+
+async def new_message_handler(
+    request: Request, id: str, form_data: MessageForm, user=Depends(get_verified_user)
 ):
     channel = Channels.get_channel_by_id(id)
     if not channel:
@@ -237,7 +414,7 @@ async def post_new_message(
         )
 
     if user.role != "admin" and not has_access(
-        user.id, type="read", access_control=channel.access_control
+        user.id, type="write", access_control=channel.access_control, strict=False
     ):
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
@@ -245,31 +422,21 @@ async def post_new_message(
 
     try:
         message = Messages.insert_new_message(form_data, channel.id, user.id)
-
         if message:
+            message = Messages.get_message_by_id(message.id)
             event_data = {
                 "channel_id": channel.id,
                 "message_id": message.id,
                 "data": {
                     "type": "message",
-                    "data": MessageUserResponse(
+                    "data": message.model_dump(),
-                        **{
-                            **message.model_dump(),
-                            "reply_count": 0,
-                            "latest_reply_at": None,
-                            "reactions": Messages.get_reactions_by_message_id(
-                                message.id
-                            ),
-                            "user": UserNameResponse(**user.model_dump()),
-                        }
-                    ).model_dump(),
                 },
                 "user": UserNameResponse(**user.model_dump()).model_dump(),
                 "channel": channel.model_dump(),
             }
 
             await sio.emit(
-                "channel-events",
+                "events:channel",
                 event_data,
                 to=f"channel:{channel.id}",
             )
@@ -280,33 +447,45 @@ async def post_new_message(
 
                 if parent_message:
                     await sio.emit(
-                        "channel-events",
+                        "events:channel",
                         {
                             "channel_id": channel.id,
                             "message_id": parent_message.id,
                             "data": {
                                 "type": "message:reply",
-                                "data": MessageUserResponse(
+                                "data": parent_message.model_dump(),
-                                    **{
-                                        **parent_message.model_dump(),
-                                        "user": UserNameResponse(
-                                            **Users.get_user_by_id(
-                                                parent_message.user_id
-                                            ).model_dump()
-                                        ),
-                                    }
-                                ).model_dump(),
                             },
                             "user": UserNameResponse(**user.model_dump()).model_dump(),
                             "channel": channel.model_dump(),
                         },
                         to=f"channel:{channel.id}",
                     )
+            return message, channel
+        else:
+            raise Exception("Error creating message")
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+        )
 
+
+@router.post("/{id}/messages/post", response_model=Optional[MessageModel])
+async def post_new_message(
+    request: Request,
+    id: str,
+    form_data: MessageForm,
+    background_tasks: BackgroundTasks,
+    user=Depends(get_verified_user),
+):
+
+    try:
+        message, channel = await new_message_handler(request, id, form_data, user)
         active_user_ids = get_user_ids_from_room(f"channel:{channel.id}")
 
-            background_tasks.add_task(
+        async def background_handler():
-                send_notification,
+            await model_response_handler(request, channel, message, user)
+            await send_notification(
                 request.app.state.WEBUI_NAME,
                 request.app.state.config.WEBUI_URL,
                 channel,
@@ -314,7 +493,12 @@ async def post_new_message(
                 active_user_ids,
             )
 
-        return MessageModel(**message.model_dump())
+        background_tasks.add_task(background_handler)
+
+        return message
+
+    except HTTPException as e:
+        raise e
     except Exception as e:
         log.exception(e)
         raise HTTPException(
@@ -460,20 +644,13 @@ async def update_message_by_id(
 
         if message:
             await sio.emit(
-                "channel-events",
+                "events:channel",
                 {
                     "channel_id": channel.id,
                     "message_id": message.id,
                     "data": {
                         "type": "message:update",
-                        "data": MessageUserResponse(
+                        "data": message.model_dump(),
-                            **{
-                                **message.model_dump(),
-                                "user": UserNameResponse(
-                                    **user.model_dump()
-                                ).model_dump(),
-                            }
-                        ).model_dump(),
                     },
                     "user": UserNameResponse(**user.model_dump()).model_dump(),
                     "channel": channel.model_dump(),
@@ -509,7 +686,7 @@ async def add_reaction_to_message(
         )
 
     if user.role != "admin" and not has_access(
-        user.id, type="read", access_control=channel.access_control
+        user.id, type="write", access_control=channel.access_control, strict=False
     ):
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
@@ -531,7 +708,7 @@ async def add_reaction_to_message(
         message = Messages.get_message_by_id(message_id)
 
         await sio.emit(
-            "channel-events",
+            "events:channel",
             {
                 "channel_id": channel.id,
                 "message_id": message.id,
@@ -539,9 +716,6 @@ async def add_reaction_to_message(
                     "type": "message:reaction:add",
                     "data": {
                         **message.model_dump(),
-                        "user": UserNameResponse(
-                            **Users.get_user_by_id(message.user_id).model_dump()
-                        ).model_dump(),
                         "name": form_data.name,
                     },
                 },
@@ -575,7 +749,7 @@ async def remove_reaction_by_id_and_user_id_and_name(
         )
 
     if user.role != "admin" and not has_access(
-        user.id, type="read", access_control=channel.access_control
+        user.id, type="write", access_control=channel.access_control, strict=False
     ):
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
@@ -600,7 +774,7 @@ async def remove_reaction_by_id_and_user_id_and_name(
         message = Messages.get_message_by_id(message_id)
 
         await sio.emit(
-            "channel-events",
+            "events:channel",
             {
                 "channel_id": channel.id,
                 "message_id": message.id,
@@ -608,9 +782,6 @@ async def remove_reaction_by_id_and_user_id_and_name(
                     "type": "message:reaction:remove",
                     "data": {
                         **message.model_dump(),
-                        "user": UserNameResponse(
-                            **Users.get_user_by_id(message.user_id).model_dump()
-                        ).model_dump(),
                         "name": form_data.name,
                     },
                 },
@@ -657,7 +828,9 @@ async def delete_message_by_id(
     if (
         user.role != "admin"
         and message.user_id != user.id
-        and not has_access(user.id, type="read", access_control=channel.access_control)
+        and not has_access(
+            user.id, type="write", access_control=channel.access_control, strict=False
+        )
     ):
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
@@ -666,7 +839,7 @@ async def delete_message_by_id(
     try:
         Messages.delete_message_by_id(message_id)
         await sio.emit(
-            "channel-events",
+            "events:channel",
             {
                 "channel_id": channel.id,
                 "message_id": message.id,
@@ -689,22 +862,13 @@ async def delete_message_by_id(
 
             if parent_message:
                 await sio.emit(
-                    "channel-events",
+                    "events:channel",
                     {
                         "channel_id": channel.id,
                         "message_id": parent_message.id,
                         "data": {
                             "type": "message:reply",
-                            "data": MessageUserResponse(
+                            "data": parent_message.model_dump(),
-                                **{
-                                    **parent_message.model_dump(),
-                                    "user": UserNameResponse(
-                                        **Users.get_user_by_id(
-                                            parent_message.user_id
-                                        ).model_dump()
-                                    ),
-                                }
-                            ).model_dump(),
                         },
                         "user": UserNameResponse(**user.model_dump()).model_dump(),
                         "channel": channel.model_dump(),

backend/open_webui/routers/chats.py

@@ -37,7 +37,9 @@ router = APIRouter()
 @router.get("/", response_model=list[ChatTitleIdResponse])
 @router.get("/list", response_model=list[ChatTitleIdResponse])
 def get_session_user_chat_list(
-    user=Depends(get_verified_user), page: Optional[int] = None
+    user=Depends(get_verified_user),
+    page: Optional[int] = None,
+    include_folders: Optional[bool] = False,
 ):
     try:
         if page is not None:
@@ -45,10 +47,12 @@ def get_session_user_chat_list(
             skip = (page - 1) * limit
 
             return Chats.get_chat_title_id_list_by_user_id(
-                user.id, skip=skip, limit=limit
+                user.id, include_folders=include_folders, skip=skip, limit=limit
             )
         else:
-            return Chats.get_chat_title_id_list_by_user_id(user.id)
+            return Chats.get_chat_title_id_list_by_user_id(
+                user.id, include_folders=include_folders
+            )
     except Exception as e:
         log.exception(e)
         raise HTTPException(
@@ -166,7 +170,7 @@ async def import_chat(form_data: ChatImportForm, user=Depends(get_verified_user)
 
 
 @router.get("/search", response_model=list[ChatTitleIdResponse])
-async def search_user_chats(
+def search_user_chats(
     text: str, page: Optional[int] = None, user=Depends(get_verified_user)
 ):
     if page is None:
@@ -214,6 +218,28 @@ async def get_chats_by_folder_id(folder_id: str, user=Depends(get_verified_user)
     ]
 
 
+@router.get("/folder/{folder_id}/list")
+async def get_chat_list_by_folder_id(
+    folder_id: str, page: Optional[int] = 1, user=Depends(get_verified_user)
+):
+    try:
+        limit = 60
+        skip = (page - 1) * limit
+
+        return [
+            {"title": chat.title, "id": chat.id, "updated_at": chat.updated_at}
+            for chat in Chats.get_chats_by_folder_id_and_user_id(
+                folder_id, user.id, skip=skip, limit=limit
+            )
+        ]
+
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
 ############################
 # GetPinnedChats
 ############################
@@ -335,6 +361,16 @@ async def archive_all_chats(user=Depends(get_verified_user)):
     return Chats.archive_all_chats_by_user_id(user.id)
 
 
+############################
+# UnarchiveAllChats
+############################
+
+
+@router.post("/unarchive/all", response_model=bool)
+async def unarchive_all_chats(user=Depends(get_verified_user)):
+    return Chats.unarchive_all_chats_by_user_id(user.id)
+
+
 ############################
 # GetSharedChatById
 ############################

backend/open_webui/routers/configs.py

@@ -1,5 +1,7 @@
+import logging
 from fastapi import APIRouter, Depends, Request, HTTPException
 from pydantic import BaseModel, ConfigDict
+import aiohttp
 
 from typing import Optional
 
@@ -12,10 +14,24 @@ from open_webui.utils.tools import (
     get_tool_server_url,
     set_tool_servers,
 )
+from open_webui.utils.mcp.client import MCPClient
 
+from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.utils.oauth import (
+    get_discovery_urls,
+    get_oauth_client_info_with_dynamic_client_registration,
+    encrypt_data,
+    decrypt_data,
+    OAuthClientInformationFull,
+)
+from mcp.shared.auth import OAuthMetadata
 
 router = APIRouter()
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
+
 
 ############################
 # ImportConfig
@@ -79,6 +95,43 @@ async def set_connections_config(
     }
 
 
+class OAuthClientRegistrationForm(BaseModel):
+    url: str
+    client_id: str
+    client_name: Optional[str] = None
+
+
+@router.post("/oauth/clients/register")
+async def register_oauth_client(
+    request: Request,
+    form_data: OAuthClientRegistrationForm,
+    type: Optional[str] = None,
+    user=Depends(get_admin_user),
+):
+    try:
+        oauth_client_id = form_data.client_id
+        if type:
+            oauth_client_id = f"{type}:{form_data.client_id}"
+
+        oauth_client_info = (
+            await get_oauth_client_info_with_dynamic_client_registration(
+                request, oauth_client_id, form_data.url
+            )
+        )
+        return {
+            "status": True,
+            "oauth_client_info": encrypt_data(
+                oauth_client_info.model_dump(mode="json")
+            ),
+        }
+    except Exception as e:
+        log.debug(f"Failed to register OAuth client: {e}")
+        raise HTTPException(
+            status_code=400,
+            detail=f"Failed to register OAuth client",
+        )
+
+
 ############################
 # ToolServers Config
 ############################
@@ -87,6 +140,7 @@ async def set_connections_config(
 class ToolServerConnection(BaseModel):
     url: str
     path: str
+    type: Optional[str] = "openapi"  # openapi, mcp
     auth_type: Optional[str]
     key: Optional[str]
     config: Optional[dict]
@@ -114,8 +168,29 @@ async def set_tool_servers_config(
     request.app.state.config.TOOL_SERVER_CONNECTIONS = [
         connection.model_dump() for connection in form_data.TOOL_SERVER_CONNECTIONS
     ]
+
     await set_tool_servers(request)
 
+    for connection in request.app.state.config.TOOL_SERVER_CONNECTIONS:
+        server_type = connection.get("type", "openapi")
+        if server_type == "mcp":
+            server_id = connection.get("info", {}).get("id")
+            auth_type = connection.get("auth_type", "none")
+            if auth_type == "oauth_2.1" and server_id:
+                try:
+                    oauth_client_info = connection.get("info", {}).get(
+                        "oauth_client_info", ""
+                    )
+                    oauth_client_info = decrypt_data(oauth_client_info)
+
+                    await request.app.state.oauth_client_manager.add_client(
+                        f"{server_type}:{server_id}",
+                        OAuthClientInformationFull(**oauth_client_info),
+                    )
+                except Exception as e:
+                    log.debug(f"Failed to add OAuth client for MCP tool server: {e}")
+                    continue
+
     return {
         "TOOL_SERVER_CONNECTIONS": request.app.state.config.TOOL_SERVER_CONNECTIONS,
     }
@@ -129,19 +204,106 @@ async def verify_tool_servers_config(
     Verify the connection to the tool server.
     """
     try:
+        if form_data.type == "mcp":
+            if form_data.auth_type == "oauth_2.1":
+                discovery_urls = get_discovery_urls(form_data.url)
+                for discovery_url in discovery_urls:
+                    log.debug(
+                        f"Trying to fetch OAuth 2.1 discovery document from {discovery_url}"
+                    )
+                    async with aiohttp.ClientSession() as session:
+                        async with session.get(
+                            discovery_url
+                        ) as oauth_server_metadata_response:
+                            if oauth_server_metadata_response.status == 200:
+                                try:
+                                    oauth_server_metadata = (
+                                        OAuthMetadata.model_validate(
+                                            await oauth_server_metadata_response.json()
+                                        )
+                                    )
+                                    return {
+                                        "status": True,
+                                        "oauth_server_metadata": oauth_server_metadata.model_dump(
+                                            mode="json"
+                                        ),
+                                    }
+                                except Exception as e:
+                                    log.info(
+                                        f"Failed to parse OAuth 2.1 discovery document: {e}"
+                                    )
+                                    raise HTTPException(
+                                        status_code=400,
+                                        detail=f"Failed to parse OAuth 2.1 discovery document from {discovery_urls[0]}",
+                                    )
+
+                raise HTTPException(
+                    status_code=400,
+                    detail=f"Failed to fetch OAuth 2.1 discovery document from {discovery_urls}",
+                )
+            else:
+                try:
+                    client = MCPClient()
+                    headers = None
 
                     token = None
                     if form_data.auth_type == "bearer":
                         token = form_data.key
                     elif form_data.auth_type == "session":
                         token = request.state.token.credentials
+                    elif form_data.auth_type == "system_oauth":
+                        try:
+                            if request.cookies.get("oauth_session_id", None):
+                                token = await request.app.state.oauth_manager.get_oauth_token(
+                                    user.id,
+                                    request.cookies.get("oauth_session_id", None),
+                                )
+                        except Exception as e:
+                            pass
+
+                    if token:
+                        headers = {"Authorization": f"Bearer {token}"}
+
+                    await client.connect(form_data.url, headers=headers)
+                    specs = await client.list_tool_specs()
+                    return {
+                        "status": True,
+                        "specs": specs,
+                    }
+                except Exception as e:
+                    log.debug(f"Failed to create MCP client: {e}")
+                    raise HTTPException(
+                        status_code=400,
+                        detail=f"Failed to create MCP client",
+                    )
+                finally:
+                    if client:
+                        await client.disconnect()
+        else:  # openapi
+            token = None
+            if form_data.auth_type == "bearer":
+                token = form_data.key
+            elif form_data.auth_type == "session":
+                token = request.state.token.credentials
+            elif form_data.auth_type == "system_oauth":
+                try:
+                    if request.cookies.get("oauth_session_id", None):
+                        token = await request.app.state.oauth_manager.get_oauth_token(
+                            user.id,
+                            request.cookies.get("oauth_session_id", None),
+                        )
+                except Exception as e:
+                    pass
 
             url = get_tool_server_url(form_data.url, form_data.path)
             return await get_tool_server_data(token, url)
+    except HTTPException as e:
+        raise e
     except Exception as e:
+        log.debug(f"Failed to connect to the tool server: {e}")
         raise HTTPException(
             status_code=400,
-            detail=f"Failed to connect to the tool server: {str(e)}",
+            detail=f"Failed to connect to the tool server",
         )
 
 

backend/open_webui/routers/files.py

@@ -120,11 +120,6 @@ 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)
-
-        Files.update_file_data_by_id(
-            file_item.id,
-            {"status": "completed"},
-        )
     except Exception as e:
         log.error(f"Error processing file: {file_item.id}")
         Files.update_file_data_by_id(

backend/open_webui/routers/folders.py

@@ -12,6 +12,7 @@ from open_webui.models.folders import (
     FolderForm,
     FolderUpdateForm,
     FolderModel,
+    FolderNameIdResponse,
     Folders,
 )
 from open_webui.models.chats import Chats
@@ -44,7 +45,7 @@ router = APIRouter()
 ############################
 
 
-@router.get("/", response_model=list[FolderModel])
+@router.get("/", response_model=list[FolderNameIdResponse])
 async def get_folders(user=Depends(get_verified_user)):
     folders = Folders.get_folders_by_user_id(user.id)
 
@@ -76,14 +77,6 @@ async def get_folders(user=Depends(get_verified_user)):
     return [
         {
             **folder.model_dump(),
-            "items": {
-                "chats": [
-                    {"title": chat.title, "id": chat.id, "updated_at": chat.updated_at}
-                    for chat in Chats.get_chats_by_folder_id_and_user_id(
-                        folder.id, user.id
-                    )
-                ]
-            },
         }
         for folder in folders
     ]
@@ -262,10 +255,10 @@ async def update_folder_is_expanded_by_id(
 async def delete_folder_by_id(
     request: Request, id: str, user=Depends(get_verified_user)
 ):
+    if Chats.count_chats_by_folder_id_and_user_id(id, user.id):
         chat_delete_permission = has_permission(
             user.id, "chat.delete", request.app.state.config.USER_PERMISSIONS
         )
-
         if user.role != "admin" and not chat_delete_permission:
             raise HTTPException(
                 status_code=status.HTTP_403_FORBIDDEN,

backend/open_webui/routers/functions.py

@@ -148,6 +148,18 @@ async def sync_functions(
                 content=function.content,
             )
 
+            if hasattr(function_module, "Valves") and function.valves:
+                Valves = function_module.Valves
+                try:
+                    Valves(
+                        **{k: v for k, v in function.valves.items() if v is not None}
+                    )
+                except Exception as e:
+                    log.exception(
+                        f"Error validating valves for function {function.id}: {e}"
+                    )
+                    raise e
+
         return Functions.sync_functions(user.id, form_data.functions)
     except Exception as e:
         log.exception(f"Failed to load a function: {e}")
@@ -419,8 +431,10 @@ async def update_function_valves_by_id(
             try:
                 form_data = {k: v for k, v in form_data.items() if v is not None}
                 valves = Valves(**form_data)
-                Functions.update_function_valves_by_id(id, valves.model_dump())
+
-                return valves.model_dump()
+                valves_dict = valves.model_dump(exclude_unset=True)
+                Functions.update_function_valves_by_id(id, valves_dict)
+                return valves_dict
             except Exception as e:
                 log.exception(f"Error updating function values by id {id}: {e}")
                 raise HTTPException(
@@ -502,10 +516,11 @@ async def update_function_user_valves_by_id(
             try:
                 form_data = {k: v for k, v in form_data.items() if v is not None}
                 user_valves = UserValves(**form_data)
+                user_valves_dict = user_valves.model_dump(exclude_unset=True)
                 Functions.update_user_valves_by_id_and_user_id(
-                    id, user.id, user_valves.model_dump()
+                    id, user.id, user_valves_dict
                 )
-                return user_valves.model_dump()
+                return user_valves_dict
             except Exception as e:
                 log.exception(f"Error updating function user valves by id {id}: {e}")
                 raise HTTPException(

backend/open_webui/routers/images.py

@@ -514,6 +514,7 @@ async def image_generations(
         size = form_data.size
 
     width, height = tuple(map(int, size.split("x")))
+    model = get_image_model(request)
 
     r = None
     try:
@@ -531,11 +532,7 @@ async def image_generations(
                 headers["X-OpenWebUI-User-Role"] = user.role
 
             data = {
-                "model": (
+                "model": model,
-                    request.app.state.config.IMAGE_GENERATION_MODEL
-                    if request.app.state.config.IMAGE_GENERATION_MODEL != ""
-                    else "dall-e-2"
-                ),
                 "prompt": form_data.prompt,
                 "n": form_data.n,
                 "size": (
@@ -584,7 +581,6 @@ async def image_generations(
             headers["Content-Type"] = "application/json"
             headers["x-goog-api-key"] = request.app.state.config.IMAGES_GEMINI_API_KEY
 
-            model = get_image_model(request)
             data = {
                 "instances": {"prompt": form_data.prompt},
                 "parameters": {
@@ -640,7 +636,7 @@ async def image_generations(
                 }
             )
             res = await comfyui_generate_image(
-                request.app.state.config.IMAGE_GENERATION_MODEL,
+                model,
                 form_data,
                 user.id,
                 request.app.state.config.COMFYUI_BASE_URL,

backend/open_webui/routers/models.py

@@ -1,4 +1,9 @@
 from typing import Optional
+import io
+import base64
+import json
+import asyncio
+import logging
 
 from open_webui.models.models import (
     ModelForm,
@@ -10,12 +15,22 @@ from open_webui.models.models import (
 
 from pydantic import BaseModel
 from open_webui.constants import ERROR_MESSAGES
-from fastapi import APIRouter, Depends, HTTPException, Request, status
+from fastapi import (
+    APIRouter,
+    Depends,
+    HTTPException,
+    Request,
+    status,
+    Response,
+)
+from fastapi.responses import FileResponse, StreamingResponse
 
 
 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.config import BYPASS_ADMIN_ACCESS_CONTROL
+from open_webui.config import BYPASS_ADMIN_ACCESS_CONTROL, STATIC_DIR
+
+log = logging.getLogger(__name__)
 
 router = APIRouter()
 
@@ -90,6 +105,50 @@ async def export_models(user=Depends(get_admin_user)):
     return Models.get_models()
 
 
+############################
+# ImportModels
+############################
+
+
+class ModelsImportForm(BaseModel):
+    models: list[dict]
+
+
+@router.post("/import", response_model=bool)
+async def import_models(
+    user: str = Depends(get_admin_user), form_data: ModelsImportForm = (...)
+):
+    try:
+        data = form_data.models
+        if isinstance(data, list):
+            for model_data in data:
+                # Here, you can add logic to validate model_data if needed
+                model_id = model_data.get("id")
+                if model_id:
+                    existing_model = Models.get_model_by_id(model_id)
+                    if existing_model:
+                        # Update existing model
+                        model_data["meta"] = model_data.get("meta", {})
+                        model_data["params"] = model_data.get("params", {})
+
+                        updated_model = ModelForm(
+                            **{**existing_model.model_dump(), **model_data}
+                        )
+                        Models.update_model_by_id(model_id, updated_model)
+                    else:
+                        # Insert new model
+                        model_data["meta"] = model_data.get("meta", {})
+                        model_data["params"] = model_data.get("params", {})
+                        new_model = ModelForm(**model_data)
+                        Models.insert_new_model(user_id=user.id, form_data=new_model)
+            return True
+        else:
+            raise HTTPException(status_code=400, detail="Invalid JSON format")
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
 ############################
 # SyncModels
 ############################
@@ -129,6 +188,39 @@ async def get_model_by_id(id: str, user=Depends(get_verified_user)):
         )
 
 
+###########################
+# GetModelById
+###########################
+
+
+@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)
+    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},
+                )
+            elif model.meta.profile_image_url.startswith("data:image"):
+                try:
+                    header, base64_data = model.meta.profile_image_url.split(",", 1)
+                    image_data = base64.b64decode(base64_data)
+                    image_buffer = io.BytesIO(image_data)
+
+                    return StreamingResponse(
+                        image_buffer,
+                        media_type="image/png",
+                        headers={"Content-Disposition": "inline; filename=image.png"},
+                    )
+                except Exception as e:
+                    pass
+        return FileResponse(f"{STATIC_DIR}/favicon.png")
+    else:
+        return FileResponse(f"{STATIC_DIR}/favicon.png")
+
+
 ############################
 # ToggleModelById
 ############################

backend/open_webui/routers/notes.py

@@ -48,7 +48,7 @@ async def get_notes(request: Request, user=Depends(get_verified_user)):
                 "user": UserResponse(**Users.get_user_by_id(note.user_id).model_dump()),
             }
         )
-        for note in Notes.get_notes_by_user_id(user.id, "write")
+        for note in Notes.get_notes_by_permission(user.id, "write")
     ]
 
     return notes
@@ -81,7 +81,9 @@ async def get_note_list(
 
     notes = [
         NoteTitleIdResponse(**note.model_dump())
-        for note in Notes.get_notes_by_user_id(user.id, "write", skip=skip, limit=limit)
+        for note in Notes.get_notes_by_permission(
+            user.id, "write", skip=skip, limit=limit
+        )
     ]
 
     return notes
@@ -178,6 +180,18 @@ async def update_note_by_id(
             status_code=status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.DEFAULT()
         )
 
+    # Check if user can share publicly
+    if (
+        user.role != "admin"
+        and form_data.access_control == None
+        and not has_permission(
+            user.id,
+            "sharing.public_notes",
+            request.app.state.config.USER_PERMISSIONS,
+        )
+    ):
+        form_data.access_control = {}
+
     try:
         note = Notes.update_note_by_id(id, form_data)
         await sio.emit(

backend/open_webui/routers/ollama.py

@@ -1020,6 +1020,10 @@ class GenerateEmbedForm(BaseModel):
     options: Optional[dict] = None
     keep_alive: Optional[Union[int, str]] = None
 
+    model_config = ConfigDict(
+        extra="allow",
+    )
+
 
 @router.post("/api/embed")
 @router.post("/api/embed/{url_idx}")
@@ -1694,13 +1698,15 @@ async def download_file_stream(
                     yield f'data: {{"progress": {progress}, "completed": {current_size}, "total": {total_size}}}\n\n'
 
                 if done:
-                    file.seek(0)
+                    file.close()
+
+                    with open(file_path, "rb") as file:
                         chunk_size = 1024 * 1024 * 2
                         hashed = calculate_sha256(file, chunk_size)
-                    file.seek(0)
 
                         url = f"{ollama_url}/api/blobs/sha256:{hashed}"
-                    response = requests.post(url, data=file)
+                        with requests.Session() as session:
+                            response = session.post(url, data=file, timeout=30)
 
                             if response.ok:
                                 res = {

backend/open_webui/routers/openai.py

@@ -9,6 +9,8 @@ from aiocache import cached
 import requests
 from urllib.parse import quote
 
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
 from fastapi import Depends, HTTPException, Request, APIRouter
 from fastapi.responses import (
     FileResponse,
@@ -119,7 +121,7 @@ def openai_reasoning_model_handler(payload):
     return payload
 
 
-def get_headers_and_cookies(
+async def get_headers_and_cookies(
     request: Request,
     url,
     key=None,
@@ -172,7 +174,7 @@ def get_headers_and_cookies(
         oauth_token = None
         try:
             if request.cookies.get("oauth_session_id", None):
-                oauth_token = request.app.state.oauth_manager.get_oauth_token(
+                oauth_token = await request.app.state.oauth_manager.get_oauth_token(
                     user.id,
                     request.cookies.get("oauth_session_id", None),
                 )
@@ -182,12 +184,30 @@ def get_headers_and_cookies(
         if oauth_token:
             token = f"{oauth_token.get('access_token', '')}"
 
+    elif auth_type in ("azure_ad", "microsoft_entra_id"):
+        token = get_microsoft_entra_id_access_token()
+
     if token:
         headers["Authorization"] = f"Bearer {token}"
 
     return headers, cookies
 
 
+def get_microsoft_entra_id_access_token():
+    """
+    Get Microsoft Entra ID access token using DefaultAzureCredential for Azure OpenAI.
+    Returns the token string or None if authentication fails.
+    """
+    try:
+        token_provider = get_bearer_token_provider(
+            DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+        )
+        return token_provider()
+    except Exception as e:
+        log.error(f"Error getting Microsoft Entra ID access token: {e}")
+        return None
+
+
 ##########################################
 #
 # API routes
@@ -285,7 +305,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             request.app.state.config.OPENAI_API_CONFIGS.get(url, {}),  # Legacy support
         )
 
-        headers, cookies = get_headers_and_cookies(
+        headers, cookies = await get_headers_and_cookies(
             request, url, key, api_config, user=user
         )
 
@@ -550,7 +570,7 @@ async def get_models(
             timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST),
         ) as session:
             try:
-                headers, cookies = get_headers_and_cookies(
+                headers, cookies = await get_headers_and_cookies(
                     request, url, key, api_config, user=user
                 )
 
@@ -636,14 +656,17 @@ async def verify_connection(
         timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST),
     ) as session:
         try:
-            headers, cookies = get_headers_and_cookies(
+            headers, cookies = await get_headers_and_cookies(
                 request, url, key, api_config, user=user
             )
 
             if api_config.get("azure", False):
+                # Only set api-key header if not using Azure Entra ID authentication
+                auth_type = api_config.get("auth_type", "bearer")
+                if auth_type not in ("azure_ad", "microsoft_entra_id"):
                     headers["api-key"] = key
-                api_version = api_config.get("api_version", "") or "2023-03-15-preview"
 
+                api_version = api_config.get("api_version", "") or "2023-03-15-preview"
                 async with session.get(
                     url=f"{url}/openai/models?api-version={api_version}",
                     headers=headers,
@@ -878,14 +901,19 @@ async def generate_chat_completion(
             convert_logit_bias_input_to_json(payload["logit_bias"])
         )
 
-    headers, cookies = get_headers_and_cookies(
+    headers, cookies = await get_headers_and_cookies(
         request, url, key, api_config, metadata, user=user
     )
 
     if api_config.get("azure", False):
         api_version = api_config.get("api_version", "2023-03-15-preview")
         request_url, payload = convert_to_azure_payload(url, payload, api_version)
+
+        # Only set api-key header if not using Azure Entra ID authentication
+        auth_type = api_config.get("auth_type", "bearer")
+        if auth_type not in ("azure_ad", "microsoft_entra_id"):
             headers["api-key"] = key
+
         headers["api-version"] = api_version
         request_url = f"{request_url}/chat/completions?api-version={api_version}"
     else:
@@ -982,7 +1010,9 @@ async def embeddings(request: Request, form_data: dict, user):
     session = None
     streaming = False
 
-    headers, cookies = get_headers_and_cookies(request, url, key, api_config, user=user)
+    headers, cookies = await get_headers_and_cookies(
+        request, url, key, api_config, user=user
+    )
     try:
         session = aiohttp.ClientSession(trust_env=True)
         r = await session.request(
@@ -1052,13 +1082,18 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
     streaming = False
 
     try:
-        headers, cookies = get_headers_and_cookies(
+        headers, cookies = await get_headers_and_cookies(
             request, url, key, api_config, user=user
         )
 
         if api_config.get("azure", False):
             api_version = api_config.get("api_version", "2023-03-15-preview")
+
+            # Only set api-key header if not using Azure Entra ID authentication
+            auth_type = api_config.get("auth_type", "bearer")
+            if auth_type not in ("azure_ad", "microsoft_entra_id"):
                 headers["api-key"] = key
+
             headers["api-version"] = api_version
 
             payload = json.loads(body)

backend/open_webui/routers/retrieval.py

@@ -50,6 +50,8 @@ from open_webui.retrieval.loaders.youtube import YoutubeLoader
 # Web search engines
 from open_webui.retrieval.web.main import SearchResult
 from open_webui.retrieval.web.utils import get_web_loader
+from open_webui.retrieval.web.ollama import search_ollama_cloud
+from open_webui.retrieval.web.perplexity_search import search_perplexity_search
 from open_webui.retrieval.web.brave import search_brave
 from open_webui.retrieval.web.kagi import search_kagi
 from open_webui.retrieval.web.mojeek import search_mojeek
@@ -81,6 +83,7 @@ from open_webui.retrieval.utils import (
     query_doc,
     query_doc_with_hybrid_search,
 )
+from open_webui.retrieval.vector.utils import filter_metadata
 from open_webui.utils.misc import (
     calculate_sha256_string,
 )
@@ -431,6 +434,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         "EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
         "TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
         "DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
+        "DOCLING_PARAMS": request.app.state.config.DOCLING_PARAMS,
         "DOCLING_DO_OCR": request.app.state.config.DOCLING_DO_OCR,
         "DOCLING_FORCE_OCR": request.app.state.config.DOCLING_FORCE_OCR,
         "DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
@@ -474,6 +478,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
             "WEB_SEARCH_DOMAIN_FILTER_LIST": request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
             "BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
             "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,
             "YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
             "YACY_USERNAME": request.app.state.config.YACY_USERNAME,
@@ -530,6 +535,7 @@ class WebConfig(BaseModel):
     WEB_SEARCH_DOMAIN_FILTER_LIST: Optional[List[str]] = []
     BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL: Optional[bool] = None
     BYPASS_WEB_SEARCH_WEB_LOADER: Optional[bool] = None
+    OLLAMA_CLOUD_WEB_SEARCH_API_KEY: Optional[str] = None
     SEARXNG_QUERY_URL: Optional[str] = None
     YACY_QUERY_URL: Optional[str] = None
     YACY_USERNAME: Optional[str] = None
@@ -590,6 +596,7 @@ class ConfigForm(BaseModel):
     # Content extraction settings
     CONTENT_EXTRACTION_ENGINE: Optional[str] = None
     PDF_EXTRACT_IMAGES: Optional[bool] = None
+
     DATALAB_MARKER_API_KEY: Optional[str] = None
     DATALAB_MARKER_API_BASE_URL: Optional[str] = None
     DATALAB_MARKER_ADDITIONAL_CONFIG: Optional[str] = None
@@ -601,11 +608,13 @@ class ConfigForm(BaseModel):
     DATALAB_MARKER_FORMAT_LINES: Optional[bool] = None
     DATALAB_MARKER_USE_LLM: Optional[bool] = None
     DATALAB_MARKER_OUTPUT_FORMAT: Optional[str] = None
+
     EXTERNAL_DOCUMENT_LOADER_URL: Optional[str] = None
     EXTERNAL_DOCUMENT_LOADER_API_KEY: Optional[str] = None
 
     TIKA_SERVER_URL: Optional[str] = None
     DOCLING_SERVER_URL: Optional[str] = None
+    DOCLING_PARAMS: Optional[dict] = None
     DOCLING_DO_OCR: Optional[bool] = None
     DOCLING_FORCE_OCR: Optional[bool] = None
     DOCLING_OCR_ENGINE: Optional[str] = None
@@ -782,6 +791,11 @@ async def update_rag_config(
         if form_data.DOCLING_SERVER_URL is not None
         else request.app.state.config.DOCLING_SERVER_URL
     )
+    request.app.state.config.DOCLING_PARAMS = (
+        form_data.DOCLING_PARAMS
+        if form_data.DOCLING_PARAMS is not None
+        else request.app.state.config.DOCLING_PARAMS
+    )
     request.app.state.config.DOCLING_DO_OCR = (
         form_data.DOCLING_DO_OCR
         if form_data.DOCLING_DO_OCR is not None
@@ -993,6 +1007,9 @@ async def update_rag_config(
         request.app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER = (
             form_data.web.BYPASS_WEB_SEARCH_WEB_LOADER
         )
+        request.app.state.config.OLLAMA_CLOUD_WEB_SEARCH_API_KEY = (
+            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.YACY_QUERY_URL = form_data.web.YACY_QUERY_URL
         request.app.state.config.YACY_USERNAME = form_data.web.YACY_USERNAME
@@ -1101,6 +1118,7 @@ async def update_rag_config(
         "EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
         "TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
         "DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
+        "DOCLING_PARAMS": request.app.state.config.DOCLING_PARAMS,
         "DOCLING_DO_OCR": request.app.state.config.DOCLING_DO_OCR,
         "DOCLING_FORCE_OCR": request.app.state.config.DOCLING_FORCE_OCR,
         "DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
@@ -1144,6 +1162,7 @@ async def update_rag_config(
             "WEB_SEARCH_DOMAIN_FILTER_LIST": request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
             "BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
             "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,
             "YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
             "YACY_USERNAME": request.app.state.config.YACY_USERNAME,
@@ -1412,8 +1431,13 @@ def process_file(
     form_data: ProcessFileForm,
     user=Depends(get_verified_user),
 ):
-    try:
+    if user.role == "admin":
         file = Files.get_file_by_id(form_data.file_id)
+    else:
+        file = Files.get_file_by_id_and_user_id(form_data.file_id, user.id)
+
+    if file:
+        try:
 
             collection_name = form_data.collection_name
 
@@ -1426,7 +1450,9 @@ def process_file(
 
                 try:
                     # /files/{file_id}/data/content/update
-                VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
+                    VECTOR_DB_CLIENT.delete_collection(
+                        collection_name=f"file-{file.id}"
+                    )
                 except:
                     # Audio file upload pipeline
                     pass
@@ -1511,6 +1537,7 @@ def process_file(
                             "picture_description_mode": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE,
                             "picture_description_local": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL,
                             "picture_description_api": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API,
+                            **request.app.state.config.DOCLING_PARAMS,
                         },
                         PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES,
                         DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
@@ -1525,7 +1552,7 @@ def process_file(
                         Document(
                             page_content=doc.page_content,
                             metadata={
-                            **doc.metadata,
+                                **filter_metadata(doc.metadata),
                                 "name": file.filename,
                                 "created_by": file.user_id,
                                 "file_id": file.id,
@@ -1589,17 +1616,29 @@ def process_file(
                             },
                         )
 
+                        Files.update_file_data_by_id(
+                            file.id,
+                            {"status": "completed"},
+                        )
+
                         return {
                             "status": True,
                             "collection_name": collection_name,
                             "filename": file.filename,
                             "content": text_content,
                         }
+                    else:
+                        raise Exception("Error saving document to vector database")
                 except Exception as e:
                     raise e
 
         except Exception as e:
             log.exception(e)
+            Files.update_file_data_by_id(
+                file.id,
+                {"status": "failed"},
+            )
+
             if "No pandoc was found" in str(e):
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
@@ -1611,6 +1650,11 @@ def process_file(
                     detail=str(e),
                 )
 
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
 
 class ProcessTextForm(BaseModel):
     name: str
@@ -1825,7 +1869,25 @@ async def search_web(request: Request, engine: str, query: str) -> list[SearchRe
     logging.info(f"search_web: {engine} query: {query}")
 
     # TODO: add playwright to search the web
-    if engine == "searxng":
+    if engine == "ollama_cloud":
+        return search_ollama_cloud(
+            "https://ollama.com",
+            request.app.state.config.OLLAMA_CLOUD_WEB_SEARCH_API_KEY,
+            query,
+            request.app.state.config.WEB_SEARCH_RESULT_COUNT,
+            request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
+        )
+    elif engine == "perplexity_search":
+        if request.app.state.config.PERPLEXITY_API_KEY:
+            return search_perplexity_search(
+                request.app.state.config.PERPLEXITY_API_KEY,
+                query,
+                request.app.state.config.WEB_SEARCH_RESULT_COUNT,
+                request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
+            )
+        else:
+            raise Exception("No PERPLEXITY_API_KEY found in environment variables")
+    elif engine == "searxng":
         if request.app.state.config.SEARXNG_QUERY_URL:
             return search_searxng(
                 request.app.state.config.SEARXNG_QUERY_URL,
@@ -2059,7 +2121,7 @@ async def process_web_search(
     result_items = []
 
     try:
-        logging.info(
+        logging.debug(
             f"trying to web search with {request.app.state.config.WEB_SEARCH_ENGINE, form_data.queries}"
         )
 

backend/open_webui/routers/tools.py

@@ -9,6 +9,7 @@ from pydantic import BaseModel, HttpUrl
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 
 
+from open_webui.models.oauth_sessions import OAuthSessions
 from open_webui.models.tools import (
     ToolForm,
     ToolModel,
@@ -16,7 +17,11 @@ from open_webui.models.tools import (
     ToolUserResponse,
     Tools,
 )
-from open_webui.utils.plugin import load_tool_module_by_id, replace_imports
+from open_webui.utils.plugin import (
+    load_tool_module_by_id,
+    replace_imports,
+    get_tool_module_from_cache,
+)
 from open_webui.utils.tools import get_tool_specs
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.utils.access_control import has_access, has_permission
@@ -34,6 +39,14 @@ log.setLevel(SRC_LOG_LEVELS["MAIN"])
 router = APIRouter()
 
 
+def get_tool_module(request, tool_id, load_from_db=True):
+    """
+    Get the tool module by its ID.
+    """
+    tool_module, _ = get_tool_module_from_cache(request, tool_id, load_from_db)
+    return tool_module
+
+
 ############################
 # GetTools
 ############################
@@ -41,8 +54,21 @@ router = APIRouter()
 
 @router.get("/", response_model=list[ToolUserResponse])
 async def get_tools(request: Request, user=Depends(get_verified_user)):
-    tools = Tools.get_tools()
+    tools = []
 
+    # Local Tools
+    for tool in Tools.get_tools():
+        tool_module = get_tool_module(request, tool.id)
+        tools.append(
+            ToolUserResponse(
+                **{
+                    **tool.model_dump(),
+                    "has_user_valves": hasattr(tool_module, "UserValves"),
+                }
+            )
+        )
+
+    # OpenAPI Tool Servers
     for server in await get_tool_servers(request):
         tools.append(
             ToolUserResponse(
@@ -68,6 +94,50 @@ async def get_tools(request: Request, user=Depends(get_verified_user)):
             )
         )
 
+    # MCP Tool Servers
+    for server in request.app.state.config.TOOL_SERVER_CONNECTIONS:
+        if server.get("type", "openapi") == "mcp":
+            server_id = server.get("info", {}).get("id")
+            auth_type = server.get("auth_type", "none")
+
+            session_token = None
+            if auth_type == "oauth_2.1":
+                splits = server_id.split(":")
+                server_id = splits[-1] if len(splits) > 1 else server_id
+
+                session_token = (
+                    await request.app.state.oauth_client_manager.get_oauth_token(
+                        user.id, f"mcp:{server_id}"
+                    )
+                )
+
+            tools.append(
+                ToolUserResponse(
+                    **{
+                        "id": f"server:mcp:{server.get('info', {}).get('id')}",
+                        "user_id": f"server:mcp:{server.get('info', {}).get('id')}",
+                        "name": server.get("info", {}).get("name", "MCP Tool Server"),
+                        "meta": {
+                            "description": server.get("info", {}).get(
+                                "description", ""
+                            ),
+                        },
+                        "access_control": server.get("config", {}).get(
+                            "access_control", None
+                        ),
+                        "updated_at": int(time.time()),
+                        "created_at": int(time.time()),
+                        **(
+                            {
+                                "authenticated": session_token is not None,
+                            }
+                            if auth_type == "oauth_2.1"
+                            else {}
+                        ),
+                    }
+                )
+            )
+
     if user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL:
         # Admin can see all tools
         return tools
@@ -462,8 +532,9 @@ async def update_tools_valves_by_id(
     try:
         form_data = {k: v for k, v in form_data.items() if v is not None}
         valves = Valves(**form_data)
-        Tools.update_tool_valves_by_id(id, valves.model_dump())
+        valves_dict = valves.model_dump(exclude_unset=True)
-        return valves.model_dump()
+        Tools.update_tool_valves_by_id(id, valves_dict)
+        return valves_dict
     except Exception as e:
         log.exception(f"Failed to update tool valves by id {id}: {e}")
         raise HTTPException(
@@ -538,10 +609,11 @@ async def update_tools_user_valves_by_id(
             try:
                 form_data = {k: v for k, v in form_data.items() if v is not None}
                 user_valves = UserValves(**form_data)
+                user_valves_dict = user_valves.model_dump(exclude_unset=True)
                 Tools.update_user_valves_by_id_and_user_id(
-                    id, user.id, user_valves.model_dump()
+                    id, user.id, user_valves_dict
                 )
-                return user_valves.model_dump()
+                return user_valves_dict
             except Exception as e:
                 log.exception(f"Failed to update user valves by id {id}: {e}")
                 raise HTTPException(

backend/open_webui/routers/users.py

@@ -18,6 +18,7 @@ from open_webui.models.users import (
     UserModel,
     UserListResponse,
     UserInfoListResponse,
+    UserIdNameListResponse,
     UserRoleUpdateForm,
     Users,
     UserSettings,
@@ -100,6 +101,23 @@ async def get_all_users(
     return Users.get_users()
 
 
+@router.get("/search", response_model=UserIdNameListResponse)
+async def search_users(
+    query: Optional[str] = None,
+    user=Depends(get_verified_user),
+):
+    limit = PAGE_ITEM_COUNT
+
+    page = 1  # Always return the first page for search
+    skip = (page - 1) * limit
+
+    filter = {}
+    if query:
+        filter["query"] = query
+
+    return Users.get_users(filter=filter, skip=skip, limit=limit)
+
+
 ############################
 # User Groups
 ############################
@@ -139,6 +157,7 @@ class SharingPermissions(BaseModel):
     public_knowledge: bool = True
     public_prompts: bool = True
     public_tools: bool = True
+    public_notes: bool = True
 
 
 class ChatPermissions(BaseModel):

backend/open_webui/socket/main.py

@@ -356,7 +356,7 @@ async def join_note(sid, data):
     await sio.enter_room(sid, f"note:{note.id}")
 
 
-@sio.on("channel-events")
+@sio.on("events:channel")
 async def channel_events(sid, data):
     room = f"channel:{data['channel_id']}"
     participants = sio.manager.get_participants(
@@ -373,7 +373,7 @@ async def channel_events(sid, data):
 
     if event_type == "typing":
         await sio.emit(
-            "channel-events",
+            "events:channel",
             {
                 "channel_id": data["channel_id"],
                 "message_id": data.get("message_id", None),
@@ -653,12 +653,15 @@ def get_event_emitter(request_info, update_db=True):
             )
         )
 
+        chat_id = request_info.get("chat_id", None)
+        message_id = request_info.get("message_id", None)
+
         emit_tasks = [
             sio.emit(
-                "chat-events",
+                "events",
                 {
-                    "chat_id": request_info.get("chat_id", None),
+                    "chat_id": chat_id,
-                    "message_id": request_info.get("message_id", None),
+                    "message_id": message_id,
                     "data": event_data,
                 },
                 to=session_id,
@@ -667,8 +670,11 @@ def get_event_emitter(request_info, update_db=True):
         ]
 
         await asyncio.gather(*emit_tasks)
-
+        if (
-        if update_db:
+            update_db
+            and message_id
+            and not request_info.get("chat_id", "").startswith("local:")
+        ):
             if "type" in event_data and event_data["type"] == "status":
                 Chats.add_message_status_to_chat_by_id_and_message_id(
                     request_info["chat_id"],
@@ -705,6 +711,23 @@ def get_event_emitter(request_info, update_db=True):
                     },
                 )
 
+            if "type" in event_data and event_data["type"] == "embeds":
+                message = Chats.get_message_by_id_and_message_id(
+                    request_info["chat_id"],
+                    request_info["message_id"],
+                )
+
+                embeds = event_data.get("data", {}).get("embeds", [])
+                embeds.extend(message.get("embeds", []))
+
+                Chats.upsert_message_to_chat_by_id_and_message_id(
+                    request_info["chat_id"],
+                    request_info["message_id"],
+                    {
+                        "embeds": embeds,
+                    },
+                )
+
             if "type" in event_data and event_data["type"] == "files":
                 message = Chats.get_message_by_id_and_message_id(
                     request_info["chat_id"],
@@ -747,7 +770,7 @@ def get_event_emitter(request_info, update_db=True):
 def get_event_call(request_info):
     async def __event_caller__(event_data):
         response = await sio.call(
-            "chat-events",
+            "events",
             {
                 "chat_id": request_info.get("chat_id", None),
                 "message_id": request_info.get("message_id", None),

backend/open_webui/tasks.py

@@ -164,7 +164,10 @@ async def stop_task(redis, task_id: str):
         # Task successfully canceled
         return {"status": True, "message": f"Task {task_id} successfully stopped."}
 
-    return {"status": False, "message": f"Failed to stop task {task_id}."}
+    if task.cancelled() or task.done():
+        return {"status": True, "message": f"Task {task_id} successfully cancelled."}
+
+    return {"status": True, "message": f"Cancellation requested for {task_id}."}
 
 
 async def stop_item_tasks(redis: Redis, item_id: str):

backend/open_webui/utils/access_control.py

@@ -110,9 +110,13 @@ def has_access(
     type: str = "write",
     access_control: Optional[dict] = None,
     user_group_ids: Optional[Set[str]] = None,
+    strict: bool = True,
 ) -> bool:
     if access_control is None:
+        if strict:
             return type == "read"
+        else:
+            return True
 
     if user_group_ids is None:
         user_groups = Groups.get_groups_by_member_id(user_id)
@@ -130,9 +134,10 @@ def has_access(
 # Get all users with access to a resource
 def get_users_with_access(
     type: str = "write", access_control: Optional[dict] = None
-) -> List[UserModel]:
+) -> list[UserModel]:
     if access_control is None:
-        return Users.get_users()
+        result = Users.get_users()
+        return result.get("users", [])
 
     permission_access = access_control.get(type, {})
     permitted_group_ids = permission_access.get("group_ids", [])

backend/open_webui/utils/auth.py

@@ -6,7 +6,7 @@ import hmac
 import hashlib
 import requests
 import os
-
+import bcrypt
 
 from cryptography.hazmat.primitives.ciphers.aead import AESGCM
 from cryptography.hazmat.primitives.asymmetric import ed25519
@@ -38,11 +38,8 @@ from open_webui.env import (
 
 from fastapi import BackgroundTasks, Depends, HTTPException, Request, Response, status
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
-from passlib.context import CryptContext
 
 
-logging.getLogger("passlib").setLevel(logging.ERROR)
-
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["OAUTH"])
 
@@ -155,17 +152,23 @@ def get_license_data(app, key):
 
 
 bearer_security = HTTPBearer(auto_error=False)
-pwd_context = CryptContext(schemes=["bcrypt"], deprecated="auto")
 
 
-def verify_password(plain_password, hashed_password):
+def get_password_hash(password: str) -> str:
+    """Hash a password using bcrypt"""
+    return bcrypt.hashpw(password.encode("utf-8"), bcrypt.gensalt()).decode("utf-8")
+
+
+def verify_password(plain_password: str, hashed_password: str) -> bool:
+    """Verify a password against its hash"""
     return (
-        pwd_context.verify(plain_password, hashed_password) if hashed_password else None
+        bcrypt.checkpw(
+            plain_password.encode("utf-8"),
+            hashed_password.encode("utf-8"),
+        )
+        if hashed_password
+        else None
     )
-
-
-def get_password_hash(password):
-    return pwd_context.hash(password)
 
 
 def create_token(data: dict, expires_delta: Union[timedelta, None] = None) -> str:

backend/open_webui/utils/channels.py

@@ -0,0 +1,31 @@
+import re
+
+
+def extract_mentions(message: str, triggerChar: str = "@"):
+    # Escape triggerChar in case it's a regex special character
+    triggerChar = re.escape(triggerChar)
+    pattern = rf"<{triggerChar}([A-Z]):([^|>]+)"
+
+    matches = re.findall(pattern, message)
+    return [{"id_type": id_type, "id": id_value} for id_type, id_value in matches]
+
+
+def replace_mentions(message: str, triggerChar: str = "@", use_label: bool = True):
+    """
+    Replace mentions in the message with either their label (after the pipe `|`)
+    or their id if no label exists.
+
+    Example:
+      "<@M:gpt-4.1|GPT-4>" -> "GPT-4"   (if use_label=True)
+      "<@M:gpt-4.1|GPT-4>" -> "gpt-4.1" (if use_label=False)
+    """
+    # Escape triggerChar
+    triggerChar = re.escape(triggerChar)
+
+    def replacer(match):
+        id_type, id_value, label = match.groups()
+        return label if use_label and label else id_value
+
+    # Regex captures: idType, id, optional label
+    pattern = rf"<{triggerChar}([A-Z]):([^|>]+)(?:\|([^>]+))?>"
+    return re.sub(pattern, replacer, message)

backend/open_webui/utils/chat.py

@@ -80,6 +80,7 @@ async def generate_direct_chat_completion(
     event_caller = get_event_call(metadata)
 
     channel = f"{user_id}:{session_id}:{request_id}"
+    logging.info(f"WebSocket channel: {channel}")
 
     if form_data.get("stream"):
         q = asyncio.Queue()
@@ -121,7 +122,10 @@ async def generate_direct_chat_completion(
 
                             yield f"data: {json.dumps(data)}\n\n"
                         elif isinstance(data, str):
-                            yield data
+                            if "data:" in data:
+                                yield f"{data}\n\n"
+                            else:
+                                yield f"data: {data}\n\n"
                 except Exception as e:
                     log.debug(f"Error in event generator: {e}")
                     pass

backend/open_webui/utils/files.py

@@ -0,0 +1,97 @@
+from open_webui.routers.images import (
+    load_b64_image_data,
+    upload_image,
+)
+
+from fastapi import (
+    APIRouter,
+    Depends,
+    HTTPException,
+    Request,
+    UploadFile,
+)
+
+from open_webui.routers.files import upload_file_handler
+
+import mimetypes
+import base64
+import io
+
+
+def get_image_url_from_base64(request, base64_image_string, metadata, user):
+    if "data:image/png;base64" in base64_image_string:
+        image_url = ""
+        # Extract base64 image data from the line
+        image_data, content_type = load_b64_image_data(base64_image_string)
+        if image_data is not None:
+            image_url = upload_image(
+                request,
+                image_data,
+                content_type,
+                metadata,
+                user,
+            )
+        return image_url
+    return None
+
+
+def load_b64_audio_data(b64_str):
+    try:
+        if "," in b64_str:
+            header, b64_data = b64_str.split(",", 1)
+        else:
+            b64_data = b64_str
+            header = "data:audio/wav;base64"
+        audio_data = base64.b64decode(b64_data)
+        content_type = (
+            header.split(";")[0].split(":")[1] if ";" in header else "audio/wav"
+        )
+        return audio_data, content_type
+    except Exception as e:
+        print(f"Error decoding base64 audio data: {e}")
+        return None, None
+
+
+def upload_audio(request, audio_data, content_type, metadata, user):
+    audio_format = mimetypes.guess_extension(content_type)
+    file = UploadFile(
+        file=io.BytesIO(audio_data),
+        filename=f"generated-{audio_format}",  # will be converted to a unique ID on upload_file
+        headers={
+            "content-type": content_type,
+        },
+    )
+    file_item = upload_file_handler(
+        request,
+        file=file,
+        metadata=metadata,
+        process=False,
+        user=user,
+    )
+    url = request.app.url_path_for("get_file_content_by_id", id=file_item.id)
+    return url
+
+
+def get_audio_url_from_base64(request, base64_audio_string, metadata, user):
+    if "data:audio/wav;base64" in base64_audio_string:
+        audio_url = ""
+        # Extract base64 audio data from the line
+        audio_data, content_type = load_b64_audio_data(base64_audio_string)
+        if audio_data is not None:
+            audio_url = upload_audio(
+                request,
+                audio_data,
+                content_type,
+                metadata,
+                user,
+            )
+        return audio_url
+    return None
+
+
+def get_file_url_from_base64(request, base64_file_string, metadata, user):
+    if "data:image/png;base64" in base64_file_string:
+        return get_image_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

backend/open_webui/utils/filter.py

@@ -127,8 +127,10 @@ async def process_filter_functions(
             raise e
 
     # Handle file cleanup for inlet
-    if skip_files and "files" in form_data.get("metadata", {}):
+    if skip_files:
-        del form_data["files"]
+        if "files" in form_data.get("metadata", {}):
             del form_data["metadata"]["files"]
+        if "files" in form_data:
+            del form_data["files"]
 
     return form_data, {}

backend/open_webui/utils/mcp/client.py

@@ -0,0 +1,110 @@
+import asyncio
+from typing import Optional
+from contextlib import AsyncExitStack
+
+from mcp import ClientSession
+from mcp.client.auth import OAuthClientProvider, TokenStorage
+from mcp.client.streamable_http import streamablehttp_client
+from mcp.shared.auth import OAuthClientInformationFull, OAuthClientMetadata, OAuthToken
+
+
+class MCPClient:
+    def __init__(self):
+        self.session: Optional[ClientSession] = None
+        self.exit_stack = AsyncExitStack()
+
+    async def connect(self, url: str, headers: Optional[dict] = None):
+        try:
+            self._streams_context = streamablehttp_client(url, headers=headers)
+
+            transport = await self.exit_stack.enter_async_context(self._streams_context)
+            read_stream, write_stream, _ = transport
+
+            self._session_context = ClientSession(
+                read_stream, write_stream
+            )  # pylint: disable=W0201
+
+            self.session = await self.exit_stack.enter_async_context(
+                self._session_context
+            )
+            await self.session.initialize()
+        except Exception as e:
+            await self.disconnect()
+            raise e
+
+    async def list_tool_specs(self) -> Optional[dict]:
+        if not self.session:
+            raise RuntimeError("MCP client is not connected.")
+
+        result = await self.session.list_tools()
+        tools = result.tools
+
+        tool_specs = []
+        for tool in tools:
+            name = tool.name
+            description = tool.description
+
+            inputSchema = tool.inputSchema
+
+            # TODO: handle outputSchema if needed
+            outputSchema = getattr(tool, "outputSchema", None)
+
+            tool_specs.append(
+                {"name": name, "description": description, "parameters": inputSchema}
+            )
+
+        return tool_specs
+
+    async def call_tool(
+        self, function_name: str, function_args: dict
+    ) -> Optional[dict]:
+        if not self.session:
+            raise RuntimeError("MCP client is not connected.")
+
+        result = await self.session.call_tool(function_name, function_args)
+        if not result:
+            raise Exception("No result returned from MCP tool call.")
+
+        result_dict = result.model_dump(mode="json")
+        result_content = result_dict.get("content", {})
+
+        if result.isError:
+            raise Exception(result_content)
+        else:
+            return result_content
+
+    async def list_resources(self, cursor: Optional[str] = None) -> Optional[dict]:
+        if not self.session:
+            raise RuntimeError("MCP client is not connected.")
+
+        result = await self.session.list_resources(cursor=cursor)
+        if not result:
+            raise Exception("No result returned from MCP list_resources call.")
+
+        result_dict = result.model_dump()
+        resources = result_dict.get("resources", [])
+
+        return resources
+
+    async def read_resource(self, uri: str) -> Optional[dict]:
+        if not self.session:
+            raise RuntimeError("MCP client is not connected.")
+
+        result = await self.session.read_resource(uri)
+        if not result:
+            raise Exception("No result returned from MCP read_resource call.")
+        result_dict = result.model_dump()
+
+        return result_dict
+
+    async def disconnect(self):
+        # Clean up and close the session
+        await self.exit_stack.aclose()
+
+    async def __aenter__(self):
+        await self.exit_stack.__aenter__()
+        return self
+
+    async def __aexit__(self, exc_type, exc_value, traceback):
+        await self.exit_stack.__aexit__(exc_type, exc_value, traceback)
+        await self.disconnect()

backend/open_webui/utils/middleware.py

@@ -20,9 +20,11 @@ from concurrent.futures import ThreadPoolExecutor
 
 
 from fastapi import Request, HTTPException
+from fastapi.responses import HTMLResponse
 from starlette.responses import Response, StreamingResponse, JSONResponse
 
 
+from open_webui.models.oauth_sessions import OAuthSessions
 from open_webui.models.chats import Chats
 from open_webui.models.folders import Folders
 from open_webui.models.users import Users
@@ -52,6 +54,11 @@ from open_webui.routers.pipelines import (
 from open_webui.routers.memories import query_memory, QueryMemoryForm
 
 from open_webui.utils.webhook import post_webhook
+from open_webui.utils.files import (
+    get_audio_url_from_base64,
+    get_file_url_from_base64,
+    get_image_url_from_base64,
+)
 
 
 from open_webui.models.users import UserModel
@@ -73,10 +80,12 @@ from open_webui.utils.misc import (
     add_or_update_system_message,
     add_or_update_user_message,
     get_last_user_message,
+    get_last_user_message_item,
     get_last_assistant_message,
     get_system_message,
     prepend_to_first_user_message_content,
     convert_logit_bias_input_to_json,
+    get_content_from_message,
 )
 from open_webui.utils.tools import get_tools
 from open_webui.utils.plugin import load_function_module_by_id
@@ -86,6 +95,7 @@ from open_webui.utils.filter import (
 )
 from open_webui.utils.code_interpreter import execute_code_jupyter
 from open_webui.utils.payload import apply_system_prompt_to_body
+from open_webui.utils.mcp.client import MCPClient
 
 
 from open_webui.config import (
@@ -125,6 +135,149 @@ DEFAULT_SOLUTION_TAGS = [("<|begin_of_solution|>", "<|end_of_solution|>")]
 DEFAULT_CODE_INTERPRETER_TAGS = [("<code_interpreter>", "</code_interpreter>")]
 
 
+def process_tool_result(
+    request,
+    tool_function_name,
+    tool_result,
+    tool_type,
+    direct_tool=False,
+    metadata=None,
+    user=None,
+):
+    tool_result_embeds = []
+
+    if isinstance(tool_result, HTMLResponse):
+        content_disposition = tool_result.headers.get("Content-Disposition", "")
+        if "inline" in content_disposition:
+            content = tool_result.body.decode("utf-8", "replace")
+            tool_result_embeds.append(content)
+
+            if 200 <= tool_result.status_code < 300:
+                tool_result = {
+                    "status": "success",
+                    "code": "ui_component",
+                    "message": f"{tool_function_name}: Embedded UI result is active and visible to the user.",
+                }
+            elif 400 <= tool_result.status_code < 500:
+                tool_result = {
+                    "status": "error",
+                    "code": "ui_component",
+                    "message": f"{tool_function_name}: Client error {tool_result.status_code} from embedded UI result.",
+                }
+            elif 500 <= tool_result.status_code < 600:
+                tool_result = {
+                    "status": "error",
+                    "code": "ui_component",
+                    "message": f"{tool_function_name}: Server error {tool_result.status_code} from embedded UI result.",
+                }
+            else:
+                tool_result = {
+                    "status": "error",
+                    "code": "ui_component",
+                    "message": f"{tool_function_name}: Unexpected status code {tool_result.status_code} from embedded UI result.",
+                }
+        else:
+            tool_result = tool_result.body.decode("utf-8", "replace")
+
+    elif (tool_type == "external" and isinstance(tool_result, tuple)) or (
+        direct_tool and isinstance(tool_result, list) and len(tool_result) == 2
+    ):
+        tool_result, tool_response_headers = tool_result
+
+        try:
+            if not isinstance(tool_response_headers, dict):
+                tool_response_headers = dict(tool_response_headers)
+        except Exception as e:
+            tool_response_headers = {}
+            log.debug(e)
+
+        if tool_response_headers and isinstance(tool_response_headers, dict):
+            content_disposition = tool_response_headers.get(
+                "Content-Disposition",
+                tool_response_headers.get("content-disposition", ""),
+            )
+
+            if "inline" in content_disposition:
+                content_type = tool_response_headers.get(
+                    "Content-Type",
+                    tool_response_headers.get("content-type", ""),
+                )
+                location = tool_response_headers.get(
+                    "Location",
+                    tool_response_headers.get("location", ""),
+                )
+
+                if "text/html" in content_type:
+                    # Display as iframe embed
+                    tool_result_embeds.append(tool_result)
+                    tool_result = {
+                        "status": "success",
+                        "code": "ui_component",
+                        "message": f"{tool_function_name}: Embedded UI result is active and visible to the user.",
+                    }
+                elif location:
+                    tool_result_embeds.append(location)
+                    tool_result = {
+                        "status": "success",
+                        "code": "ui_component",
+                        "message": f"{tool_function_name}: Embedded UI result is active and visible to the user.",
+                    }
+
+    tool_result_files = []
+
+    if isinstance(tool_result, list):
+        if tool_type == "mcp":  # MCP
+            tool_response = []
+            for item in tool_result:
+                if isinstance(item, dict):
+                    if item.get("type") == "text":
+                        text = item.get("text", "")
+                        if isinstance(text, str):
+                            try:
+                                text = json.loads(text)
+                            except json.JSONDecodeError:
+                                pass
+                        tool_response.append(text)
+                    elif item.get("type") in ["image", "audio"]:
+                        file_url = get_file_url_from_base64(
+                            request,
+                            f"data:{item.get('mimeType')};base64,{item.get('data', item.get('blob', ''))}",
+                            {
+                                "chat_id": metadata.get("chat_id", None),
+                                "message_id": metadata.get("message_id", None),
+                                "session_id": metadata.get("session_id", None),
+                                "result": item,
+                            },
+                            user,
+                        )
+
+                        tool_result_files.append(
+                            {
+                                "type": item.get("type", "data"),
+                                "url": file_url,
+                            }
+                        )
+            tool_result = tool_response[0] if len(tool_response) == 1 else tool_response
+        else:  # OpenAPI
+            for item in tool_result:
+                if isinstance(item, str) and item.startswith("data:"):
+                    tool_result_files.append(
+                        {
+                            "type": "data",
+                            "content": item,
+                        }
+                    )
+                    tool_result.remove(item)
+
+    if isinstance(tool_result, list):
+        tool_result = {"results": tool_result}
+
+    if isinstance(tool_result, dict) or isinstance(tool_result, list):
+        tool_result = json.dumps(tool_result, indent=2, ensure_ascii=False)
+
+    return tool_result, tool_result_files, tool_result_embeds
+
+
 async def chat_completion_tools_handler(
     request: Request, body: dict, extra_params: dict, user: UserModel, models, tools
 ) -> tuple[dict, dict]:
@@ -132,7 +285,7 @@ async def chat_completion_tools_handler(
         content = None
         if hasattr(response, "body_iterator"):
             async for chunk in response.body_iterator:
-                data = json.loads(chunk.decode("utf-8"))
+                data = json.loads(chunk.decode("utf-8", "replace"))
                 content = data["choices"][0]["message"]["content"]
 
             # Cleanup any remaining background tasks if necessary
@@ -144,12 +297,14 @@ async def chat_completion_tools_handler(
 
     def get_tools_function_calling_payload(messages, task_model_id, content):
         user_message = get_last_user_message(messages)
-        history = "\n".join(
+
-            f"{message['role'].upper()}: \"\"\"{message['content']}\"\"\""
+        recent_messages = messages[-4:] if len(messages) > 4 else messages
-            for message in messages[::-1][:4]
+        chat_history = "\n".join(
+            f"{message['role'].upper()}: \"\"\"{get_content_from_message(message)}\"\"\""
+            for message in recent_messages
         )
 
-        prompt = f"History:\n{history}\nQuery: {user_message}"
+        prompt = f"History:\n{chat_history}\nQuery: {user_message}"
 
         return {
             "model": task_model_id,
@@ -162,6 +317,7 @@ async def chat_completion_tools_handler(
         }
 
     event_caller = extra_params["__event_call__"]
+    event_emitter = extra_params["__event_emitter__"]
     metadata = extra_params["__metadata__"]
 
     task_model_id = get_task_model_id(
@@ -216,8 +372,14 @@ async def chat_completion_tools_handler(
 
                 tool_function_params = tool_call.get("parameters", {})
 
+                tool = None
+                tool_type = ""
+                direct_tool = False
+
                 try:
                     tool = tools[tool_function_name]
+                    tool_type = tool.get("type", "")
+                    direct_tool = tool.get("direct", False)
 
                     spec = tool.get("spec", {})
                     allowed_params = (
@@ -249,18 +411,46 @@ async def chat_completion_tools_handler(
                 except Exception as e:
                     tool_result = str(e)
 
-                tool_result_files = []
+                tool_result, tool_result_files, tool_result_embeds = (
-                if isinstance(tool_result, list):
+                    process_tool_result(
-                    for item in tool_result:
+                        request,
-                        # check if string
+                        tool_function_name,
-                        if isinstance(item, str) and item.startswith("data:"):
+                        tool_result,
-                            tool_result_files.append(item)
+                        tool_type,
-                            tool_result.remove(item)
+                        direct_tool,
+                        metadata,
+                        user,
+                    )
+                )
 
-                if isinstance(tool_result, dict) or isinstance(tool_result, list):
+                if event_emitter:
-                    tool_result = json.dumps(tool_result, indent=2)
+                    if tool_result_files:
+                        await event_emitter(
+                            {
+                                "type": "files",
+                                "data": {
+                                    "files": tool_result_files,
+                                },
+                            }
+                        )
 
-                if isinstance(tool_result, str):
+                    if tool_result_embeds:
+                        await event_emitter(
+                            {
+                                "type": "embeds",
+                                "data": {
+                                    "embeds": tool_result_embeds,
+                                },
+                            }
+                        )
+
+                print(
+                    f"Tool {tool_function_name} result: {tool_result}",
+                    tool_result_files,
+                    tool_result_embeds,
+                )
+
+                if tool_result:
                     tool = tools[tool_function_name]
                     tool_id = tool.get("tool_id", "")
 
@@ -274,18 +464,19 @@ async def chat_completion_tools_handler(
                     sources.append(
                         {
                             "source": {
-                                "name": (f"TOOL:{tool_name}"),
+                                "name": (f"{tool_name}"),
                             },
-                            "document": [tool_result],
+                            "document": [str(tool_result)],
                             "metadata": [
                                 {
-                                    "source": (f"TOOL:{tool_name}"),
+                                    "source": (f"{tool_name}"),
                                     "parameters": tool_function_params,
                                 }
                             ],
                             "tool_result": True,
                         }
                     )
+
                     # Citation is not enabled for this tool
                     body["messages"] = add_or_update_user_message(
                         f"\nTool `{tool_name}` Output: {tool_result}",
@@ -631,7 +822,11 @@ async def chat_completion_files_handler(
     sources = []
 
     if files := body.get("metadata", {}).get("files", None):
+        # Check if all files are in full context mode
+        all_full_context = all(item.get("context") == "full" for item in files)
+
         queries = []
+        if not all_full_context:
             try:
                 queries_response = await generate_queries(
                     request,
@@ -663,6 +858,7 @@ async def chat_completion_files_handler(
         if len(queries) == 0:
             queries = [get_last_user_message(body["messages"])]
 
+        if not all_full_context:
             await __event_emitter__(
                 {
                     "type": "status",
@@ -701,7 +897,8 @@ async def chat_completion_files_handler(
                         r=request.app.state.config.RELEVANCE_THRESHOLD,
                         hybrid_bm25_weight=request.app.state.config.HYBRID_BM25_WEIGHT,
                         hybrid_search=request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
-                        full_context=request.app.state.config.RAG_FULL_CONTEXT,
+                        full_context=all_full_context
+                        or request.app.state.config.RAG_FULL_CONTEXT,
                         user=user,
                     ),
                 )
@@ -807,7 +1004,7 @@ async def process_chat_payload(request, form_data, user, metadata, model):
     if system_message:
         try:
             form_data = apply_system_prompt_to_body(
-                system_message.get("content"), form_data, metadata, user
+                system_message.get("content"), form_data, metadata, user, replace=True
             )
         except:
             pass
@@ -818,7 +1015,7 @@ async def process_chat_payload(request, form_data, user, metadata, model):
     oauth_token = None
     try:
         if request.cookies.get("oauth_session_id", None):
-            oauth_token = request.app.state.oauth_manager.get_oauth_token(
+            oauth_token = await request.app.state.oauth_manager.get_oauth_token(
                 user.id,
                 request.cookies.get("oauth_session_id", None),
             )
@@ -987,14 +1184,113 @@ async def process_chat_payload(request, form_data, user, metadata, model):
     # Server side tools
     tool_ids = metadata.get("tool_ids", None)
     # Client side tools
-    tool_servers = metadata.get("tool_servers", None)
+    direct_tool_servers = metadata.get("tool_servers", None)
 
     log.debug(f"{tool_ids=}")
-    log.debug(f"{tool_servers=}")
+    log.debug(f"{direct_tool_servers=}")
 
     tools_dict = {}
 
+    mcp_clients = {}
+    mcp_tools_dict = {}
+
     if tool_ids:
+        for tool_id in tool_ids:
+            if tool_id.startswith("server:mcp:"):
+                try:
+                    server_id = tool_id[len("server:mcp:") :]
+
+                    mcp_server_connection = None
+                    for (
+                        server_connection
+                    ) in request.app.state.config.TOOL_SERVER_CONNECTIONS:
+                        if (
+                            server_connection.get("type", "") == "mcp"
+                            and server_connection.get("info", {}).get("id") == server_id
+                        ):
+                            mcp_server_connection = server_connection
+                            break
+
+                    if not mcp_server_connection:
+                        log.error(f"MCP server with id {server_id} not found")
+                        continue
+
+                    auth_type = mcp_server_connection.get("auth_type", "")
+
+                    headers = {}
+                    if auth_type == "bearer":
+                        headers["Authorization"] = (
+                            f"Bearer {mcp_server_connection.get('key', '')}"
+                        )
+                    elif auth_type == "none":
+                        # No authentication
+                        pass
+                    elif auth_type == "session":
+                        headers["Authorization"] = (
+                            f"Bearer {request.state.token.credentials}"
+                        )
+                    elif auth_type == "system_oauth":
+                        oauth_token = extra_params.get("__oauth_token__", None)
+                        if oauth_token:
+                            headers["Authorization"] = (
+                                f"Bearer {oauth_token.get('access_token', '')}"
+                            )
+                    elif auth_type == "oauth_2.1":
+                        try:
+                            splits = server_id.split(":")
+                            server_id = splits[-1] if len(splits) > 1 else server_id
+
+                            oauth_token = await request.app.state.oauth_client_manager.get_oauth_token(
+                                user.id, f"mcp:{server_id}"
+                            )
+
+                            if oauth_token:
+                                headers["Authorization"] = (
+                                    f"Bearer {oauth_token.get('access_token', '')}"
+                                )
+                        except Exception as e:
+                            log.error(f"Error getting OAuth token: {e}")
+                            oauth_token = None
+
+                    mcp_clients[server_id] = MCPClient()
+                    await mcp_clients[server_id].connect(
+                        url=mcp_server_connection.get("url", ""),
+                        headers=headers if headers else None,
+                    )
+
+                    tool_specs = await mcp_clients[server_id].list_tool_specs()
+                    for tool_spec in tool_specs:
+
+                        def make_tool_function(client, function_name):
+                            async def tool_function(**kwargs):
+                                print(kwargs)
+                                print(client)
+                                print(await client.list_tool_specs())
+                                return await client.call_tool(
+                                    function_name,
+                                    function_args=kwargs,
+                                )
+
+                            return tool_function
+
+                        tool_function = make_tool_function(
+                            mcp_clients[server_id], tool_spec["name"]
+                        )
+
+                        mcp_tools_dict[f"{server_id}_{tool_spec['name']}"] = {
+                            "spec": {
+                                **tool_spec,
+                                "name": f"{server_id}_{tool_spec['name']}",
+                            },
+                            "callable": tool_function,
+                            "type": "mcp",
+                            "client": mcp_clients[server_id],
+                            "direct": False,
+                        }
+                except Exception as e:
+                    log.debug(e)
+                    continue
+
         tools_dict = await get_tools(
             request,
             tool_ids,
@@ -1006,9 +1302,11 @@ async def process_chat_payload(request, form_data, user, metadata, model):
                 "__files__": metadata.get("files", []),
             },
         )
+        if mcp_tools_dict:
+            tools_dict = {**tools_dict, **mcp_tools_dict}
 
-    if tool_servers:
+    if direct_tool_servers:
-        for tool_server in tool_servers:
+        for tool_server in direct_tool_servers:
             tool_specs = tool_server.pop("specs", [])
 
             for tool in tool_specs:
@@ -1018,6 +1316,9 @@ async def process_chat_payload(request, form_data, user, metadata, model):
                     "server": tool_server,
                 }
 
+    if mcp_clients:
+        metadata["mcp_clients"] = mcp_clients
+
     if tools_dict:
         if metadata.get("params", {}).get("function_calling") == "native":
             # If the function calling is native, then call the tools function calling handler
@@ -1050,9 +1351,7 @@ async def process_chat_payload(request, form_data, user, metadata, model):
         citation_idx_map = {}
 
         for source in sources:
-            is_tool_result = source.get("tool_result", False)
+            if "document" in source:
-
-            if "document" in source and not is_tool_result:
                 for document_text, document_metadata in zip(
                     source["document"], source["metadata"]
                 ):
@@ -1079,25 +1378,14 @@ async def process_chat_payload(request, form_data, user, metadata, model):
             raise Exception("No user message found")
 
         if context_string != "":
-            # Workaround for Ollama 2.0+ system prompt issue
+            form_data["messages"] = add_or_update_user_message(
-            # TODO: replace with add_or_update_system_message
-            if model.get("owned_by") == "ollama":
-                form_data["messages"] = prepend_to_first_user_message_content(
-                    rag_template(
-                        request.app.state.config.RAG_TEMPLATE,
-                        context_string,
-                        prompt,
-                    ),
-                    form_data["messages"],
-                )
-            else:
-                form_data["messages"] = add_or_update_system_message(
                 rag_template(
                     request.app.state.config.RAG_TEMPLATE,
                     context_string,
                     prompt,
                 ),
                 form_data["messages"],
+                append=False,
             )
 
     # If there are citations, add them to the data_items
@@ -1131,10 +1419,13 @@ async def process_chat_response(
     request, response, form_data, user, metadata, model, events, tasks
 ):
     async def background_tasks_handler():
+        message = None
+        messages = []
+
+        if "chat_id" in metadata and not metadata["chat_id"].startswith("local:"):
             messages_map = Chats.get_messages_map_by_chat_id(metadata["chat_id"])
             message = messages_map.get(metadata["message_id"]) if messages_map else None
 
-        if message:
             message_list = get_message_list(messages_map, metadata["message_id"])
 
             # Remove details tags and files from the messages.
@@ -1167,12 +1458,21 @@ async def process_chat_response(
                         "content": content,
                     }
                 )
+        else:
+            # Local temp chat, get the model and message from the form_data
+            message = get_last_user_message_item(form_data.get("messages", []))
+            messages = form_data.get("messages", [])
+            if message:
+                message["model"] = form_data.get("model")
 
+        if message and "model" in message:
             if tasks and messages:
                 if (
                     TASKS.FOLLOW_UP_GENERATION in tasks
                     and tasks[TASKS.FOLLOW_UP_GENERATION]
                 ):
+
+                    print("Generating follow ups")
                     res = await generate_follow_ups(
                         request,
                         {
@@ -1203,15 +1503,6 @@ async def process_chat_response(
                             follow_ups = json.loads(follow_ups_string).get(
                                 "follow_ups", []
                             )
-
-                            Chats.upsert_message_to_chat_by_id_and_message_id(
-                                metadata["chat_id"],
-                                metadata["message_id"],
-                                {
-                                    "followUps": follow_ups,
-                                },
-                            )
-
                             await event_emitter(
                                 {
                                     "type": "chat:message:follow_ups",
@@ -1220,10 +1511,26 @@ async def process_chat_response(
                                     },
                                 }
                             )
+
+                            if not metadata.get("chat_id", "").startswith("local:"):
+                                Chats.upsert_message_to_chat_by_id_and_message_id(
+                                    metadata["chat_id"],
+                                    metadata["message_id"],
+                                    {
+                                        "followUps": follow_ups,
+                                    },
+                                )
+
                         except Exception as e:
                             pass
 
-                if TASKS.TITLE_GENERATION in tasks:
+                if not metadata.get("chat_id", "").startswith(
+                    "local:"
+                ):  # Only update titles and tags for non-temp chats
+                    if (
+                        TASKS.TITLE_GENERATION in tasks
+                        and tasks[TASKS.TITLE_GENERATION]
+                    ):
                         user_message = get_last_user_message(messages)
                         if user_message and len(user_message) > 100:
                             user_message = user_message[:100] + "..."
@@ -1246,7 +1553,8 @@ async def process_chat_response(
                                         res.get("choices", [])[0]
                                         .get("message", {})
                                         .get(
-                                        "content", message.get("content", user_message)
+                                            "content",
+                                            message.get("content", user_message),
                                         )
                                     )
                                 else:
@@ -1266,7 +1574,9 @@ async def process_chat_response(
                                 if not title:
                                     title = messages[0].get("content", user_message)
 
-                            Chats.update_chat_title_by_id(metadata["chat_id"], title)
+                                Chats.update_chat_title_by_id(
+                                    metadata["chat_id"], title
+                                )
 
                                 await event_emitter(
                                     {
@@ -1352,7 +1662,9 @@ async def process_chat_response(
                         response.body, bytes
                     ):
                         try:
-                            response_data = json.loads(response.body.decode("utf-8"))
+                            response_data = json.loads(
+                                response.body.decode("utf-8", "replace")
+                            )
                         except json.JSONDecodeError:
                             response_data = {
                                 "error": {"detail": "Invalid JSON response"}
@@ -1498,7 +1810,7 @@ async def process_chat_response(
     oauth_token = None
     try:
         if request.cookies.get("oauth_session_id", None):
-            oauth_token = request.app.state.oauth_manager.get_oauth_token(
+            oauth_token = await request.app.state.oauth_manager.get_oauth_token(
                 user.id,
                 request.cookies.get("oauth_session_id", None),
             )
@@ -1581,7 +1893,8 @@ async def process_chat_response(
                                         break
 
                                 if tool_result is not None:
-                                    tool_calls_display_content = f'{tool_calls_display_content}<details type="tool_calls" done="true" id="{tool_call_id}" name="{tool_name}" arguments="{html.escape(json.dumps(tool_arguments))}" result="{html.escape(json.dumps(tool_result, ensure_ascii=False))}" files="{html.escape(json.dumps(tool_result_files)) if tool_result_files else ""}">\n<summary>Tool Executed</summary>\n</details>\n'
+                                    tool_result_embeds = result.get("embeds", "")
+                                    tool_calls_display_content = f'{tool_calls_display_content}<details type="tool_calls" done="true" id="{tool_call_id}" name="{tool_name}" arguments="{html.escape(json.dumps(tool_arguments))}" result="{html.escape(json.dumps(tool_result, ensure_ascii=False))}" files="{html.escape(json.dumps(tool_result_files)) if tool_result_files else ""}" embeds="{html.escape(json.dumps(tool_result_embeds))}">\n<summary>Tool Executed</summary>\n</details>\n'
                                 else:
                                     tool_calls_display_content = f'{tool_calls_display_content}<details type="tool_calls" done="false" id="{tool_call_id}" name="{tool_name}" arguments="{html.escape(json.dumps(tool_arguments))}">\n<summary>Executing...</summary>\n</details>\n'
 
@@ -1985,7 +2298,11 @@ async def process_chat_response(
                             last_delta_data = None
 
                     async for line in response.body_iterator:
-                        line = line.decode("utf-8") if isinstance(line, bytes) else line
+                        line = (
+                            line.decode("utf-8", "replace")
+                            if isinstance(line, bytes)
+                            else line
+                        )
                         data = line
 
                         # Skip empty lines
@@ -2031,6 +2348,20 @@ async def process_chat_response(
                                     )
                                 else:
                                     choices = data.get("choices", [])
+
+                                    # 17421
+                                    usage = data.get("usage", {}) or {}
+                                    usage.update(data.get("timings", {}))  # llama.cpp
+                                    if usage:
+                                        await event_emitter(
+                                            {
+                                                "type": "chat:completion",
+                                                "data": {
+                                                    "usage": usage,
+                                                },
+                                            }
+                                        )
+
                                     if not choices:
                                         error = data.get("error", {})
                                         if error:
@@ -2042,20 +2373,6 @@ async def process_chat_response(
                                                     },
                                                 }
                                             )
-                                        usage = data.get("usage", {})
-                                        usage.update(
-                                            data.get("timings", {})
-                                        )  # llama.cpp
-
-                                        if usage:
-                                            await event_emitter(
-                                                {
-                                                    "type": "chat:completion",
-                                                    "data": {
-                                                        "usage": usage,
-                                                    },
-                                                }
-                                            )
                                         continue
 
                                     delta = choices[0].get("delta", {})
@@ -2328,8 +2645,12 @@ async def process_chat_response(
                     results = []
 
                     for tool_call in response_tool_calls:
+
+                        print("tool_call", tool_call)
                         tool_call_id = tool_call.get("id", "")
-                        tool_name = tool_call.get("function", {}).get("name", "")
+                        tool_function_name = tool_call.get("function", {}).get(
+                            "name", ""
+                        )
                         tool_args = tool_call.get("function", {}).get("arguments", "{}")
 
                         tool_function_params = {}
@@ -2359,11 +2680,17 @@ async def process_chat_response(
                         )
 
                         tool_result = None
+                        tool = None
+                        tool_type = None
+                        direct_tool = False
 
-                        if tool_name in tools:
+                        if tool_function_name in tools:
-                            tool = tools[tool_name]
+                            tool = tools[tool_function_name]
                             spec = tool.get("spec", {})
 
+                            tool_type = tool.get("type", "")
+                            direct_tool = tool.get("direct", False)
+
                             try:
                                 allowed_params = (
                                     spec.get("parameters", {})
@@ -2377,13 +2704,13 @@ async def process_chat_response(
                                     if k in allowed_params
                                 }
 
-                                if tool.get("direct", False):
+                                if direct_tool:
                                     tool_result = await event_caller(
                                         {
                                             "type": "execute:tool",
                                             "data": {
                                                 "id": str(uuid4()),
-                                                "name": tool_name,
+                                                "name": tool_function_name,
                                                 "params": tool_function_params,
                                                 "server": tool.get("server", {}),
                                                 "session_id": metadata.get(
@@ -2402,19 +2729,16 @@ async def process_chat_response(
                             except Exception as e:
                                 tool_result = str(e)
 
-                        tool_result_files = []
+                        tool_result, tool_result_files, tool_result_embeds = (
-                        if isinstance(tool_result, list):
+                            process_tool_result(
-                            for item in tool_result:
+                                request,
-                                # check if string
+                                tool_function_name,
-                                if isinstance(item, str) and item.startswith("data:"):
+                                tool_result,
-                                    tool_result_files.append(item)
+                                tool_type,
-                                    tool_result.remove(item)
+                                direct_tool,
-
+                                metadata,
-                        if isinstance(tool_result, dict) or isinstance(
+                                user,
-                            tool_result, list
+                            )
-                        ):
-                            tool_result = json.dumps(
-                                tool_result, indent=2, ensure_ascii=False
                         )
 
                         results.append(
@@ -2426,11 +2750,15 @@ async def process_chat_response(
                                     if tool_result_files
                                     else {}
                                 ),
+                                **(
+                                    {"embeds": tool_result_embeds}
+                                    if tool_result_embeds
+                                    else {}
+                                ),
                             }
                         )
 
                     content_blocks[-1]["results"] = results
-
                     content_blocks.append(
                         {
                             "type": "text",
@@ -2571,20 +2899,15 @@ async def process_chat_response(
                                     if isinstance(stdout, str):
                                         stdoutLines = stdout.split("\n")
                                         for idx, line in enumerate(stdoutLines):
+
                                             if "data:image/png;base64" in line:
-                                                image_url = ""
+                                                image_url = get_image_url_from_base64(
-                                                # Extract base64 image data from the line
-                                                image_data, content_type = (
-                                                    load_b64_image_data(line)
-                                                )
-                                                if image_data is not None:
-                                                    image_url = upload_image(
                                                     request,
-                                                        image_data,
+                                                    line,
-                                                        content_type,
                                                     metadata,
                                                     user,
                                                 )
+                                                if image_url:
                                                     stdoutLines[idx] = (
                                                         f"![Output Image]({image_url})"
                                                     )
@@ -2597,16 +2920,9 @@ async def process_chat_response(
                                         resultLines = result.split("\n")
                                         for idx, line in enumerate(resultLines):
                                             if "data:image/png;base64" in line:
-                                                image_url = ""
+                                                image_url = get_image_url_from_base64(
-                                                # Extract base64 image data from the line
-                                                image_data, content_type = (
-                                                    load_b64_image_data(line)
-                                                )
-                                                if image_data is not None:
-                                                    image_url = upload_image(
                                                     request,
-                                                        image_data,
+                                                    line,
-                                                        content_type,
                                                     metadata,
                                                     user,
                                                 )

backend/open_webui/utils/misc.py

@@ -120,17 +120,26 @@ def pop_system_message(messages: list[dict]) -> tuple[Optional[dict], list[dict]
     return get_system_message(messages), remove_system_message(messages)
 
 
-def prepend_to_first_user_message_content(
+def update_message_content(message: dict, content: str, append: bool = True) -> dict:
-    content: str, messages: list[dict]
-) -> list[dict]:
-    for message in messages:
-        if message["role"] == "user":
     if isinstance(message["content"], list):
         for item in message["content"]:
             if item["type"] == "text":
+                if append:
+                    item["text"] = f"{item['text']}\n{content}"
+                else:
                     item["text"] = f"{content}\n{item['text']}"
+    else:
+        if append:
+            message["content"] = f"{message['content']}\n{content}"
         else:
             message["content"] = f"{content}\n{message['content']}"
+    return message
+
+
+def replace_system_message_content(content: str, messages: list[dict]) -> dict:
+    for message in messages:
+        if message["role"] == "system":
+            message["content"] = content
             break
     return messages
 
@@ -148,10 +157,7 @@ def add_or_update_system_message(
     """
 
     if messages and messages[0].get("role") == "system":
-        if append:
+        messages[0] = update_message_content(messages[0], content, append)
-            messages[0]["content"] = f"{messages[0]['content']}\n{content}"
-        else:
-            messages[0]["content"] = f"{content}\n{messages[0]['content']}"
     else:
         # Insert at the beginning
         messages.insert(0, {"role": "system", "content": content})
@@ -159,7 +165,7 @@ def add_or_update_system_message(
     return messages
 
 
-def add_or_update_user_message(content: str, messages: list[dict]):
+def add_or_update_user_message(content: str, messages: list[dict], append: bool = True):
     """
     Adds a new user message at the end of the messages list
     or updates the existing user message at the end.
@@ -170,7 +176,7 @@ def add_or_update_user_message(content: str, messages: list[dict]):
     """
 
     if messages and messages[-1].get("role") == "user":
-        messages[-1]["content"] = f"{messages[-1]['content']}\n{content}"
+        messages[-1] = update_message_content(messages[-1], content, append)
     else:
         # Insert at the end
         messages.append({"role": "user", "content": content})
@@ -178,6 +184,16 @@ def add_or_update_user_message(content: str, messages: list[dict]):
     return messages
 
 
+def prepend_to_first_user_message_content(
+    content: str, messages: list[dict]
+) -> list[dict]:
+    for message in messages:
+        if message["role"] == "user":
+            message = update_message_content(message, content, append=False)
+            break
+    return messages
+
+
 def append_or_update_assistant_message(content: str, messages: list[dict]):
     """
     Adds a new assistant message at the end of the messages list
@@ -383,17 +399,10 @@ def parse_ollama_modelfile(model_text):
         "top_k": int,
         "top_p": float,
         "num_keep": int,
-        "typical_p": float,
         "presence_penalty": float,
         "frequency_penalty": float,
-        "penalize_newline": bool,
-        "numa": bool,
         "num_batch": int,
         "num_gpu": int,
-        "main_gpu": int,
-        "low_vram": bool,
-        "f16_kv": bool,
-        "vocab_only": bool,
         "use_mmap": bool,
         "use_mlock": bool,
         "num_thread": int,

backend/open_webui/utils/models.py

@@ -22,10 +22,11 @@ from open_webui.utils.access_control import has_access
 
 
 from open_webui.config import (
+    BYPASS_ADMIN_ACCESS_CONTROL,
     DEFAULT_ARENA_MODEL,
 )
 
-from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+from open_webui.env import BYPASS_MODEL_ACCESS_CONTROL, SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
 from open_webui.models.users import UserModel
 
 
@@ -262,6 +263,7 @@ async def get_all_models(request, refresh: bool = False, user: UserModel = None)
                 "icon": function.meta.manifest.get("icon_url", None)
                 or getattr(module, "icon_url", None)
                 or getattr(module, "icon", None),
+                "has_user_valves": hasattr(module, "UserValves"),
             }
         ]
 
@@ -332,3 +334,40 @@ def check_model_access(user, model):
             )
         ):
             raise Exception("Model not found")
+
+
+def get_filtered_models(models, user):
+    # Filter out models that the user does not have access to
+    if (
+        user.role == "user"
+        or (user.role == "admin" and not BYPASS_ADMIN_ACCESS_CONTROL)
+    ) and not BYPASS_MODEL_ACCESS_CONTROL:
+        filtered_models = []
+        for model in models:
+            if model.get("arena"):
+                if has_access(
+                    user.id,
+                    type="read",
+                    access_control=model.get("info", {})
+                    .get("meta", {})
+                    .get("access_control", {}),
+                ):
+                    filtered_models.append(model)
+                continue
+
+            model_info = Models.get_model_by_id(model["id"])
+            if model_info:
+                if (
+                    (user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL)
+                    or user.id == model_info.user_id
+                    or has_access(
+                        user.id,
+                        type="read",
+                        access_control=model_info.access_control,
+                    )
+                ):
+                    filtered_models.append(model)
+
+        return filtered_models
+    else:
+        return models

backend/open_webui/utils/oauth.py

@@ -1,7 +1,9 @@
 import base64
+import hashlib
 import logging
 import mimetypes
 import sys
+import urllib
 import uuid
 import json
 from datetime import datetime, timedelta
@@ -9,6 +11,9 @@ from datetime import datetime, timedelta
 import re
 import fnmatch
 import time
+import secrets
+from cryptography.fernet import Fernet
+
 
 import aiohttp
 from authlib.integrations.starlette_client import OAuth
@@ -18,6 +23,7 @@ from fastapi import (
     status,
 )
 from starlette.responses import RedirectResponse
+from typing import Optional
 
 
 from open_webui.models.auths import Auths
@@ -56,11 +62,27 @@ from open_webui.env import (
     WEBUI_AUTH_COOKIE_SAME_SITE,
     WEBUI_AUTH_COOKIE_SECURE,
     ENABLE_OAUTH_ID_TOKEN_COOKIE,
+    OAUTH_CLIENT_INFO_ENCRYPTION_KEY,
 )
 from open_webui.utils.misc import parse_duration
 from open_webui.utils.auth import get_password_hash, create_token
 from open_webui.utils.webhook import post_webhook
 
+from mcp.shared.auth import (
+    OAuthClientMetadata,
+    OAuthMetadata,
+)
+
+
+class OAuthClientInformationFull(OAuthClientMetadata):
+    issuer: Optional[str] = None  # URL of the OAuth server that issued this client
+
+    client_id: str
+    client_secret: str | None = None
+    client_id_issued_at: int | None = None
+    client_secret_expires_at: int | None = None
+
+
 from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
 
 logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
@@ -89,6 +111,42 @@ auth_manager_config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
 auth_manager_config.OAUTH_UPDATE_PICTURE_ON_LOGIN = OAUTH_UPDATE_PICTURE_ON_LOGIN
 
 
+FERNET = None
+
+if len(OAUTH_CLIENT_INFO_ENCRYPTION_KEY) != 44:
+    key_bytes = hashlib.sha256(OAUTH_CLIENT_INFO_ENCRYPTION_KEY.encode()).digest()
+    OAUTH_CLIENT_INFO_ENCRYPTION_KEY = base64.urlsafe_b64encode(key_bytes)
+else:
+    OAUTH_CLIENT_INFO_ENCRYPTION_KEY = OAUTH_CLIENT_INFO_ENCRYPTION_KEY.encode()
+
+try:
+    FERNET = Fernet(OAUTH_CLIENT_INFO_ENCRYPTION_KEY)
+except Exception as e:
+    log.error(f"Error initializing Fernet with provided key: {e}")
+    raise
+
+
+def encrypt_data(data) -> str:
+    """Encrypt data for storage"""
+    try:
+        data_json = json.dumps(data)
+        encrypted = FERNET.encrypt(data_json.encode()).decode()
+        return encrypted
+    except Exception as e:
+        log.error(f"Error encrypting data: {e}")
+        raise
+
+
+def decrypt_data(data: str):
+    """Decrypt data from storage"""
+    try:
+        decrypted = FERNET.decrypt(data.encode()).decode()
+        return json.loads(decrypted)
+    except Exception as e:
+        log.error(f"Error decrypting data: {e}")
+        raise
+
+
 def is_in_blocked_groups(group_name: str, groups: list) -> bool:
     """
     Check if a group name matches any blocked pattern.
@@ -133,14 +191,438 @@ def is_in_blocked_groups(group_name: str, groups: list) -> bool:
     return False
 
 
+def get_parsed_and_base_url(server_url) -> tuple[urllib.parse.ParseResult, str]:
+    parsed = urllib.parse.urlparse(server_url)
+    base_url = f"{parsed.scheme}://{parsed.netloc}"
+    return parsed, base_url
+
+
+def get_discovery_urls(server_url) -> list[str]:
+    parsed, base_url = get_parsed_and_base_url(server_url)
+
+    urls = [
+        urllib.parse.urljoin(base_url, "/.well-known/oauth-authorization-server"),
+        urllib.parse.urljoin(base_url, "/.well-known/openid-configuration"),
+    ]
+
+    if parsed.path and parsed.path != "/":
+        urls.append(
+            urllib.parse.urljoin(
+                base_url,
+                f"/.well-known/oauth-authorization-server{parsed.path.rstrip('/')}",
+            )
+        )
+        urls.append(
+            urllib.parse.urljoin(
+                base_url, f"/.well-known/openid-configuration{parsed.path.rstrip('/')}"
+            )
+        )
+
+    return urls
+
+
+# TODO: Some OAuth providers require Initial Access Tokens (IATs) for dynamic client registration.
+# This is not currently supported.
+async def get_oauth_client_info_with_dynamic_client_registration(
+    request,
+    client_id: str,
+    oauth_server_url: str,
+    oauth_server_key: Optional[str] = None,
+) -> OAuthClientInformationFull:
+    try:
+        oauth_server_metadata = None
+        oauth_server_metadata_url = None
+
+        redirect_base_url = (
+            str(request.app.state.config.WEBUI_URL or request.base_url)
+        ).rstrip("/")
+
+        oauth_client_metadata = OAuthClientMetadata(
+            client_name="Open WebUI",
+            redirect_uris=[f"{redirect_base_url}/oauth/clients/{client_id}/callback"],
+            grant_types=["authorization_code", "refresh_token"],
+            response_types=["code"],
+            token_endpoint_auth_method="client_secret_post",
+        )
+
+        # Attempt to fetch OAuth server metadata to get registration endpoint & scopes
+        discovery_urls = get_discovery_urls(oauth_server_url)
+        for url in discovery_urls:
+            async with aiohttp.ClientSession() as session:
+                async with session.get(
+                    url, ssl=AIOHTTP_CLIENT_SESSION_SSL
+                ) as oauth_server_metadata_response:
+                    if oauth_server_metadata_response.status == 200:
+                        try:
+                            oauth_server_metadata = OAuthMetadata.model_validate(
+                                await oauth_server_metadata_response.json()
+                            )
+                            oauth_server_metadata_url = url
+                            if (
+                                oauth_client_metadata.scope is None
+                                and oauth_server_metadata.scopes_supported is not None
+                            ):
+                                oauth_client_metadata.scope = " ".join(
+                                    oauth_server_metadata.scopes_supported
+                                )
+                            break
+                        except Exception as e:
+                            log.error(f"Error parsing OAuth metadata from {url}: {e}")
+                            continue
+
+        registration_url = None
+        if oauth_server_metadata and oauth_server_metadata.registration_endpoint:
+            registration_url = str(oauth_server_metadata.registration_endpoint)
+        else:
+            _, base_url = get_parsed_and_base_url(oauth_server_url)
+            registration_url = urllib.parse.urljoin(base_url, "/register")
+
+        registration_data = oauth_client_metadata.model_dump(
+            exclude_none=True,
+            mode="json",
+            by_alias=True,
+        )
+
+        # Perform dynamic client registration and return client info
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                registration_url, json=registration_data, ssl=AIOHTTP_CLIENT_SESSION_SSL
+            ) as oauth_client_registration_response:
+                try:
+                    registration_response_json = (
+                        await oauth_client_registration_response.json()
+                    )
+                    oauth_client_info = OAuthClientInformationFull.model_validate(
+                        {
+                            **registration_response_json,
+                            **{"issuer": oauth_server_metadata_url},
+                        }
+                    )
+                    log.info(
+                        f"Dynamic client registration successful at {registration_url}, client_id: {oauth_client_info.client_id}"
+                    )
+                    return oauth_client_info
+                except Exception as e:
+                    error_text = None
+                    try:
+                        error_text = await oauth_client_registration_response.text()
+                        log.error(
+                            f"Dynamic client registration failed at {registration_url}: {oauth_client_registration_response.status} - {error_text}"
+                        )
+                    except Exception as e:
+                        pass
+
+                    log.error(f"Error parsing client registration response: {e}")
+                    raise Exception(
+                        f"Dynamic client registration failed: {error_text}"
+                        if error_text
+                        else "Error parsing client registration response"
+                    )
+        raise Exception("Dynamic client registration failed")
+    except Exception as e:
+        log.error(f"Exception during dynamic client registration: {e}")
+        raise e
+
+
+class OAuthClientManager:
+    def __init__(self, app):
+        self.oauth = OAuth()
+        self.app = app
+        self.clients = {}
+
+    def add_client(self, client_id, oauth_client_info: OAuthClientInformationFull):
+        self.clients[client_id] = {
+            "client": self.oauth.register(
+                name=client_id,
+                client_id=oauth_client_info.client_id,
+                client_secret=oauth_client_info.client_secret,
+                client_kwargs=(
+                    {"scope": oauth_client_info.scope}
+                    if oauth_client_info.scope
+                    else {}
+                ),
+                server_metadata_url=(
+                    oauth_client_info.issuer if oauth_client_info.issuer else None
+                ),
+            ),
+            "client_info": oauth_client_info,
+        }
+        return self.clients[client_id]
+
+    def remove_client(self, client_id):
+        if client_id in self.clients:
+            del self.clients[client_id]
+            log.info(f"Removed OAuth client {client_id}")
+        return True
+
+    def get_client(self, client_id):
+        client = self.clients.get(client_id)
+        return client["client"] if client else None
+
+    def get_client_info(self, client_id):
+        client = self.clients.get(client_id)
+        return client["client_info"] if client else None
+
+    def get_server_metadata_url(self, client_id):
+        if client_id in self.clients:
+            client = self.clients[client_id]
+            return (
+                client.server_metadata_url
+                if hasattr(client, "server_metadata_url")
+                else None
+            )
+        return None
+
+    async def get_oauth_token(
+        self, user_id: str, client_id: str, force_refresh: bool = False
+    ):
+        """
+        Get a valid OAuth token for the user, automatically refreshing if needed.
+
+        Args:
+            user_id: The user ID
+            client_id: The OAuth client ID (provider)
+            force_refresh: Force token refresh even if current token appears valid
+
+        Returns:
+            dict: OAuth token data with access_token, or None if no valid token available
+        """
+        try:
+            # Get the OAuth session
+            session = OAuthSessions.get_session_by_provider_and_user_id(
+                client_id, user_id
+            )
+            if not session:
+                log.warning(
+                    f"No OAuth session found for user {user_id}, client_id {client_id}"
+                )
+                return None
+
+            if force_refresh or datetime.now() + timedelta(
+                minutes=5
+            ) >= datetime.fromtimestamp(session.expires_at):
+                log.debug(
+                    f"Token refresh needed for user {user_id}, client_id {session.provider}"
+                )
+                refreshed_token = await self._refresh_token(session)
+                if refreshed_token:
+                    return refreshed_token
+                else:
+                    log.warning(
+                        f"Token refresh failed for user {user_id}, client_id {session.provider}, deleting session {session.id}"
+                    )
+                    OAuthSessions.delete_session_by_id(session.id)
+                    return None
+            return session.token
+
+        except Exception as e:
+            log.error(f"Error getting OAuth token for user {user_id}: {e}")
+            return None
+
+    async def _refresh_token(self, session) -> dict:
+        """
+        Refresh an OAuth token if needed, with concurrency protection.
+
+        Args:
+            session: The OAuth session object
+
+        Returns:
+            dict: Refreshed token data, or None if refresh failed
+        """
+        try:
+            # Perform the actual refresh
+            refreshed_token = await self._perform_token_refresh(session)
+
+            if refreshed_token:
+                # Update the session with new token data
+                session = OAuthSessions.update_session_by_id(
+                    session.id, refreshed_token
+                )
+                log.info(f"Successfully refreshed token for session {session.id}")
+                return session.token
+            else:
+                log.error(f"Failed to refresh token for session {session.id}")
+                return None
+
+        except Exception as e:
+            log.error(f"Error refreshing token for session {session.id}: {e}")
+            return None
+
+    async def _perform_token_refresh(self, session) -> dict:
+        """
+        Perform the actual OAuth token refresh.
+
+        Args:
+            session: The OAuth session object
+
+        Returns:
+            dict: New token data, or None if refresh failed
+        """
+        client_id = session.provider
+        token_data = session.token
+
+        if not token_data.get("refresh_token"):
+            log.warning(f"No refresh token available for session {session.id}")
+            return None
+
+        try:
+            client = self.get_client(client_id)
+            if not client:
+                log.error(f"No OAuth client found for provider {client_id}")
+                return None
+
+            token_endpoint = None
+            async with aiohttp.ClientSession(trust_env=True) as session_http:
+                async with session_http.get(
+                    self.get_server_metadata_url(client_id)
+                ) as r:
+                    if r.status == 200:
+                        openid_data = await r.json()
+                        token_endpoint = openid_data.get("token_endpoint")
+                    else:
+                        log.error(
+                            f"Failed to fetch OpenID configuration for client_id {client_id}"
+                        )
+            if not token_endpoint:
+                log.error(f"No token endpoint found for client_id {client_id}")
+                return None
+
+            # Prepare refresh request
+            refresh_data = {
+                "grant_type": "refresh_token",
+                "refresh_token": token_data["refresh_token"],
+                "client_id": client.client_id,
+            }
+            if hasattr(client, "client_secret") and client.client_secret:
+                refresh_data["client_secret"] = client.client_secret
+
+            # Make refresh request
+            async with aiohttp.ClientSession(trust_env=True) as session_http:
+                async with session_http.post(
+                    token_endpoint,
+                    data=refresh_data,
+                    headers={"Content-Type": "application/x-www-form-urlencoded"},
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
+                ) as r:
+                    if r.status == 200:
+                        new_token_data = await r.json()
+
+                        # Merge with existing token data (preserve refresh_token if not provided)
+                        if "refresh_token" not in new_token_data:
+                            new_token_data["refresh_token"] = token_data[
+                                "refresh_token"
+                            ]
+
+                        # Add timestamp for tracking
+                        new_token_data["issued_at"] = datetime.now().timestamp()
+
+                        # Calculate expires_at if we have expires_in
+                        if (
+                            "expires_in" in new_token_data
+                            and "expires_at" not in new_token_data
+                        ):
+                            new_token_data["expires_at"] = int(
+                                datetime.now().timestamp()
+                                + new_token_data["expires_in"]
+                            )
+
+                        log.debug(f"Token refresh successful for client_id {client_id}")
+                        return new_token_data
+                    else:
+                        error_text = await r.text()
+                        log.error(
+                            f"Token refresh failed for client_id {client_id}: {r.status} - {error_text}"
+                        )
+                        return None
+
+        except Exception as e:
+            log.error(f"Exception during token refresh for client_id {client_id}: {e}")
+            return None
+
+    async def handle_authorize(self, request, client_id: str) -> RedirectResponse:
+        client = self.get_client(client_id)
+        if client is None:
+            raise HTTPException(404)
+
+        client_info = self.get_client_info(client_id)
+        if client_info is None:
+            raise HTTPException(404)
+
+        redirect_uri = (
+            client_info.redirect_uris[0] if client_info.redirect_uris else None
+        )
+        return await client.authorize_redirect(request, str(redirect_uri))
+
+    async def handle_callback(self, request, client_id: str, user_id: str, response):
+        client = self.get_client(client_id)
+        if client is None:
+            raise HTTPException(404)
+
+        error_message = None
+        try:
+            token = await client.authorize_access_token(request)
+            if token:
+                try:
+                    # Add timestamp for tracking
+                    token["issued_at"] = datetime.now().timestamp()
+
+                    # Calculate expires_at if we have expires_in
+                    if "expires_in" in token and "expires_at" not in token:
+                        token["expires_at"] = (
+                            datetime.now().timestamp() + token["expires_in"]
+                        )
+
+                    # Clean up any existing sessions for this user/client_id first
+                    sessions = OAuthSessions.get_sessions_by_user_id(user_id)
+                    for session in sessions:
+                        if session.provider == client_id:
+                            OAuthSessions.delete_session_by_id(session.id)
+
+                    session = OAuthSessions.create_session(
+                        user_id=user_id,
+                        provider=client_id,
+                        token=token,
+                    )
+                    log.info(
+                        f"Stored OAuth session server-side for user {user_id}, client_id {client_id}"
+                    )
+                except Exception as e:
+                    error_message = "Failed to store OAuth session server-side"
+                    log.error(f"Failed to store OAuth session server-side: {e}")
+            else:
+                error_message = "Failed to obtain OAuth token"
+                log.warning(error_message)
+        except Exception as e:
+            error_message = "OAuth callback error"
+            log.warning(f"OAuth callback error: {e}")
+
+        redirect_url = (
+            str(request.app.state.config.WEBUI_URL or request.base_url)
+        ).rstrip("/")
+
+        if error_message:
+            log.debug(error_message)
+            redirect_url = f"{redirect_url}/?error={error_message}"
+            return RedirectResponse(url=redirect_url, headers=response.headers)
+
+        response = RedirectResponse(url=redirect_url, headers=response.headers)
+        return response
+
+
 class OAuthManager:
     def __init__(self, app):
         self.oauth = OAuth()
         self.app = app
 
         self._clients = {}
-        for _, provider_config in OAUTH_PROVIDERS.items():
+
-            provider_config["register"](self.oauth)
+        for name, provider_config in OAUTH_PROVIDERS.items():
+            if "register" not in provider_config:
+                log.error(f"OAuth provider {name} missing register function")
+                continue
+
+            client = provider_config["register"](self.oauth)
+            self._clients[name] = client
 
     def get_client(self, provider_name):
         if provider_name not in self._clients:
@@ -157,7 +639,7 @@ class OAuthManager:
             )
         return None
 
-    def get_oauth_token(
+    async def get_oauth_token(
         self, user_id: str, session_id: str, force_refresh: bool = False
     ):
         """
@@ -186,13 +668,15 @@ class OAuthManager:
                 log.debug(
                     f"Token refresh needed for user {user_id}, provider {session.provider}"
                 )
-                refreshed_token = self._refresh_token(session)
+                refreshed_token = await self._refresh_token(session)
                 if refreshed_token:
                     return refreshed_token
                 else:
                     log.warning(
-                        f"Token refresh failed for user {user_id}, provider {session.provider}"
+                        f"Token refresh failed for user {user_id}, provider {session.provider}, deleting session {session.id}"
                     )
+                    OAuthSessions.delete_session_by_id(session.id)
+
                     return None
             return session.token
 
@@ -252,9 +736,10 @@ class OAuthManager:
                 log.error(f"No OAuth client found for provider {provider}")
                 return None
 
+            server_metadata_url = self.get_server_metadata_url(provider)
             token_endpoint = None
             async with aiohttp.ClientSession(trust_env=True) as session_http:
-                async with session_http.get(client.gserver_metadata_url) as r:
+                async with session_http.get(server_metadata_url) as r:
                     if r.status == 200:
                         openid_data = await r.json()
                         token_endpoint = openid_data.get("token_endpoint")
@@ -301,7 +786,7 @@ class OAuthManager:
                             "expires_in" in new_token_data
                             and "expires_at" not in new_token_data
                         ):
-                            new_token_data["expires_at"] = (
+                            new_token_data["expires_at"] = int(
                                 datetime.now().timestamp()
                                 + new_token_data["expires_in"]
                             )
@@ -574,7 +1059,7 @@ class OAuthManager:
             raise HTTPException(404)
         # If the provider has a custom redirect URL, use that, otherwise automatically generate one
         redirect_uri = OAUTH_PROVIDERS[provider].get("redirect_uri") or request.url_for(
-            "oauth_callback", provider=provider
+            "oauth_login_callback", provider=provider
         )
         client = self.get_client(provider)
         if client is None:
@@ -791,9 +1276,9 @@ class OAuthManager:
                 else ERROR_MESSAGES.DEFAULT("Error during OAuth process")
             )
 
-        redirect_base_url = str(request.app.state.config.WEBUI_URL or request.base_url)
+        redirect_base_url = (
-        if redirect_base_url.endswith("/"):
+            str(request.app.state.config.WEBUI_URL or request.base_url)
-            redirect_base_url = redirect_base_url[:-1]
+        ).rstrip("/")
         redirect_url = f"{redirect_base_url}/auth"
 
         if error_message:

backend/open_webui/utils/payload.py

@@ -2,6 +2,7 @@ from open_webui.utils.task import prompt_template, prompt_variables_template
 from open_webui.utils.misc import (
     deep_update,
     add_or_update_system_message,
+    replace_system_message_content,
 )
 
 from typing import Callable, Optional
@@ -10,7 +11,11 @@ import json
 
 # inplace function: form_data is modified
 def apply_system_prompt_to_body(
-    system: Optional[str], form_data: dict, metadata: Optional[dict] = None, user=None
+    system: Optional[str],
+    form_data: dict,
+    metadata: Optional[dict] = None,
+    user=None,
+    replace: bool = False,
 ) -> dict:
     if not system:
         return form_data
@@ -24,9 +29,15 @@ def apply_system_prompt_to_body(
     # Legacy (API Usage)
     system = prompt_template(system, user)
 
+    if replace:
+        form_data["messages"] = replace_system_message_content(
+            system, form_data.get("messages", [])
+        )
+    else:
         form_data["messages"] = add_or_update_system_message(
             system, form_data.get("messages", [])
         )
+
     return form_data
 
 
@@ -153,17 +164,11 @@ def apply_model_params_to_body_ollama(params: dict, form_data: dict) -> dict:
         "repeat_last_n": int,
         "top_k": int,
         "min_p": float,
-        "typical_p": float,
         "repeat_penalty": float,
         "presence_penalty": float,
         "frequency_penalty": float,
-        "penalize_newline": bool,
         "stop": lambda x: [bytes(s, "utf-8").decode("unicode_escape") for s in x],
-        "numa": bool,
         "num_gpu": int,
-        "main_gpu": int,
-        "low_vram": bool,
-        "vocab_only": bool,
         "use_mmap": bool,
         "use_mlock": bool,
         "num_thread": int,

backend/open_webui/utils/plugin.py

@@ -166,6 +166,48 @@ def load_function_module_by_id(function_id: str, content: str | None = None):
         os.unlink(temp_file.name)
 
 
+def get_tool_module_from_cache(request, tool_id, load_from_db=True):
+    if load_from_db:
+        # Always load from the database by default
+        tool = Tools.get_tool_by_id(tool_id)
+        if not tool:
+            raise Exception(f"Tool not found: {tool_id}")
+        content = tool.content
+
+        new_content = replace_imports(content)
+        if new_content != content:
+            content = new_content
+            # Update the tool content in the database
+            Tools.update_tool_by_id(tool_id, {"content": content})
+
+        if (
+            hasattr(request.app.state, "TOOL_CONTENTS")
+            and tool_id in request.app.state.TOOL_CONTENTS
+        ) and (
+            hasattr(request.app.state, "TOOLS") and tool_id in request.app.state.TOOLS
+        ):
+            if request.app.state.TOOL_CONTENTS[tool_id] == content:
+                return request.app.state.TOOLS[tool_id], None
+
+        tool_module, frontmatter = load_tool_module_by_id(tool_id, content)
+    else:
+        if hasattr(request.app.state, "TOOLS") and tool_id in request.app.state.TOOLS:
+            return request.app.state.TOOLS[tool_id], None
+
+        tool_module, frontmatter = load_tool_module_by_id(tool_id)
+
+    if not hasattr(request.app.state, "TOOLS"):
+        request.app.state.TOOLS = {}
+
+    if not hasattr(request.app.state, "TOOL_CONTENTS"):
+        request.app.state.TOOL_CONTENTS = {}
+
+    request.app.state.TOOLS[tool_id] = tool_module
+    request.app.state.TOOL_CONTENTS[tool_id] = content
+
+    return tool_module, frontmatter
+
+
 def get_function_module_from_cache(request, function_id, load_from_db=True):
     if load_from_db:
         # Always load from the database by default

backend/open_webui/utils/telemetry/metrics.py

@@ -163,7 +163,16 @@ def setup_metrics(app: FastAPI, resource: Resource) -> None:
     @app.middleware("http")
     async def _metrics_middleware(request: Request, call_next):
         start_time = time.perf_counter()
+
+        status_code = None
+        try:
             response = await call_next(request)
+            status_code = getattr(response, "status_code", 500)
+            return response
+        except Exception:
+            status_code = 500
+            raise
+        finally:
             elapsed_ms = (time.perf_counter() - start_time) * 1000.0
 
             # Route template e.g. "/items/{item_id}" instead of real path.
@@ -173,10 +182,8 @@ def setup_metrics(app: FastAPI, resource: Resource) -> None:
             attrs: Dict[str, str | int] = {
                 "http.method": request.method,
                 "http.route": route_path,
-            "http.status_code": response.status_code,
+                "http.status_code": status_code,
             }
 
             request_counter.add(1, attrs)
             duration_histogram.record(elapsed_ms, attrs)
-
-        return response

backend/open_webui/utils/tools.py

@@ -96,8 +96,23 @@ async def get_tools(
     for tool_id in tool_ids:
         tool = Tools.get_tool_by_id(tool_id)
         if tool is None:
+
             if tool_id.startswith("server:"):
-                server_id = tool_id.split(":")[1]
+                splits = tool_id.split(":")
+
+                if len(splits) == 2:
+                    type = "openapi"
+                    server_id = splits[1]
+                elif len(splits) == 3:
+                    type = splits[1]
+                    server_id = splits[2]
+
+                server_id_splits = server_id.split("|")
+                if len(server_id_splits) == 2:
+                    server_id = server_id_splits[0]
+                    function_names = server_id_splits[1].split(",")
+
+                if type == "openapi":
 
                     tool_server_data = None
                     for server in await get_tool_servers(request):
@@ -111,7 +126,9 @@ async def get_tools(
 
                     tool_server_idx = tool_server_data.get("idx", 0)
                     tool_server_connection = (
-                    request.app.state.config.TOOL_SERVER_CONNECTIONS[tool_server_idx]
+                        request.app.state.config.TOOL_SERVER_CONNECTIONS[
+                            tool_server_idx
+                        ]
                     )
 
                     specs = tool_server_data.get("specs", [])
@@ -145,7 +162,9 @@ async def get_tools(
 
                         headers["Content-Type"] = "application/json"
 
-                    def make_tool_function(function_name, tool_server_data, headers):
+                        def make_tool_function(
+                            function_name, tool_server_data, headers
+                        ):
                             async def tool_function(**kwargs):
                                 return await execute_tool_server(
                                     url=tool_server_data["url"],
@@ -171,6 +190,8 @@ async def get_tools(
                             "tool_id": tool_id,
                             "callable": callable,
                             "spec": spec,
+                            # Misc info
+                            "type": "external",
                         }
 
                         # Handle function name collisions
@@ -182,6 +203,10 @@ async def get_tools(
                             function_name = f"{server_id}_{function_name}"
 
                         tools_dict[function_name] = tool_dict
+
+                else:
+                    continue
+
             else:
                 continue
         else:
@@ -563,25 +588,20 @@ async def get_tool_server_data(token: str, url: str) -> Dict[str, Any]:
             error = str(err)
         raise Exception(error)
 
-    data = {
+    log.debug(f"Fetched data: {res}")
-        "openapi": res,
+    return res
-        "info": res.get("info", {}),
-        "specs": convert_openapi_to_tool_payload(res),
-    }
-
-    log.info(f"Fetched data: {data}")
-    return data
 
 
 async def get_tool_servers_data(servers: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
     # Prepare list of enabled servers along with their original index
+
+    tasks = []
     server_entries = []
     for idx, server in enumerate(servers):
-        if server.get("config", {}).get("enable"):
+        if (
-            # Path (to OpenAPI spec URL) can be either a full URL or a path to append to the base URL
+            server.get("config", {}).get("enable")
-            openapi_path = server.get("path", "openapi.json")
+            and server.get("type", "openapi") == "openapi"
-            full_url = get_tool_server_url(server.get("url"), openapi_path)
+        ):
-
             info = server.get("info", {})
 
             auth_type = server.get("auth_type", "bearer")
@@ -597,12 +617,34 @@ async def get_tool_servers_data(servers: List[Dict[str, Any]]) -> List[Dict[str,
             if not id:
                 id = str(idx)
 
-            server_entries.append((id, idx, server, full_url, info, token))
+            server_url = server.get("url")
+            spec_type = server.get("spec_type", "url")
 
             # Create async tasks to fetch data
-    tasks = [
+            task = None
-        get_tool_server_data(token, url) for (_, _, _, url, _, token) in server_entries
+            if spec_type == "url":
-    ]
+                # Path (to OpenAPI spec URL) can be either a full URL or a path to append to the base URL
+                openapi_path = server.get("path", "openapi.json")
+                spec_url = get_tool_server_url(server_url, openapi_path)
+                # Fetch from URL
+                task = get_tool_server_data(token, spec_url)
+            elif spec_type == "json" and server.get("spec", ""):
+                # Use provided JSON spec
+                spec_json = None
+                try:
+                    spec_json = json.loads(server.get("spec", ""))
+                except Exception as e:
+                    log.error(f"Error parsing JSON spec for tool server {id}: {e}")
+
+                if spec_json:
+                    task = asyncio.sleep(
+                        0,
+                        result=spec_json,
+                    )
+
+            if task:
+                tasks.append(task)
+                server_entries.append((id, idx, server, server_url, info, token))
 
     # Execute tasks concurrently
     responses = await asyncio.gather(*tasks, return_exceptions=True)
@@ -614,8 +656,13 @@ async def get_tool_servers_data(servers: List[Dict[str, Any]]) -> List[Dict[str,
             log.error(f"Failed to connect to {url} OpenAPI tool server")
             continue
 
-        openapi_data = response.get("openapi", {})
+        response = {
+            "openapi": response,
+            "info": response.get("info", {}),
+            "specs": convert_openapi_to_tool_payload(response),
+        }
 
+        openapi_data = response.get("openapi", {})
         if info and isinstance(openapi_data, dict):
             openapi_data["info"] = openapi_data.get("info", {})
 
@@ -646,7 +693,7 @@ async def execute_tool_server(
     name: str,
     params: Dict[str, Any],
     server_data: Dict[str, Any],
-) -> Any:
+) -> Tuple[Dict[str, Any], Optional[Dict[str, Any]]]:
     error = None
     try:
         openapi = server_data.get("openapi", {})
@@ -718,6 +765,7 @@ async def execute_tool_server(
                     headers=headers,
                     cookies=cookies,
                     ssl=AIOHTTP_CLIENT_SESSION_TOOL_SERVER_SSL,
+                    allow_redirects=False,
                 ) as response:
                     if response.status >= 400:
                         text = await response.text()
@@ -728,13 +776,15 @@ async def execute_tool_server(
                     except Exception:
                         response_data = await response.text()
 
-                    return response_data
+                    response_headers = response.headers
+                    return (response_data, response_headers)
             else:
                 async with request_method(
                     final_url,
                     headers=headers,
                     cookies=cookies,
                     ssl=AIOHTTP_CLIENT_SESSION_TOOL_SERVER_SSL,
+                    allow_redirects=False,
                 ) as response:
                     if response.status >= 400:
                         text = await response.text()
@@ -745,12 +795,13 @@ async def execute_tool_server(
                     except Exception:
                         response_data = await response.text()
 
-                    return response_data
+                    response_headers = response.headers
+                    return (response_data, response_headers)
 
     except Exception as err:
         error = str(err)
         log.exception(f"API Request Error: {error}")
-        return {"error": error}
+        return ({"error": error}, None)
 
 
 def get_tool_server_url(url: Optional[str], path: str) -> str:

backend/requirements.txt

@@ -1,59 +1,66 @@
-fastapi==0.115.7
+fastapi==0.118.0
-uvicorn[standard]==0.35.0
+uvicorn[standard]==0.37.0
-pydantic==2.11.7
+pydantic==2.11.9
 python-multipart==0.0.20
+itsdangerous==2.2.0
 
 python-socketio==5.13.0
 python-jose==3.4.0
-passlib[bcrypt]==1.7.4
 cryptography
+bcrypt==5.0.0
+argon2-cffi==25.1.0
+PyJWT[crypto]==2.10.1
+authlib==1.6.3
 
-requests==2.32.4
+requests==2.32.5
 aiohttp==3.12.15
 async-timeout
 aiocache
 aiofiles
 starlette-compress==1.6.0
 httpx[socks,http2,zstd,cli,brotli]==0.28.1
+starsessions[redis]==2.2.1
 
 sqlalchemy==2.0.38
 alembic==1.14.0
 peewee==3.18.1
 peewee-migrate==1.12.2
-psycopg2-binary==2.9.10
-pgvector==0.4.1
-PyMySQL==1.1.1
-bcrypt==4.3.0
-
-pymongo
-redis
-boto3==1.40.5
-
-argon2-cffi==25.1.0
-APScheduler==3.10.4
 
 pycrdt==0.12.25
+redis
 
+pymongo
+
+psycopg2-binary==2.9.10
+pgvector==0.4.1
+
+PyMySQL==1.1.1
+boto3==1.40.5
+
+APScheduler==3.10.4
 RestrictedPython==8.0
 
 loguru==0.7.3
 asgiref==3.8.1
 
 # AI libraries
+tiktoken
+mcp==1.14.1
+
 openai
 anthropic
-google-genai==1.32.0
+google-genai==1.38.0
 google-generativeai==0.8.5
-tiktoken
 
-langchain==0.3.26
+langchain==0.3.27
-langchain-community==0.3.27
+langchain-community==0.3.29
 
 fake-useragent==2.2.0
-chromadb==1.0.20
+chromadb==1.1.0
+opensearch-py==2.8.0
+
 pymilvus==2.5.0
 qdrant-client==1.14.3
-opensearch-py==2.8.0
 playwright==1.49.1 # Caution: version must match docker-compose.playwright.yaml
 elasticsearch==9.1.0
 pinecone==6.0.2
@@ -61,12 +68,12 @@ oracledb==3.2.0
 
 av==14.0.1 # Caution: Set due to FATAL FIPS SELFTEST FAILURE, see discussion https://github.com/open-webui/open-webui/discussions/15720
 transformers
-sentence-transformers==4.1.0
+sentence-transformers==5.1.1
 accelerate
-colbert-ai==0.2.21
 pyarrow==20.0.0 # fix: pin pyarrow version to 20 for rpi compatibility #15897
 einops==0.8.1 
 
+colbert-ai==0.2.21
 
 ftfy==6.2.3
 pypdf==6.0.0
@@ -76,7 +83,7 @@ docx2txt==0.8
 python-pptx==1.0.2
 unstructured==0.16.17
 nltk==3.9.1
-Markdown==3.8.2
+Markdown==3.9
 pypandoc==1.15
 pandas==2.2.3
 openpyxl==3.1.5
@@ -94,13 +101,10 @@ rapidocr-onnxruntime==1.4.4
 rank-bm25==0.2.2
 
 onnxruntime==1.20.1
-
 faster-whisper==1.1.1
 
-PyJWT[crypto]==2.10.1
-authlib==1.6.3
 
-black==25.1.0
+black==25.9.0
 youtube-transcript-api==1.2.2
 pytube==15.0.0
 
@@ -120,7 +124,7 @@ pytest-docker~=3.1.1
 googleapis-common-protos==1.70.0
 google-cloud-storage==2.19.0
 
-azure-identity==1.23.0
+azure-identity==1.25.0
 azure-storage-blob==12.24.1
 
 
@@ -134,14 +138,14 @@ firecrawl-py==1.12.0
 tencentcloud-sdk-python==3.0.1336
 
 ## Trace
-opentelemetry-api==1.36.0
+opentelemetry-api==1.37.0
-opentelemetry-sdk==1.36.0
+opentelemetry-sdk==1.37.0
-opentelemetry-exporter-otlp==1.36.0
+opentelemetry-exporter-otlp==1.37.0
-opentelemetry-instrumentation==0.57b0
+opentelemetry-instrumentation==0.58b0
-opentelemetry-instrumentation-fastapi==0.57b0
+opentelemetry-instrumentation-fastapi==0.58b0
-opentelemetry-instrumentation-sqlalchemy==0.57b0
+opentelemetry-instrumentation-sqlalchemy==0.58b0
-opentelemetry-instrumentation-redis==0.57b0
+opentelemetry-instrumentation-redis==0.58b0
-opentelemetry-instrumentation-requests==0.57b0
+opentelemetry-instrumentation-requests==0.58b0
-opentelemetry-instrumentation-logging==0.57b0
+opentelemetry-instrumentation-logging==0.58b0
-opentelemetry-instrumentation-httpx==0.57b0
+opentelemetry-instrumentation-httpx==0.58b0
-opentelemetry-instrumentation-aiohttp-client==0.57b0
+opentelemetry-instrumentation-aiohttp-client==0.58b0

backend/start.sh

@@ -70,5 +70,18 @@ if [ -n "$SPACE_ID" ]; then
 fi
 
 PYTHON_CMD=$(command -v python3 || command -v python)
+UVICORN_WORKERS="${UVICORN_WORKERS:-1}"
 
-WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec "$PYTHON_CMD" -m uvicorn open_webui.main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*' --workers "${UVICORN_WORKERS:-1}"
+# If script is called with arguments, use them; otherwise use default workers
+if [ "$#" -gt 0 ]; then
+    ARGS=("$@")
+else
+    ARGS=(--workers "$UVICORN_WORKERS")
+fi
+
+# Run uvicorn
+WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec "$PYTHON_CMD" -m uvicorn open_webui.main:app \
+    --host "$HOST" \
+    --port "$PORT" \
+    --forwarded-allow-ips '*' \
+    "${ARGS[@]}"

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.6.29",
+	"version": "0.6.32",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.6.29",
+			"version": "0.6.32",
 			"dependencies": {
 				"@azure/msal-browser": "^4.5.0",
 				"@codemirror/lang-javascript": "^6.2.2",
@@ -23,7 +23,7 @@
 				"@tiptap/core": "^3.0.7",
 				"@tiptap/extension-bubble-menu": "^2.26.1",
 				"@tiptap/extension-code-block-lowlight": "^3.0.7",
-				"@tiptap/extension-drag-handle": "^3.0.7",
+				"@tiptap/extension-drag-handle": "^3.4.5",
 				"@tiptap/extension-file-handler": "^3.0.7",
 				"@tiptap/extension-floating-menu": "^2.26.1",
 				"@tiptap/extension-highlight": "^3.3.0",
@@ -39,6 +39,7 @@
 				"@tiptap/starter-kit": "^3.0.7",
 				"@tiptap/suggestion": "^3.4.2",
 				"@xyflow/svelte": "^0.1.19",
+				"alpinejs": "^3.15.0",
 				"async": "^3.2.5",
 				"bits-ui": "^0.21.15",
 				"chart.js": "^4.5.0",
@@ -3383,9 +3384,9 @@
 			}
 		},
 		"node_modules/@tiptap/extension-collaboration": {
-			"version": "3.0.7",
+			"version": "3.4.5",
-			"resolved": "https://registry.npmjs.org/@tiptap/extension-collaboration/-/extension-collaboration-3.0.7.tgz",
+			"resolved": "https://registry.npmjs.org/@tiptap/extension-collaboration/-/extension-collaboration-3.4.5.tgz",
-			"integrity": "sha512-so59vQCAS1vy6k86byk96fYvAPM5w8u8/Yp3jKF1LPi9LH4wzS4hGnOP/dEbedxPU48an9WB1lSOczSKPECJaQ==",
+			"integrity": "sha512-JyPXTYkYi2XzUWsmObv2cogMrs7huAvfq6l7d5hAwsU2FnA1vMycaa48N4uekogySP6VBkiQNDf9B4T09AwwqA==",
 			"license": "MIT",
 			"peer": true,
 			"funding": {
@@ -3393,8 +3394,8 @@
 				"url": "https://github.com/sponsors/ueberdosis"
 			},
 			"peerDependencies": {
-				"@tiptap/core": "^3.0.7",
+				"@tiptap/core": "^3.4.5",
-				"@tiptap/pm": "^3.0.7",
+				"@tiptap/pm": "^3.4.5",
 				"@tiptap/y-tiptap": "^3.0.0-beta.3",
 				"yjs": "^13"
 			}
@@ -3413,9 +3414,9 @@
 			}
 		},
 		"node_modules/@tiptap/extension-drag-handle": {
-			"version": "3.0.7",
+			"version": "3.4.5",
-			"resolved": "https://registry.npmjs.org/@tiptap/extension-drag-handle/-/extension-drag-handle-3.0.7.tgz",
+			"resolved": "https://registry.npmjs.org/@tiptap/extension-drag-handle/-/extension-drag-handle-3.4.5.tgz",
-			"integrity": "sha512-rm8+0kPz5C5JTp4f1QY61Qd5d7zlJAxLeJtOvgC9RCnrNG1F7LCsmOkvy5fsU6Qk2YCCYOiSSMC4S4HKPrUJhw==",
+			"integrity": "sha512-177hQ9lMQYJz+SuCg8eA47MB2tn3G3MGBJ5+3PNl5Bs4WQukR9uHpxdR+bH00/LedwxrlNlglMa5Hirrx9odMQ==",
 			"license": "MIT",
 			"dependencies": {
 				"@floating-ui/dom": "^1.6.13"
@@ -3425,10 +3426,10 @@
 				"url": "https://github.com/sponsors/ueberdosis"
 			},
 			"peerDependencies": {
-				"@tiptap/core": "^3.0.7",
+				"@tiptap/core": "^3.4.5",
-				"@tiptap/extension-collaboration": "^3.0.7",
+				"@tiptap/extension-collaboration": "^3.4.5",
-				"@tiptap/extension-node-range": "^3.0.7",
+				"@tiptap/extension-node-range": "^3.4.5",
-				"@tiptap/pm": "^3.0.7",
+				"@tiptap/pm": "^3.4.5",
 				"@tiptap/y-tiptap": "^3.0.0-beta.3"
 			}
 		},
@@ -3642,9 +3643,9 @@
 			}
 		},
 		"node_modules/@tiptap/extension-node-range": {
-			"version": "3.0.7",
+			"version": "3.4.5",
-			"resolved": "https://registry.npmjs.org/@tiptap/extension-node-range/-/extension-node-range-3.0.7.tgz",
+			"resolved": "https://registry.npmjs.org/@tiptap/extension-node-range/-/extension-node-range-3.4.5.tgz",
-			"integrity": "sha512-cHViNqtOUD9CLJxEj28rcj8tb8RYQZ7kwmtSvIye84Y3MJIzigRm4IUBNNOYnZfq5YAZIR97WKcJeFz3EU1VPg==",
+			"integrity": "sha512-mHCjdJZX8DZCpnw9wBqioanANy6tRoy20/OcJxMW1T7naeRCuCU4sFjwO37yb/tmYk1BQA2/L1/H2r0fVoZwtA==",
 			"license": "MIT",
 			"peer": true,
 			"funding": {
@@ -3652,8 +3653,8 @@
 				"url": "https://github.com/sponsors/ueberdosis"
 			},
 			"peerDependencies": {
-				"@tiptap/core": "^3.0.7",
+				"@tiptap/core": "^3.4.5",
-				"@tiptap/pm": "^3.0.7"
+				"@tiptap/pm": "^3.4.5"
 			}
 		},
 		"node_modules/@tiptap/extension-ordered-list": {
@@ -4569,6 +4570,21 @@
 				"@types/estree": "^1.0.0"
 			}
 		},
+		"node_modules/@vue/reactivity": {
+			"version": "3.1.5",
+			"resolved": "https://registry.npmjs.org/@vue/reactivity/-/reactivity-3.1.5.tgz",
+			"integrity": "sha512-1tdfLmNjWG6t/CsPldh+foumYFo3cpyCHgBYQ34ylaMsJ+SNHQ1kApMIa8jN+i593zQuaw3AdWH0nJTARzCFhg==",
+			"license": "MIT",
+			"dependencies": {
+				"@vue/shared": "3.1.5"
+			}
+		},
+		"node_modules/@vue/shared": {
+			"version": "3.1.5",
+			"resolved": "https://registry.npmjs.org/@vue/shared/-/shared-3.1.5.tgz",
+			"integrity": "sha512-oJ4F3TnvpXaQwZJNF3ZK+kLPHKarDmJjJ6jyzVNDKH9md1dptjC7lWR//jrGuLdek/U6iltWxqAnYOu8gCiOvA==",
+			"license": "MIT"
+		},
 		"node_modules/@webreflection/fetch": {
 			"version": "0.1.5",
 			"resolved": "https://registry.npmjs.org/@webreflection/fetch/-/fetch-0.1.5.tgz",
@@ -4672,6 +4688,15 @@
 				"url": "https://github.com/sponsors/epoberezkin"
 			}
 		},
+		"node_modules/alpinejs": {
+			"version": "3.15.0",
+			"resolved": "https://registry.npmjs.org/alpinejs/-/alpinejs-3.15.0.tgz",
+			"integrity": "sha512-lpokA5okCF1BKh10LG8YjqhfpxyHBk4gE7boIgVHltJzYoM7O9nK3M7VlntLEJGsVmu7U/RzUWajmHREGT38Eg==",
+			"license": "MIT",
+			"dependencies": {
+				"@vue/reactivity": "~3.1.1"
+			}
+		},
 		"node_modules/amator": {
 			"version": "1.1.0",
 			"resolved": "https://registry.npmjs.org/amator/-/amator-1.1.0.tgz",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.6.29",
+	"version": "0.6.32",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -67,7 +67,7 @@
 		"@tiptap/core": "^3.0.7",
 		"@tiptap/extension-bubble-menu": "^2.26.1",
 		"@tiptap/extension-code-block-lowlight": "^3.0.7",
-		"@tiptap/extension-drag-handle": "^3.0.7",
+		"@tiptap/extension-drag-handle": "^3.4.5",
 		"@tiptap/extension-file-handler": "^3.0.7",
 		"@tiptap/extension-floating-menu": "^2.26.1",
 		"@tiptap/extension-highlight": "^3.3.0",
@@ -83,6 +83,7 @@
 		"@tiptap/starter-kit": "^3.0.7",
 		"@tiptap/suggestion": "^3.4.2",
 		"@xyflow/svelte": "^0.1.19",
+		"alpinejs": "^3.15.0",
 		"async": "^3.2.5",
 		"bits-ui": "^0.21.15",
 		"chart.js": "^4.5.0",

pyproject.toml

@@ -10,23 +10,24 @@ dependencies = [
     "uvicorn[standard]==0.35.0",
     "pydantic==2.11.7",
     "python-multipart==0.0.20",
+    "itsdangerous==2.2.0",
 
     "python-socketio==5.13.0",
     "python-jose==3.4.0",
-    "passlib[bcrypt]==1.7.4",
     "cryptography",
-    "bcrypt==4.3.0",
+    "bcrypt==5.0.0",
-    "argon2-cffi==23.1.0",
+    "argon2-cffi==25.1.0",
     "PyJWT[crypto]==2.10.1",
     "authlib==1.6.3",
 
-    "requests==2.32.4",
+    "requests==2.32.5",
     "aiohttp==3.12.15",
     "async-timeout",
     "aiocache",
     "aiofiles",
     "starlette-compress==1.6.0",
     "httpx[socks,http2,zstd,cli,brotli]==0.28.1",
+    "starsessions[redis]==2.2.1",
 
     "sqlalchemy==2.0.38",
     "alembic==1.14.0",
@@ -46,20 +47,22 @@ dependencies = [
     "asgiref==3.8.1",
 
     "tiktoken",
+    "mcp==1.14.1",
+
     "openai",
     "anthropic",
-    "google-genai==1.32.0",
+    "google-genai==1.38.0",
     "google-generativeai==0.8.5",
 
-    "langchain==0.3.26",
+    "langchain==0.3.27",
-    "langchain-community==0.3.27",
+    "langchain-community==0.3.29",
 
     "fake-useragent==2.2.0",
     "chromadb==1.0.20",
     "opensearch-py==2.8.0",
     
     "transformers",
-    "sentence-transformers==4.1.0",
+    "sentence-transformers==5.1.1",
     "accelerate",
     "pyarrow==20.0.0",
     "einops==0.8.1",
@@ -108,7 +111,7 @@ dependencies = [
     "googleapis-common-protos==1.70.0",
     "google-cloud-storage==2.19.0",
 
-    "azure-identity==1.20.0",
+    "azure-identity==1.25.0",
     "azure-storage-blob==12.24.1",
 
     "ldap3==2.9.1",

src/app.css

@@ -70,23 +70,23 @@ textarea::placeholder {
 }
 
 .input-prose {
-	@apply prose dark:prose-invert prose-headings:font-semibold prose-hr:my-4 prose-hr:border-gray-100 prose-hr:dark:border-gray-800 prose-p:my-1 prose-img:my-1 prose-headings:my-2 prose-pre:my-0 prose-table:my-1 prose-blockquote:my-0 prose-ul:my-1 prose-ol:my-1 prose-li:my-0.5 whitespace-pre-line;
+	@apply prose dark:prose-invert prose-headings:font-semibold prose-hr:my-4 prose-hr:border-gray-50 prose-hr:dark:border-gray-850 prose-p:my-1 prose-img:my-1 prose-headings:my-2 prose-pre:my-0 prose-table:my-1 prose-blockquote:my-0 prose-ul:my-1 prose-ol:my-1 prose-li:my-0.5 whitespace-pre-line;
 }
 
 .input-prose-sm {
-	@apply prose dark:prose-invert prose-headings:font-medium prose-h1:text-2xl prose-h2:text-xl prose-h3:text-lg prose-hr:my-4 prose-hr:border-gray-100 prose-hr:dark:border-gray-800 prose-p:my-1 prose-img:my-1 prose-headings:my-2 prose-pre:my-0 prose-table:my-1 prose-blockquote:my-0 prose-ul:my-1 prose-ol:my-1 prose-li:my-1 whitespace-pre-line text-sm;
+	@apply prose dark:prose-invert prose-headings:font-medium prose-h1:text-2xl prose-h2:text-xl prose-h3:text-lg prose-hr:my-4 prose-hr:border-gray-50 prose-hr:dark:border-gray-850 prose-p:my-1 prose-img:my-1 prose-headings:my-2 prose-pre:my-0 prose-table:my-1 prose-blockquote:my-0 prose-ul:my-1 prose-ol:my-1 prose-li:my-1 whitespace-pre-line text-sm;
 }
 
 .markdown-prose {
-	@apply prose dark:prose-invert prose-blockquote:border-s-gray-100 prose-blockquote:dark:border-gray-800 prose-blockquote:border-s-2 prose-blockquote:not-italic prose-blockquote:font-normal  prose-headings:font-semibold prose-hr:my-4 prose-hr:border-gray-100 prose-hr:dark:border-gray-800 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
+	@apply prose dark:prose-invert prose-blockquote:border-s-gray-100 prose-blockquote:dark:border-gray-800 prose-blockquote:border-s-2 prose-blockquote:not-italic prose-blockquote:font-normal  prose-headings:font-semibold prose-hr:my-4 prose-hr:border-gray-50 prose-hr:dark:border-gray-850 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
 }
 
 .markdown-prose-sm {
-	@apply text-sm prose dark:prose-invert prose-blockquote:border-s-gray-100 prose-blockquote:dark:border-gray-800 prose-blockquote:border-s-2 prose-blockquote:not-italic prose-blockquote:font-normal  prose-headings:font-semibold prose-hr:my-2  prose-hr:border-gray-100 prose-hr:dark:border-gray-800 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
+	@apply text-sm prose dark:prose-invert prose-blockquote:border-s-gray-100 prose-blockquote:dark:border-gray-800 prose-blockquote:border-s-2 prose-blockquote:not-italic prose-blockquote:font-normal  prose-headings:font-semibold prose-hr:my-2  prose-hr:border-gray-50 prose-hr:dark:border-gray-850 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
 }
 
 .markdown-prose-xs {
-	@apply text-xs prose dark:prose-invert prose-blockquote:border-s-gray-100 prose-blockquote:dark:border-gray-800 prose-blockquote:border-s-2 prose-blockquote:not-italic prose-blockquote:font-normal  prose-headings:font-semibold prose-hr:my-0.5  prose-hr:border-gray-100 prose-hr:dark:border-gray-800 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
+	@apply text-xs prose dark:prose-invert prose-blockquote:border-s-gray-100 prose-blockquote:dark:border-gray-800 prose-blockquote:border-s-2 prose-blockquote:not-italic prose-blockquote:font-normal  prose-headings:font-semibold prose-hr:my-0.5  prose-hr:border-gray-50 prose-hr:dark:border-gray-850 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
 }
 
 .markdown a {
@@ -116,7 +116,7 @@ li p {
 
 ::-webkit-scrollbar-thumb {
 	--tw-border-opacity: 1;
-	background-color: rgba(215, 215, 215, 0.8);
+	background-color: rgba(215, 215, 215, 0.6);
 	border-color: rgba(255, 255, 255, var(--tw-border-opacity));
 	border-radius: 9999px;
 	border-width: 1px;
@@ -124,12 +124,12 @@ li p {
 
 /* Dark theme scrollbar styles */
 .dark ::-webkit-scrollbar-thumb {
-	background-color: rgba(67, 67, 67, 0.8); /* Darker color for dark theme */
+	background-color: rgba(67, 67, 67, 0.6); /* Darker color for dark theme */
 	border-color: rgba(0, 0, 0, var(--tw-border-opacity));
 }
 
 ::-webkit-scrollbar {
-	height: 0.6rem;
+	height: 0.4rem;
 	width: 0.4rem;
 }
 
@@ -409,17 +409,33 @@ input[type='number'] {
 	}
 }
 
-.tiptap .mention {
+.mention {
 	border-radius: 0.4rem;
 	box-decoration-break: clone;
 	padding: 0.1rem 0.3rem;
-	@apply text-blue-900 dark:text-blue-100 bg-blue-300/20 dark:bg-blue-500/20;
+	@apply text-sky-800 dark:text-sky-200 bg-sky-300/15 dark:bg-sky-500/15;
 }
 
-.tiptap .mention::after {
+.mention::after {
 	content: '\200B';
 }
 
+.tiptap .suggestion {
+	border-radius: 0.4rem;
+	box-decoration-break: clone;
+	padding: 0.1rem 0.3rem;
+	@apply text-sky-800 dark:text-sky-200 bg-sky-300/15 dark:bg-sky-500/15;
+}
+
+.tiptap .suggestion::after {
+	content: '\200B';
+}
+
+.tiptap .suggestion.is-empty::after {
+	content: '\00A0';
+	border-bottom: 1px dotted rgba(31, 41, 55, 0.12);
+}
+
 .input-prose .tiptap ul[data-type='taskList'] {
 	list-style: none;
 	margin-left: 0;
@@ -645,3 +661,112 @@ body {
 	background: #171717;
 	color: #eee;
 }
+
+/* Position the handle relative to each LI */
+.pm-li--with-handle {
+	position: relative;
+	margin-left: 12px; /* make space for the handle */
+}
+
+.tiptap ul[data-type='taskList'] .pm-list-drag-handle {
+	margin-left: 0px;
+}
+
+/* The drag handle itself */
+.pm-list-drag-handle {
+	position: absolute;
+	left: -36px; /* pull into the left gutter */
+	top: 1px;
+	width: 18px;
+	height: 18px;
+	display: inline-flex;
+	align-items: center;
+	justify-content: center;
+	font-size: 12px;
+	line-height: 1;
+	border-radius: 4px;
+	cursor: grab;
+	user-select: none;
+	opacity: 0.35;
+	transition:
+		opacity 120ms ease,
+		background 120ms ease;
+}
+
+.tiptap ul[data-type='taskList'] .pm-list-drag-handle {
+	left: -16px; /* pull into the left gutter more to avoid the checkbox */
+}
+
+.pm-list-drag-handle:active {
+	cursor: grabbing;
+}
+.pm-li--with-handle:hover > .pm-list-drag-handle {
+	opacity: 1;
+}
+.pm-list-drag-handle:hover {
+	background: rgba(0, 0, 0, 0.06);
+}
+
+:root {
+	--pm-accent: color-mix(in oklab, Highlight 70%, transparent);
+	--pm-fill-target: color-mix(in oklab, Highlight 26%, transparent);
+	--pm-fill-ancestor: color-mix(in oklab, Highlight 16%, transparent);
+}
+
+.pm-li-drop-before,
+.pm-li-drop-after,
+.pm-li-drop-into,
+.pm-li-drop-outdent {
+	position: relative;
+}
+
+/* BEFORE/AFTER lines */
+.pm-li-drop-before::before,
+.pm-li-drop-after::after {
+	content: '';
+	position: absolute;
+	left: 0;
+	right: 0;
+	height: 3px;
+	background: var(--pm-accent);
+	pointer-events: none;
+}
+.pm-li-drop-before::before {
+	top: -2px;
+}
+.pm-li-drop-after::after {
+	bottom: -2px;
+}
+
+.pm-li-drop-before,
+.pm-li-drop-after,
+.pm-li-drop-into,
+.pm-li-drop-outdent {
+	background: var(--pm-fill-target);
+	border-radius: 6px;
+}
+
+.pm-li-drop-outdent::before {
+	content: '';
+	position: absolute;
+	inset-block: 0;
+	inset-inline-start: 0;
+	width: 3px;
+	background: color-mix(in oklab, Highlight 35%, transparent);
+}
+
+.pm-li--with-handle:has(.pm-li-drop-before),
+.pm-li--with-handle:has(.pm-li-drop-after),
+.pm-li--with-handle:has(.pm-li-drop-into),
+.pm-li--with-handle:has(.pm-li-drop-outdent) {
+	background: var(--pm-fill-ancestor);
+	border-radius: 6px;
+}
+
+.pm-li-drop-before,
+.pm-li-drop-after,
+.pm-li-drop-into,
+.pm-li-drop-outdent {
+	position: relative;
+	z-index: 0;
+}

src/app.html

@@ -23,8 +23,6 @@
 			href="/static/apple-touch-icon.png"
 			crossorigin="use-credentials"
 		/>
-		<meta name="apple-mobile-web-app-title" content="Open WebUI" />
-
 		<link
 			rel="manifest"
 			href="/manifest.json"
@@ -37,14 +35,7 @@
 		/>
 		<meta name="theme-color" content="#171717" />
 		<meta name="robots" content="noindex,nofollow" />
-		<meta name="description" content="Open WebUI" />
+
-		<link
-			rel="search"
-			type="application/opensearchdescription+xml"
-			title="Open WebUI"
-			href="/opensearch.xml"
-			crossorigin="use-credentials"
-		/>
 		<script src="/static/loader.js" defer crossorigin="use-credentials"></script>
 		<link rel="stylesheet" href="/static/custom.css" crossorigin="use-credentials" />
 

src/lib/apis/channels/index.ts

@@ -248,6 +248,7 @@ export const getChannelThreadMessages = async (
 };
 
 type MessageForm = {
+	reply_to_id?: string;
 	parent_id?: string;
 	content: string;
 	data?: object;

src/lib/apis/chats/index.ts

@@ -33,6 +33,38 @@ export const createNewChat = async (token: string, chat: object, folderId: strin
 	return res;
 };
 
+export const unarchiveAllChats = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/unarchive/all`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err.detail;
+
+			console.error(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const importChat = async (
 	token: string,
 	chat: object,
@@ -77,7 +109,11 @@ export const importChat = async (
 	return res;
 };
 
-export const getChatList = async (token: string = '', page: number | null = null) => {
+export const getChatList = async (
+	token: string = '',
+	page: number | null = null,
+	include_folders: boolean = false
+) => {
 	let error = null;
 	const searchParams = new URLSearchParams();
 
@@ -85,6 +121,10 @@ export const getChatList = async (token: string = '', page: number | null = null
 		searchParams.append('page', `${page}`);
 	}
 
+	if (include_folders) {
+		searchParams.append('include_folders', 'true');
+	}
+
 	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/?${searchParams.toString()}`, {
 		method: 'GET',
 		headers: {
@@ -319,6 +359,45 @@ export const getChatsByFolderId = async (token: string, folderId: string) => {
 	return res;
 };
 
+export const getChatListByFolderId = async (token: string, folderId: string, page: number = 1) => {
+	let error = null;
+
+	const searchParams = new URLSearchParams();
+	if (page !== null) {
+		searchParams.append('page', `${page}`);
+	}
+
+	const res = await fetch(
+		`${WEBUI_API_BASE_URL}/chats/folder/${folderId}/list?${searchParams.toString()}`,
+		{
+			method: 'GET',
+			headers: {
+				Accept: 'application/json',
+				'Content-Type': 'application/json',
+				...(token && { authorization: `Bearer ${token}` })
+			}
+		}
+	)
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+			console.error(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getAllArchivedChats = async (token: string) => {
 	let error = null;
 

src/lib/apis/configs/index.ts

@@ -1,4 +1,4 @@
-import { WEBUI_API_BASE_URL } from '$lib/constants';
+import { WEBUI_API_BASE_URL, WEBUI_BASE_URL } from '$lib/constants';
 import type { Banner } from '$lib/types';
 
 export const importConfig = async (token: string, config) => {
@@ -202,6 +202,52 @@ export const verifyToolServerConnection = async (token: string, connection: obje
 	return res;
 };
 
+type RegisterOAuthClientForm = {
+	url: string;
+	client_id: string;
+	client_name?: string;
+};
+
+export const registerOAuthClient = async (
+	token: string,
+	formData: RegisterOAuthClientForm,
+	type: null | string = null
+) => {
+	let error = null;
+
+	const searchParams = type ? `?type=${type}` : '';
+	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/oauth/clients/register${searchParams}`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			...formData
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.error(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getOAuthClientAuthorizationUrl = (clientId: string, type: null | string = null) => {
+	const oauthClientId = type ? `${type}:${clientId}` : clientId;
+	return `${WEBUI_BASE_URL}/oauth/clients/${oauthClientId}/authorize`;
+};
+
 export const getCodeExecutionConfig = async (token: string) => {
 	let error = null;
 

src/lib/apis/files/index.ts

@@ -23,7 +23,7 @@ export const uploadFile = async (token: string, file: File, metadata?: object |
 			return res.json();
 		})
 		.catch((err) => {
-			error = err.detail;
+			error = err.detail || err.message;
 			console.error(err);
 			return null;
 		});

src/lib/apis/index.ts

@@ -337,14 +337,8 @@ export const getToolServerData = async (token: string, url: string) => {
 		throw error;
 	}
 
-	const data = {
+	console.log(res);
-		openapi: res,
+	return res;
-		info: res.info,
-		specs: convertOpenApiToToolPayload(res)
-	};
-
-	console.log(data);
-	return data;
 };
 
 export const getToolServersData = async (servers: object[]) => {
@@ -356,6 +350,7 @@ export const getToolServersData = async (servers: object[]) => {
 					let error = null;
 
 					let toolServerToken = null;
+
 					const auth_type = server?.auth_type ?? 'bearer';
 					if (auth_type === 'bearer') {
 						toolServerToken = server?.key;
@@ -365,7 +360,11 @@ export const getToolServersData = async (servers: object[]) => {
 						toolServerToken = localStorage.token;
 					}
 
-					const data = await getToolServerData(
+					let res = null;
+					const specType = server?.spec_type ?? 'url';
+
+					if (specType === 'url') {
+						res = await getToolServerData(
 							toolServerToken,
 							(server?.path ?? '').includes('://')
 								? server?.path
@@ -374,9 +373,21 @@ export const getToolServersData = async (servers: object[]) => {
 							error = err;
 							return null;
 						});
+					} else if ((specType === 'json' && server?.spec) ?? null) {
+						try {
+							res = JSON.parse(server?.spec);
+						} catch (e) {
+							error = 'Failed to parse JSON spec';
+						}
+					}
+
+					if (res) {
+						const { openapi, info, specs } = {
+							openapi: res,
+							info: res.info,
+							specs: convertOpenApiToToolPayload(res)
+						};
 
-					if (data) {
-						const { openapi, info, specs } = data;
 						return {
 							url: server?.url,
 							openapi: openapi,
@@ -493,18 +504,25 @@ export const executeToolServer = async (
 			throw new Error(`HTTP error! Status: ${res.status}. Message: ${resText}`);
 		}
 
-		let responseData;
+		// make a clone of res and extract headers
-		try {
+		const responseHeaders = {};
-			responseData = await res.json();
+		res.headers.forEach((value, key) => {
-		} catch (err) {
+			responseHeaders[key] = value;
-			responseData = await res.text();
+		});
-		}
 
-		return responseData;
+		const text = await res.text();
+		let responseData;
+
+		try {
+			responseData = JSON.parse(text);
+		} catch {
+			responseData = text;
+		}
+		return [responseData, responseHeaders];
 	} catch (err: any) {
 		error = err.message;
 		console.error('API Request Error:', error);
-		return { error };
+		return [{ error }, null];
 	}
 };
 

src/lib/apis/models/index.ts

@@ -31,6 +31,34 @@ export const getModels = async (token: string = '') => {
 	return res;
 };
 
+export const importModels = async (token: string, models: object[]) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/import`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({ models: models })
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err;
+			console.error(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getBaseModels = async (token: string = '') => {
 	let error = null;
 

src/lib/apis/users/index.ts

@@ -194,6 +194,34 @@ export const getAllUsers = async (token: string) => {
 	return res;
 };
 
+export const searchUsers = async (token: string, query: string) => {
+	let error = null;
+	let res = null;
+
+	res = await fetch(`${WEBUI_API_BASE_URL}/users/search?query=${encodeURIComponent(query)}`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.error(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getUserSettings = async (token: string) => {
 	let error = null;
 	const res = await fetch(`${WEBUI_API_BASE_URL}/users/user/settings`, {

src/lib/components/AddConnectionModal.svelte

@@ -122,7 +122,7 @@
 				return;
 			}
 
-			if (!key) {
+			if (!key && !['azure_ad', 'microsoft_entra_id'].includes(auth_type)) {
 				loading = false;
 
 				toast.error($i18n.t('Key is required'));
@@ -331,6 +331,9 @@
 												<option value="session">{$i18n.t('Session')}</option>
 												{#if !direct}
 													<option value="system_oauth">{$i18n.t('OAuth')}</option>
+													{#if azure}
+														<option value="microsoft_entra_id">{$i18n.t('Entra ID')}</option>
+													{/if}
 												{/if}
 											{/if}
 										</select>
@@ -361,6 +364,12 @@
 											>
 												{$i18n.t('Forwards system user OAuth access token to authenticate')}
 											</div>
+										{:else if ['azure_ad', 'microsoft_entra_id'].includes(auth_type)}
+											<div
+												class={`text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+											>
+												{$i18n.t('Uses DefaultAzureCredential to authenticate')}
+											</div>
 										{/if}
 									</div>
 								</div>
@@ -443,7 +452,7 @@
 							</div>
 						{/if}
 
-						<div class="flex flex-col w-full">
+						<div class="flex flex-col w-full mt-2">
 							<div class="mb-1 flex justify-between">
 								<div
 									class={`mb-0.5 text-xs text-gray-500
@@ -499,8 +508,6 @@
 							{/if}
 						</div>
 
-						<hr class=" border-gray-100 dark:border-gray-700/10 my-1.5 w-full" />
-
 						<div class="flex items-center">
 							<label class="sr-only" for="add-model-id-input">{$i18n.t('Add a model ID')}</label>
 							<input
@@ -528,9 +535,7 @@
 						</div>
 					</div>
 
-					<hr class=" border-gray-50 dark:border-gray-850 my-2.5 w-full" />
+					<div class="flex gap-2 mt-2">
-
-					<div class="flex gap-2">
 						<div class="flex flex-col w-full">
 							<div
 								class={`mb-0.5 text-xs text-gray-500

src/lib/components/AddServerModal.svelte

@@ -1,440 +0,0 @@
-<script lang="ts">
-	import { toast } from 'svelte-sonner';
-	import { getContext, onMount } from 'svelte';
-	const i18n = getContext('i18n');
-
-	import { settings } from '$lib/stores';
-	import Modal from '$lib/components/common/Modal.svelte';
-	import Plus from '$lib/components/icons/Plus.svelte';
-	import Minus from '$lib/components/icons/Minus.svelte';
-	import PencilSolid from '$lib/components/icons/PencilSolid.svelte';
-	import SensitiveInput from '$lib/components/common/SensitiveInput.svelte';
-	import Tooltip from '$lib/components/common/Tooltip.svelte';
-	import Switch from '$lib/components/common/Switch.svelte';
-	import Tags from './common/Tags.svelte';
-	import { getToolServerData } from '$lib/apis';
-	import { verifyToolServerConnection } from '$lib/apis/configs';
-	import AccessControl from './workspace/common/AccessControl.svelte';
-	import Spinner from '$lib/components/common/Spinner.svelte';
-	import XMark from '$lib/components/icons/XMark.svelte';
-
-	export let onSubmit: Function = () => {};
-	export let onDelete: Function = () => {};
-
-	export let show = false;
-	export let edit = false;
-
-	export let direct = false;
-	export let connection = null;
-
-	let url = '';
-	let path = 'openapi.json';
-
-	let auth_type = 'bearer';
-	let key = '';
-
-	let accessControl = {};
-
-	let id = '';
-	let name = '';
-	let description = '';
-
-	let enable = true;
-
-	let loading = false;
-
-	const verifyHandler = async () => {
-		if (url === '') {
-			toast.error($i18n.t('Please enter a valid URL'));
-			return;
-		}
-
-		if (path === '') {
-			toast.error($i18n.t('Please enter a valid path'));
-			return;
-		}
-
-		if (direct) {
-			const res = await getToolServerData(
-				auth_type === 'bearer' ? key : localStorage.token,
-				path.includes('://') ? path : `${url}${path.startsWith('/') ? '' : '/'}${path}`
-			).catch((err) => {
-				toast.error($i18n.t('Connection failed'));
-			});
-
-			if (res) {
-				toast.success($i18n.t('Connection successful'));
-				console.debug('Connection successful', res);
-			}
-		} else {
-			const res = await verifyToolServerConnection(localStorage.token, {
-				url,
-				path,
-				auth_type,
-				key,
-				config: {
-					enable: enable,
-					access_control: accessControl
-				},
-				info: {
-					id,
-					name,
-					description
-				}
-			}).catch((err) => {
-				toast.error($i18n.t('Connection failed'));
-			});
-
-			if (res) {
-				toast.success($i18n.t('Connection successful'));
-				console.debug('Connection successful', res);
-			}
-		}
-	};
-
-	const submitHandler = async () => {
-		loading = true;
-
-		// remove trailing slash from url
-		url = url.replace(/\/$/, '');
-
-		const connection = {
-			url,
-			path,
-			auth_type,
-			key,
-			config: {
-				enable: enable,
-				access_control: accessControl
-			},
-			info: {
-				id: id,
-				name: name,
-				description: description
-			}
-		};
-
-		await onSubmit(connection);
-
-		loading = false;
-		show = false;
-
-		url = '';
-		path = 'openapi.json';
-		key = '';
-		auth_type = 'bearer';
-
-		id = '';
-		name = '';
-		description = '';
-
-		enable = true;
-		accessControl = null;
-	};
-
-	const init = () => {
-		if (connection) {
-			url = connection.url;
-			path = connection?.path ?? 'openapi.json';
-
-			auth_type = connection?.auth_type ?? 'bearer';
-			key = connection?.key ?? '';
-
-			id = connection.info?.id ?? '';
-			name = connection.info?.name ?? '';
-			description = connection.info?.description ?? '';
-
-			enable = connection.config?.enable ?? true;
-			accessControl = connection.config?.access_control ?? null;
-		}
-	};
-
-	$: if (show) {
-		init();
-	}
-
-	onMount(() => {
-		init();
-	});
-</script>
-
-<Modal size="sm" bind:show>
-	<div>
-		<div class=" flex justify-between dark:text-gray-100 px-5 pt-4 pb-2">
-			<h1 class=" text-lg font-medium self-center font-primary">
-				{#if edit}
-					{$i18n.t('Edit Connection')}
-				{:else}
-					{$i18n.t('Add Connection')}
-				{/if}
-			</h1>
-			<button
-				class="self-center"
-				aria-label={$i18n.t('Close Configure Connection Modal')}
-				on:click={() => {
-					show = false;
-				}}
-			>
-				<XMark className={'size-5'} />
-			</button>
-		</div>
-
-		<div class="flex flex-col md:flex-row w-full px-4 pb-4 md:space-x-4 dark:text-gray-200">
-			<div class=" flex flex-col w-full sm:flex-row sm:justify-center sm:space-x-6">
-				<form
-					class="flex flex-col w-full"
-					on:submit={(e) => {
-						e.preventDefault();
-						submitHandler();
-					}}
-				>
-					<div class="px-1">
-						<div class="flex gap-2">
-							<div class="flex flex-col w-full">
-								<div class="flex justify-between mb-0.5">
-									<label
-										for="api-base-url"
-										class={`text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-										>{$i18n.t('URL')}</label
-									>
-								</div>
-
-								<div class="flex flex-1 items-center">
-									<input
-										id="api-base-url"
-										class={`w-full flex-1 text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
-										type="text"
-										bind:value={url}
-										placeholder={$i18n.t('API Base URL')}
-										autocomplete="off"
-										required
-									/>
-
-									<Tooltip
-										content={$i18n.t('Verify Connection')}
-										className="shrink-0 flex items-center mr-1"
-									>
-										<button
-											class="self-center p-1 bg-transparent hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 rounded-lg transition"
-											on:click={() => {
-												verifyHandler();
-											}}
-											aria-label={$i18n.t('Verify Connection')}
-											type="button"
-										>
-											<svg
-												xmlns="http://www.w3.org/2000/svg"
-												viewBox="0 0 20 20"
-												fill="currentColor"
-												class="w-4 h-4"
-												aria-hidden="true"
-											>
-												<path
-													fill-rule="evenodd"
-													d="M15.312 11.424a5.5 5.5 0 01-9.201 2.466l-.312-.311h2.433a.75.75 0 000-1.5H3.989a.75.75 0 00-.75.75v4.242a.75.75 0 001.5 0v-2.43l.31.31a7 7 0 0011.712-3.138.75.75 0 00-1.449-.39zm1.23-3.723a.75.75 0 00.219-.53V2.929a.75.75 0 00-1.5 0V5.36l-.31-.31A7 7 0 003.239 8.188a.75.75 0 101.448.389A5.5 5.5 0 0113.89 6.11l.311.31h-2.432a.75.75 0 000 1.5h4.243a.75.75 0 00.53-.219z"
-													clip-rule="evenodd"
-												/>
-											</svg>
-										</button>
-									</Tooltip>
-
-									<Tooltip content={enable ? $i18n.t('Enabled') : $i18n.t('Disabled')}>
-										<Switch bind:state={enable} />
-									</Tooltip>
-								</div>
-
-								<div class="flex-1 flex items-center">
-									<label for="url-or-path" class="sr-only"
-										>{$i18n.t('openapi.json URL or Path')}</label
-									>
-									<input
-										class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
-										type="text"
-										id="url-or-path"
-										bind:value={path}
-										placeholder={$i18n.t('openapi.json URL or Path')}
-										autocomplete="off"
-										required
-									/>
-								</div>
-							</div>
-						</div>
-
-						<div
-							class={`text-xs mt-1 ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-						>
-							{$i18n.t(`WebUI will make requests to "{{url}}"`, {
-								url: path.includes('://') ? path : `${url}${path.startsWith('/') ? '' : '/'}${path}`
-							})}
-						</div>
-
-						<div class="flex gap-2 mt-2">
-							<div class="flex flex-col w-full">
-								<label
-									for="select-bearer-or-session"
-									class={`text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-									>{$i18n.t('Auth')}</label
-								>
-
-								<div class="flex gap-2">
-									<div class="flex-shrink-0 self-start">
-										<select
-											id="select-bearer-or-session"
-											class={`w-full text-sm bg-transparent pr-5 ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
-											bind:value={auth_type}
-										>
-											<option value="none">{$i18n.t('None')}</option>
-
-											<option value="bearer">{$i18n.t('Bearer')}</option>
-											<option value="session">{$i18n.t('Session')}</option>
-
-											{#if !direct}
-												<option value="system_oauth">{$i18n.t('OAuth')}</option>
-											{/if}
-										</select>
-									</div>
-
-									<div class="flex flex-1 items-center">
-										{#if auth_type === 'bearer'}
-											<SensitiveInput
-												bind:value={key}
-												placeholder={$i18n.t('API Key')}
-												required={false}
-											/>
-										{:else if auth_type === 'none'}
-											<div
-												class={`text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-											>
-												{$i18n.t('No authentication')}
-											</div>
-										{:else if auth_type === 'session'}
-											<div
-												class={`text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-											>
-												{$i18n.t('Forwards system user session credentials to authenticate')}
-											</div>
-										{:else if auth_type === 'system_oauth'}
-											<div
-												class={`text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-											>
-												{$i18n.t('Forwards system user OAuth access token to authenticate')}
-											</div>
-										{/if}
-									</div>
-								</div>
-							</div>
-						</div>
-
-						{#if !direct}
-							<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
-
-							<div class="flex gap-2">
-								<div class="flex flex-col w-full">
-									<label
-										for="enter-id"
-										class={`mb-0.5 text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-										>{$i18n.t('ID')}
-										<span class="text-xs text-gray-200 dark:text-gray-800 ml-0.5"
-											>{$i18n.t('Optional')}</span
-										>
-									</label>
-
-									<div class="flex-1">
-										<input
-											id="enter-id"
-											class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
-											type="text"
-											bind:value={id}
-											placeholder={$i18n.t('Enter ID')}
-											autocomplete="off"
-										/>
-									</div>
-								</div>
-							</div>
-
-							<div class="flex gap-2 mt-2">
-								<div class="flex flex-col w-full">
-									<label
-										for="enter-name"
-										class={`mb-0.5 text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
-										>{$i18n.t('Name')}
-									</label>
-
-									<div class="flex-1">
-										<input
-											id="enter-name"
-											class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
-											type="text"
-											bind:value={name}
-											placeholder={$i18n.t('Enter name')}
-											autocomplete="off"
-											required
-										/>
-									</div>
-								</div>
-							</div>
-
-							<div class="flex flex-col w-full mt-2">
-								<label
-									for="description"
-									class={`mb-1 text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100 placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700 text-gray-500'}`}
-									>{$i18n.t('Description')}</label
-								>
-
-								<div class="flex-1">
-									<input
-										id="description"
-										class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
-										type="text"
-										bind:value={description}
-										placeholder={$i18n.t('Enter description')}
-										autocomplete="off"
-									/>
-								</div>
-							</div>
-
-							<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
-
-							<div class="my-2 -mx-2">
-								<div class="px-3 py-2 bg-gray-50 dark:bg-gray-950 rounded-lg">
-									<AccessControl bind:accessControl />
-								</div>
-							</div>
-						{/if}
-					</div>
-
-					<div class="flex justify-end pt-3 text-sm font-medium gap-1.5">
-						{#if edit}
-							<button
-								class="px-3.5 py-1.5 text-sm font-medium dark:bg-black dark:hover:bg-gray-900 dark:text-white bg-white text-black hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center"
-								type="button"
-								on:click={() => {
-									onDelete();
-									show = false;
-								}}
-							>
-								{$i18n.t('Delete')}
-							</button>
-						{/if}
-
-						<button
-							class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center {loading
-								? ' cursor-not-allowed'
-								: ''}"
-							type="submit"
-							disabled={loading}
-						>
-							{$i18n.t('Save')}
-
-							{#if loading}
-								<div class="ml-2 self-center">
-									<Spinner />
-								</div>
-							{/if}
-						</button>
-					</div>
-				</form>
-			</div>
-		</div>
-	</div>
-</Modal>

src/lib/components/AddToolServerModal.svelte

@@ -0,0 +1,797 @@
+<script lang="ts">
+	import { v4 as uuidv4 } from 'uuid';
+
+	import fileSaver from 'file-saver';
+	const { saveAs } = fileSaver;
+
+	import { toast } from 'svelte-sonner';
+	import { getContext, onMount } from 'svelte';
+	const i18n = getContext('i18n');
+
+	import { settings } from '$lib/stores';
+	import Modal from '$lib/components/common/Modal.svelte';
+	import Plus from '$lib/components/icons/Plus.svelte';
+	import Minus from '$lib/components/icons/Minus.svelte';
+	import PencilSolid from '$lib/components/icons/PencilSolid.svelte';
+	import SensitiveInput from '$lib/components/common/SensitiveInput.svelte';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import Switch from '$lib/components/common/Switch.svelte';
+	import Tags from './common/Tags.svelte';
+	import { getToolServerData } from '$lib/apis';
+	import { verifyToolServerConnection, registerOAuthClient } from '$lib/apis/configs';
+	import AccessControl from './workspace/common/AccessControl.svelte';
+	import Spinner from '$lib/components/common/Spinner.svelte';
+	import XMark from '$lib/components/icons/XMark.svelte';
+
+	export let onSubmit: Function = () => {};
+	export let onDelete: Function = () => {};
+
+	export let show = false;
+	export let edit = false;
+
+	export let direct = false;
+	export let connection = null;
+
+	let inputElement = null;
+
+	let type = 'openapi'; // 'openapi', 'mcp'
+
+	let url = '';
+
+	let spec_type = 'url'; // 'url', 'json'
+	let spec = ''; // used when spec_type is 'json'
+	let path = 'openapi.json';
+
+	let auth_type = 'bearer';
+	let key = '';
+
+	let accessControl = {};
+
+	let id = '';
+	let name = '';
+	let description = '';
+
+	let oauthClientInfo = null;
+
+	let enable = true;
+	let loading = false;
+
+	const registerOAuthClientHandler = async () => {
+		if (url === '') {
+			toast.error($i18n.t('Please enter a valid URL'));
+			return;
+		}
+
+		if (id === '') {
+			toast.error($i18n.t('Please enter a valid ID'));
+			return;
+		}
+
+		const res = await registerOAuthClient(
+			localStorage.token,
+			{
+				url: url,
+				client_id: id
+			},
+			'mcp'
+		).catch((err) => {
+			toast.error($i18n.t('Registration failed'));
+			return null;
+		});
+
+		if (res) {
+			toast.warning(
+				$i18n.t(
+					'Please save the connection to persist the OAuth client information and do not change the ID'
+				)
+			);
+			toast.success($i18n.t('Registration successful'));
+
+			console.debug('Registration successful', res);
+			oauthClientInfo = res?.oauth_client_info ?? null;
+		}
+	};
+
+	const verifyHandler = async () => {
+		if (url === '') {
+			toast.error($i18n.t('Please enter a valid URL'));
+			return;
+		}
+
+		if (['openapi', ''].includes(type)) {
+			if (spec_type === 'json' && spec === '') {
+				toast.error($i18n.t('Please enter a valid JSON spec'));
+				return;
+			}
+
+			if (spec_type === 'url' && path === '') {
+				toast.error($i18n.t('Please enter a valid path'));
+				return;
+			}
+		}
+
+		if (direct) {
+			const res = await getToolServerData(
+				auth_type === 'bearer' ? key : localStorage.token,
+				path.includes('://') ? path : `${url}${path.startsWith('/') ? '' : '/'}${path}`
+			).catch((err) => {
+				toast.error($i18n.t('Connection failed'));
+			});
+
+			if (res) {
+				toast.success($i18n.t('Connection successful'));
+				console.debug('Connection successful', res);
+			}
+		} else {
+			const res = await verifyToolServerConnection(localStorage.token, {
+				url,
+				path,
+				type,
+				auth_type,
+				key,
+				config: {
+					enable: enable,
+					access_control: accessControl
+				},
+				info: {
+					id,
+					name,
+					description
+				}
+			}).catch((err) => {
+				toast.error($i18n.t('Connection failed'));
+			});
+
+			if (res) {
+				toast.success($i18n.t('Connection successful'));
+				console.debug('Connection successful', res);
+			}
+		}
+	};
+
+	const importHandler = async (e) => {
+		const file = e.target.files[0];
+		if (!file) return;
+
+		const reader = new FileReader();
+		reader.onload = (event) => {
+			const json = event.target.result;
+			console.log('importHandler', json);
+
+			try {
+				let data = JSON.parse(json);
+				// validate data
+				if (Array.isArray(data)) {
+					if (data.length === 0) {
+						toast.error($i18n.t('Please select a valid JSON file'));
+						return;
+					}
+					data = data[0];
+				}
+
+				if (data.type) type = data.type;
+				if (data.url) url = data.url;
+
+				if (data.spec_type) spec_type = data.spec_type;
+				if (data.spec) spec = data.spec;
+				if (data.path) path = data.path;
+
+				if (data.auth_type) auth_type = data.auth_type;
+				if (data.key) key = data.key;
+
+				if (data.info) {
+					id = data.info.id ?? '';
+					name = data.info.name ?? '';
+					description = data.info.description ?? '';
+				}
+
+				if (data.config) {
+					enable = data.config.enable ?? true;
+					accessControl = data.config.access_control ?? {};
+				}
+
+				toast.success($i18n.t('Import successful'));
+			} catch (error) {
+				toast.error($i18n.t('Please select a valid JSON file'));
+			}
+		};
+		reader.readAsText(file);
+	};
+
+	const exportHandler = async () => {
+		// export current connection as json file
+		const json = JSON.stringify([
+			{
+				type,
+				url,
+
+				spec_type,
+				spec,
+				path,
+
+				auth_type,
+				key,
+
+				info: {
+					id: id,
+					name: name,
+					description: description
+				}
+			}
+		]);
+
+		const blob = new Blob([json], {
+			type: 'application/json'
+		});
+
+		saveAs(blob, `tool-server-${id || name || 'export'}.json`);
+	};
+
+	const submitHandler = async () => {
+		loading = true;
+
+		// remove trailing slash from url
+		url = url.replace(/\/$/, '');
+		if (id.includes(':') || id.includes('|')) {
+			toast.error($i18n.t('ID cannot contain ":" or "|" characters'));
+			loading = false;
+			return;
+		}
+
+		if (type === 'mcp' && auth_type === 'oauth_2.1' && !oauthClientInfo) {
+			toast.error($i18n.t('Please register the OAuth client'));
+			loading = false;
+			return;
+		}
+
+		// validate spec
+		if (spec_type === 'json') {
+			try {
+				const specJSON = JSON.parse(spec);
+				spec = JSON.stringify(specJSON, null, 2);
+			} catch (e) {
+				toast.error($i18n.t('Please enter a valid JSON spec'));
+				loading = false;
+				return;
+			}
+		}
+
+		const connection = {
+			type,
+			url,
+
+			spec_type,
+			spec,
+			path,
+
+			auth_type,
+			key,
+			config: {
+				enable: enable,
+				access_control: accessControl
+			},
+			info: {
+				id: id,
+				name: name,
+				description: description,
+				...(oauthClientInfo ? { oauth_client_info: oauthClientInfo } : {})
+			}
+		};
+
+		await onSubmit(connection);
+
+		loading = false;
+		show = false;
+
+		// reset form
+		type = 'openapi';
+		url = '';
+
+		spec_type = 'url';
+		spec = '';
+		path = 'openapi.json';
+
+		key = '';
+		auth_type = 'bearer';
+
+		id = '';
+		name = '';
+		description = '';
+		oauthClientInfo = null;
+
+		enable = true;
+		accessControl = null;
+	};
+
+	const init = () => {
+		if (connection) {
+			type = connection?.type ?? 'openapi';
+			url = connection.url;
+
+			spec_type = connection?.spec_type ?? 'url';
+			spec = connection?.spec ?? '';
+			path = connection?.path ?? 'openapi.json';
+
+			auth_type = connection?.auth_type ?? 'bearer';
+			key = connection?.key ?? '';
+
+			id = connection.info?.id ?? '';
+			name = connection.info?.name ?? '';
+			description = connection.info?.description ?? '';
+			oauthClientInfo = connection.info?.oauth_client_info ?? null;
+
+			enable = connection.config?.enable ?? true;
+			accessControl = connection.config?.access_control ?? null;
+		}
+	};
+
+	$: if (show) {
+		init();
+	}
+
+	onMount(() => {
+		init();
+	});
+</script>
+
+<Modal size="sm" bind:show>
+	<div>
+		<div class=" flex justify-between dark:text-gray-100 px-5 pt-4 pb-2">
+			<h1 class=" text-lg font-medium self-center font-primary">
+				{#if edit}
+					{$i18n.t('Edit Connection')}
+				{:else}
+					{$i18n.t('Add Connection')}
+				{/if}
+			</h1>
+
+			<div class="flex items-center gap-3">
+				<div class="flex gap-1.5 text-xs justify-end">
+					<button
+						class=" hover:underline"
+						type="button"
+						on:click={() => {
+							inputElement?.click();
+						}}
+					>
+						{$i18n.t('Import')}
+					</button>
+
+					<button class=" hover:underline" type="button" on:click={exportHandler}>
+						{$i18n.t('Export')}
+					</button>
+				</div>
+				<button
+					class="self-center"
+					aria-label={$i18n.t('Close Configure Connection Modal')}
+					on:click={() => {
+						show = false;
+					}}
+				>
+					<XMark className={'size-5'} />
+				</button>
+			</div>
+		</div>
+
+		<div class="flex flex-col md:flex-row w-full px-4 pb-4 md:space-x-4 dark:text-gray-200">
+			<div class=" flex flex-col w-full sm:flex-row sm:justify-center sm:space-x-6">
+				<input
+					bind:this={inputElement}
+					type="file"
+					hidden
+					accept=".json"
+					on:change={(e) => {
+						importHandler(e);
+					}}
+				/>
+
+				<form
+					class="flex flex-col w-full"
+					on:submit={(e) => {
+						e.preventDefault();
+						submitHandler();
+					}}
+				>
+					<div class="px-1">
+						{#if !direct}
+							<div class="flex gap-2 mb-1.5">
+								<div class="flex w-full justify-between items-center">
+									<div class=" text-xs text-gray-500">{$i18n.t('Type')}</div>
+
+									<div class="">
+										<button
+											on:click={() => {
+												type = ['', 'openapi'].includes(type) ? 'mcp' : 'openapi';
+											}}
+											type="button"
+											class=" text-xs text-gray-700 dark:text-gray-300"
+										>
+											{#if ['', 'openapi'].includes(type)}
+												{$i18n.t('OpenAPI')}
+											{:else if type === 'mcp'}
+												{$i18n.t('MCP')}
+												<span class="text-gray-500">{$i18n.t('Streamable HTTP')}</span>
+											{/if}
+										</button>
+									</div>
+								</div>
+							</div>
+						{/if}
+
+						<div class="flex gap-2">
+							<div class="flex flex-col w-full">
+								<div class="flex justify-between mb-0.5">
+									<label
+										for="api-base-url"
+										class={`text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+										>{$i18n.t('URL')}</label
+									>
+								</div>
+
+								<div class="flex flex-1 items-center">
+									<input
+										id="api-base-url"
+										class={`w-full flex-1 text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
+										type="text"
+										bind:value={url}
+										placeholder={$i18n.t('API Base URL')}
+										autocomplete="off"
+										required
+									/>
+
+									<Tooltip
+										content={$i18n.t('Verify Connection')}
+										className="shrink-0 flex items-center mr-1"
+									>
+										<button
+											class="self-center p-1 bg-transparent hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 rounded-lg transition"
+											on:click={() => {
+												verifyHandler();
+											}}
+											aria-label={$i18n.t('Verify Connection')}
+											type="button"
+										>
+											<svg
+												xmlns="http://www.w3.org/2000/svg"
+												viewBox="0 0 20 20"
+												fill="currentColor"
+												class="w-4 h-4"
+												aria-hidden="true"
+											>
+												<path
+													fill-rule="evenodd"
+													d="M15.312 11.424a5.5 5.5 0 01-9.201 2.466l-.312-.311h2.433a.75.75 0 000-1.5H3.989a.75.75 0 00-.75.75v4.242a.75.75 0 001.5 0v-2.43l.31.31a7 7 0 0011.712-3.138.75.75 0 00-1.449-.39zm1.23-3.723a.75.75 0 00.219-.53V2.929a.75.75 0 00-1.5 0V5.36l-.31-.31A7 7 0 003.239 8.188a.75.75 0 101.448.389A5.5 5.5 0 0113.89 6.11l.311.31h-2.432a.75.75 0 000 1.5h4.243a.75.75 0 00.53-.219z"
+													clip-rule="evenodd"
+												/>
+											</svg>
+										</button>
+									</Tooltip>
+
+									<Tooltip content={enable ? $i18n.t('Enabled') : $i18n.t('Disabled')}>
+										<Switch bind:state={enable} />
+									</Tooltip>
+								</div>
+							</div>
+						</div>
+
+						{#if ['', 'openapi'].includes(type)}
+							<div class="flex gap-2 mt-2">
+								<div class="flex flex-col w-full">
+									<div class="flex justify-between items-center mb-0.5">
+										<div class="flex gap-2 items-center">
+											<div
+												for="select-bearer-or-session"
+												class={`text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+											>
+												{$i18n.t('OpenAPI Spec')}
+											</div>
+										</div>
+									</div>
+
+									<div class="flex gap-2">
+										<div class="flex-shrink-0 self-start">
+											<select
+												id="select-bearer-or-session"
+												class={`w-full text-sm bg-transparent pr-5 ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
+												bind:value={spec_type}
+											>
+												<option value="url">{$i18n.t('URL')}</option>
+												<option value="json">{$i18n.t('JSON')}</option>
+											</select>
+										</div>
+
+										<div class="flex flex-1 items-center">
+											{#if spec_type === 'url'}
+												<div class="flex-1 flex items-center">
+													<label for="url-or-path" class="sr-only"
+														>{$i18n.t('openapi.json URL or Path')}</label
+													>
+													<input
+														class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
+														type="text"
+														id="url-or-path"
+														bind:value={path}
+														placeholder={$i18n.t('openapi.json URL or Path')}
+														autocomplete="off"
+														required
+													/>
+												</div>
+											{:else if spec_type === 'json'}
+												<div
+													class={`text-xs w-full self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+												>
+													<label for="url-or-path" class="sr-only">{$i18n.t('JSON Spec')}</label>
+													<textarea
+														class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700 text-black dark:text-white'}`}
+														bind:value={spec}
+														placeholder={$i18n.t('JSON Spec')}
+														autocomplete="off"
+														required
+														rows="5"
+													/>
+												</div>
+											{/if}
+										</div>
+									</div>
+
+									{#if ['', 'url'].includes(spec_type)}
+										<div
+											class={`text-xs mt-1 ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+										>
+											{$i18n.t(`WebUI will make requests to "{{url}}"`, {
+												url: path.includes('://')
+													? path
+													: `${url}${path.startsWith('/') ? '' : '/'}${path}`
+											})}
+										</div>
+									{/if}
+								</div>
+							</div>
+						{/if}
+
+						<div class="flex gap-2 mt-2">
+							<div class="flex flex-col w-full">
+								<div class="flex justify-between items-center">
+									<div class="flex gap-2 items-center">
+										<div
+											for="select-bearer-or-session"
+											class={`text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+										>
+											{$i18n.t('Auth')}
+										</div>
+									</div>
+
+									{#if auth_type === 'oauth_2.1'}
+										<div class="flex items-center gap-2">
+											<div class="flex flex-col justify-end items-center shrink-0">
+												<Tooltip
+													content={oauthClientInfo
+														? $i18n.t('Register Again')
+														: $i18n.t('Register Client')}
+												>
+													<button
+														class=" text-xs underline dark:text-gray-500 dark:hover:text-gray-200 text-gray-700 hover:text-gray-900 transition"
+														type="button"
+														on:click={() => {
+															registerOAuthClientHandler();
+														}}
+													>
+														{$i18n.t('Register Client')}
+													</button>
+												</Tooltip>
+											</div>
+
+											{#if !oauthClientInfo}
+												<div
+													class="text-xs font-medium px-1.5 rounded-md bg-yellow-500/20 text-yellow-700 dark:text-yellow-200"
+												>
+													{$i18n.t('Not Registered')}
+												</div>
+											{:else}
+												<div
+													class="text-xs font-medium px-1.5 rounded-md bg-green-500/20 text-green-700 dark:text-green-200"
+												>
+													{$i18n.t('Registered')}
+												</div>
+											{/if}
+										</div>
+									{/if}
+								</div>
+
+								<div class="flex gap-2">
+									<div class="flex-shrink-0 self-start">
+										<select
+											id="select-bearer-or-session"
+											class={`w-full text-sm bg-transparent pr-5 ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
+											bind:value={auth_type}
+										>
+											<option value="none">{$i18n.t('None')}</option>
+
+											<option value="bearer">{$i18n.t('Bearer')}</option>
+											<option value="session">{$i18n.t('Session')}</option>
+
+											{#if !direct}
+												<option value="system_oauth">{$i18n.t('OAuth')}</option>
+												{#if type === 'mcp'}
+													<option value="oauth_2.1">{$i18n.t('OAuth 2.1')}</option>
+												{/if}
+											{/if}
+										</select>
+									</div>
+
+									<div class="flex flex-1 items-center">
+										{#if auth_type === 'bearer'}
+											<SensitiveInput
+												bind:value={key}
+												placeholder={$i18n.t('API Key')}
+												required={false}
+											/>
+										{:else if auth_type === 'none'}
+											<div
+												class={`text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+											>
+												{$i18n.t('No authentication')}
+											</div>
+										{:else if auth_type === 'session'}
+											<div
+												class={`text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+											>
+												{$i18n.t('Forwards system user session credentials to authenticate')}
+											</div>
+										{:else if auth_type === 'system_oauth'}
+											<div
+												class={`text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+											>
+												{$i18n.t('Forwards system user OAuth access token to authenticate')}
+											</div>
+										{:else if auth_type === 'oauth_2.1'}
+											<div
+												class={`flex items-center text-xs self-center translate-y-[1px] ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+											>
+												{$i18n.t('Uses OAuth 2.1 Dynamic Client Registration')}
+											</div>
+										{/if}
+									</div>
+								</div>
+							</div>
+						</div>
+
+						{#if !direct}
+							<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
+
+							<div class="flex gap-2">
+								<div class="flex flex-col w-full">
+									<label
+										for="enter-id"
+										class={`mb-0.5 text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+										>{$i18n.t('ID')}
+
+										{#if type !== 'mcp'}
+											<span class="text-xs text-gray-200 dark:text-gray-800 ml-0.5"
+												>{$i18n.t('Optional')}</span
+											>
+										{/if}
+									</label>
+
+									<div class="flex-1">
+										<input
+											id="enter-id"
+											class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
+											type="text"
+											bind:value={id}
+											placeholder={$i18n.t('Enter ID')}
+											autocomplete="off"
+											required={type === 'mcp'}
+										/>
+									</div>
+								</div>
+							</div>
+
+							<div class="flex gap-2 mt-2">
+								<div class="flex flex-col w-full">
+									<label
+										for="enter-name"
+										class={`mb-0.5 text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100' : 'text-gray-500'}`}
+										>{$i18n.t('Name')}
+									</label>
+
+									<div class="flex-1">
+										<input
+											id="enter-name"
+											class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
+											type="text"
+											bind:value={name}
+											placeholder={$i18n.t('Enter name')}
+											autocomplete="off"
+											required
+										/>
+									</div>
+								</div>
+							</div>
+
+							<div class="flex flex-col w-full mt-2">
+								<label
+									for="description"
+									class={`mb-1 text-xs ${($settings?.highContrastMode ?? false) ? 'text-gray-800 dark:text-gray-100 placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700 text-gray-500'}`}
+									>{$i18n.t('Description')}</label
+								>
+
+								<div class="flex-1">
+									<input
+										id="description"
+										class={`w-full text-sm bg-transparent ${($settings?.highContrastMode ?? false) ? 'placeholder:text-gray-700 dark:placeholder:text-gray-100' : 'outline-hidden placeholder:text-gray-300 dark:placeholder:text-gray-700'}`}
+										type="text"
+										bind:value={description}
+										placeholder={$i18n.t('Enter description')}
+										autocomplete="off"
+									/>
+								</div>
+							</div>
+
+							<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
+
+							<div class="my-2 -mx-2">
+								<div class="px-4 py-3 bg-gray-50 dark:bg-gray-950 rounded-3xl">
+									<AccessControl bind:accessControl />
+								</div>
+							</div>
+						{/if}
+					</div>
+
+					{#if type === 'mcp'}
+						<div
+							class=" bg-yellow-500/20 text-yellow-700 dark:text-yellow-200 rounded-2xl text-xs px-4 py-3 mb-2"
+						>
+							<span class="font-medium">
+								{$i18n.t('Warning')}:
+							</span>
+							{$i18n.t(
+								'MCP support is experimental and its specification changes often, which can lead to incompatibilities. OpenAPI specification support is directly maintained by the Open WebUI team, making it the more reliable option for compatibility.'
+							)}
+
+							<a
+								class="font-medium underline"
+								href="https://docs.openwebui.com/features/mcp"
+								target="_blank">{$i18n.t('Read more →')}</a
+							>
+						</div>
+					{/if}
+
+					<div class="flex justify-between pt-3 text-sm font-medium gap-1.5">
+						<div></div>
+						<div class="flex gap-1.5">
+							{#if edit}
+								<button
+									class="px-3.5 py-1.5 text-sm font-medium dark:bg-black dark:hover:bg-gray-900 dark:text-white bg-white text-black hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center"
+									type="button"
+									on:click={() => {
+										onDelete();
+										show = false;
+									}}
+								>
+									{$i18n.t('Delete')}
+								</button>
+							{/if}
+
+							<button
+								class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center {loading
+									? ' cursor-not-allowed'
+									: ''}"
+								type="submit"
+								disabled={loading}
+							>
+								{$i18n.t('Save')}
+
+								{#if loading}
+									<div class="ml-2 self-center">
+										<Spinner />
+									</div>
+								{/if}
+							</button>
+						</div>
+					</div>
+				</form>
+			</div>
+		</div>
+	</div>
+</Modal>

src/lib/components/ChangelogModal.svelte

@@ -19,16 +19,19 @@
 
 	let changelog = null;
 
-	onMount(async () => {
+	const init = async () => {
-		const res = await getChangelog();
+		changelog = await getChangelog();
-		changelog = res;
+	};
-	});
+
+	$: if (show) {
+		init();
+	}
 </script>
 
 <Modal bind:show size="xl">
-	<div class="px-5 pt-4 dark:text-gray-300 text-gray-700">
+	<div class="px-6 pt-5 dark:text-white text-black">
 		<div class="flex justify-between items-start">
-			<div class="text-xl font-semibold">
+			<div class="text-xl font-medium">
 				{$i18n.t("What's New in")}
 				{$WEBUI_NAME}
 				<Confetti x={[-1, -0.25]} y={[0, 0.5]} />
@@ -48,7 +51,7 @@
 		</div>
 		<div class="flex items-center mt-1">
 			<div class="text-sm dark:text-gray-200">{$i18n.t('Release Notes')}</div>
-			<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-200 dark:bg-gray-700" />
+			<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-50/50 dark:bg-gray-850/50" />
 			<div class="text-sm dark:text-gray-200">
 				v{WEBUI_VERSION}
 			</div>
@@ -56,7 +59,7 @@
 	</div>
 
 	<div class=" w-full p-4 px-5 text-gray-700 dark:text-gray-100">
-		<div class=" overflow-y-scroll max-h-[32rem] scrollbar-hidden">
+		<div class=" overflow-y-scroll max-h-[30rem] scrollbar-hidden">
 			<div class="mb-3">
 				{#if changelog}
 					{#each Object.keys(changelog) as version}
@@ -65,20 +68,20 @@
 								v{version} - {changelog[version].date}
 							</div>
 
-							<hr class="border-gray-100 dark:border-gray-850 my-2" />
+							<hr class="border-gray-50/50 dark:border-gray-850/50 my-2" />
 
 							{#each Object.keys(changelog[version]).filter((section) => section !== 'date') as section}
 								<div class="w-full">
 									<div
 										class="font-semibold uppercase text-xs {section === 'added'
-											? 'text-white bg-blue-600'
+											? 'bg-blue-500/20 text-blue-700 dark:text-blue-200'
 											: section === 'fixed'
-												? 'text-white bg-green-600'
+												? 'bg-green-500/20 text-green-700 dark:text-green-200'
 												: section === 'changed'
-													? 'text-white bg-yellow-600'
+													? 'bg-yellow-500/20 text-yellow-700 dark:text-yellow-200'
 													: section === 'removed'
-														? 'text-white bg-red-600'
+														? 'bg-red-500/20 text-red-700 dark:text-red-200'
-														: ''}  w-fit px-3 rounded-full my-2.5"
+														: ''}  w-fit rounded-xl px-2 my-2.5"
 									>
 										{section}
 									</div>

src/lib/components/NotificationToast.svelte

@@ -12,6 +12,43 @@
 	export let title: string = 'HI';
 	export let content: string;
 
+	let startX = 0,
+		startY = 0;
+	let moved = false;
+	const DRAG_THRESHOLD_PX = 6;
+
+	const clickHandler = () => {
+		onClick();
+		dispatch('closeToast');
+	};
+
+	function onPointerDown(e: PointerEvent) {
+		startX = e.clientX;
+		startY = e.clientY;
+		moved = false;
+		// Ensure we continue to get events even if the toast moves under the pointer.
+		(e.currentTarget as HTMLElement).setPointerCapture?.(e.pointerId);
+	}
+
+	function onPointerMove(e: PointerEvent) {
+		if (moved) return;
+		const dx = e.clientX - startX;
+		const dy = e.clientY - startY;
+		if (dx * dx + dy * dy > DRAG_THRESHOLD_PX * DRAG_THRESHOLD_PX) {
+			moved = true;
+		}
+	}
+
+	function onPointerUp(e: PointerEvent) {
+		// Release capture if taken
+		(e.currentTarget as HTMLElement).releasePointerCapture?.(e.pointerId);
+
+		// Only treat as a click if there wasn't a drag
+		if (!moved) {
+			clickHandler();
+		}
+	}
+
 	onMount(() => {
 		if (!navigator.userActivation.hasBeenActive) {
 			return;
@@ -31,24 +68,33 @@
 	});
 </script>
 
-<button
+<!-- svelte-ignore a11y-click-events-have-key-events -->
-	class="flex gap-2.5 text-left min-w-[var(--width)] w-full dark:bg-gray-850 dark:text-white bg-white text-black border border-gray-100 dark:border-gray-850 rounded-xl px-3.5 py-3.5"
+<!-- svelte-ignore a11y-no-static-element-interactions -->
-	on:click={() => {
+<div
-		onClick();
+	class="flex gap-2.5 text-left min-w-[var(--width)] w-full dark:bg-gray-850 dark:text-white bg-white text-black border border-gray-100 dark:border-gray-800 rounded-3xl px-4 py-3.5 cursor-pointer select-none"
-		dispatch('closeToast');
+	on:dragstart|preventDefault
+	on:pointerdown={onPointerDown}
+	on:pointermove={onPointerMove}
+	on:pointerup={onPointerUp}
+	on:pointercancel={() => (moved = true)}
+	on:keydown={(e) => {
+		if (e.key === 'Enter' || e.key === ' ') {
+			e.preventDefault();
+			clickHandler();
+		}
 	}}
 >
 	<div class="shrink-0 self-top -translate-y-0.5">
-		<img src="{WEBUI_BASE_URL}/static/favicon.png" alt="favicon" class="size-7 rounded-full" />
+		<img src="{WEBUI_BASE_URL}/static/favicon.png" alt="favicon" class="size-6 rounded-full" />
 	</div>
 
 	<div>
 		{#if title}
-			<div class=" text-[13px] font-medium mb-0.5 line-clamp-1 capitalize">{title}</div>
+			<div class=" text-[13px] font-medium mb-0.5 line-clamp-1">{title}</div>
 		{/if}
 
 		<div class=" line-clamp-2 text-xs self-center dark:text-gray-300 font-normal">
 			{@html DOMPurify.sanitize(marked(content))}
 		</div>
 	</div>
-</button>
+</div>

src/lib/components/admin/Evaluations.svelte

@@ -56,7 +56,7 @@
 	<div class="flex flex-col lg:flex-row w-full h-full pb-2 lg:space-x-4">
 		<div
 			id="users-tabs-container"
-			class="tabs flex flex-row overflow-x-auto gap-2.5 max-w-full lg:gap-1 lg:flex-col lg:flex-none lg:w-40 dark:text-gray-200 text-sm font-medium text-left scrollbar-none"
+			class="tabs mx-[16px] lg:mx-0 lg:px-[16px] flex flex-row overflow-x-auto gap-2.5 max-w-full lg:gap-1 lg:flex-col lg:flex-none lg:w-50 dark:text-gray-200 text-sm font-medium text-left scrollbar-none"
 		>
 			<button
 				id="leaderboard"
@@ -113,7 +113,7 @@
 			</button>
 		</div>
 
-		<div class="flex-1 mt-1 lg:mt-0 overflow-y-scroll">
+		<div class="flex-1 mt-1 lg:mt-0 px-[16px] lg:pr-[16px] lg:pl-0 overflow-y-scroll">
 			{#if selectedTab === 'leaderboard'}
 				<Leaderboard {feedbacks} />
 			{:else if selectedTab === 'feedbacks'}

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

@@ -13,7 +13,7 @@
 	import GarbageBin from '$lib/components/icons/GarbageBin.svelte';
 	import Pencil from '$lib/components/icons/Pencil.svelte';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
-	import Download from '$lib/components/icons/ArrowDownTray.svelte';
+	import Download from '$lib/components/icons/Download.svelte';
 
 	let show = false;
 </script>
@@ -25,7 +25,7 @@
 
 	<div slot="content">
 		<DropdownMenu.Content
-			class="w-full max-w-[150px] rounded-xl px-1 py-1.5 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-lg"
+			class="w-full max-w-[150px] rounded-xl p-1 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-lg"
 			sideOffset={-2}
 			side="bottom"
 			align="start"

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

@@ -13,7 +13,7 @@
 	import { deleteFeedbackById, exportAllFeedbacks, getAllFeedbacks } from '$lib/apis/evaluations';
 
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
-	import ArrowDownTray from '$lib/components/icons/ArrowDownTray.svelte';
+	import Download from '$lib/components/icons/Download.svelte';
 	import Badge from '$lib/components/common/Badge.svelte';
 	import CloudArrowUp from '$lib/components/icons/CloudArrowUp.svelte';
 	import Pagination from '$lib/components/common/Pagination.svelte';
@@ -169,7 +169,7 @@
 
 <FeedbackModal bind:show={showFeedbackModal} {selectedFeedback} onClose={closeFeedbackModal} />
 
-<div class="mt-0.5 mb-2 gap-1 flex flex-row justify-between">
+<div class="mt-0.5 mb-1 gap-1 flex flex-row justify-between">
 	<div class="flex md:self-center text-lg font-medium px-0.5">
 		{$i18n.t('Feedback History')}
 
@@ -187,31 +187,25 @@
 						exportHandler();
 					}}
 				>
-					<ArrowDownTray className="size-3" />
+					<Download className="size-3" />
 				</button>
 			</Tooltip>
 		</div>
 	{/if}
 </div>
 
-<div
+<div class="scrollbar-hidden relative whitespace-nowrap overflow-x-auto max-w-full">
-	class="scrollbar-hidden relative whitespace-nowrap overflow-x-auto max-w-full rounded-sm pt-0.5"
->
 	{#if (feedbacks ?? []).length === 0}
 		<div class="text-center text-xs text-gray-500 dark:text-gray-400 py-1">
 			{$i18n.t('No feedbacks found')}
 		</div>
 	{:else}
-		<table
+		<table class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto max-w-full">
-			class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto max-w-full rounded-sm"
+			<thead class="text-xs text-gray-800 uppercase bg-transparent dark:text-gray-200">
-		>
+				<tr class=" border-b-[1.5px] border-gray-50 dark:border-gray-850">
-			<thead
-				class="text-xs text-gray-700 uppercase bg-gray-50 dark:bg-gray-850 dark:text-gray-400 -translate-y-0.5"
-			>
-				<tr class="">
 					<th
 						scope="col"
-						class="px-3 py-1.5 cursor-pointer select-none w-3"
+						class="px-2.5 py-2 cursor-pointer select-none w-3"
 						on:click={() => setSortKey('user')}
 					>
 						<div class="flex gap-1.5 items-center justify-end">
@@ -234,7 +228,7 @@
 
 					<th
 						scope="col"
-						class="px-3 pr-1.5 cursor-pointer select-none"
+						class="px-2.5 py-2 cursor-pointer select-none"
 						on:click={() => setSortKey('model_id')}
 					>
 						<div class="flex gap-1.5 items-center">
@@ -257,7 +251,7 @@
 
 					<th
 						scope="col"
-						class="px-3 py-1.5 text-right cursor-pointer select-none w-fit"
+						class="px-2.5 py-2 text-right cursor-pointer select-none w-fit"
 						on:click={() => setSortKey('rating')}
 					>
 						<div class="flex gap-1.5 items-center justify-end">
@@ -280,7 +274,7 @@
 
 					<th
 						scope="col"
-						class="px-3 py-1.5 text-right cursor-pointer select-none w-0"
+						class="px-2.5 py-2 text-right cursor-pointer select-none w-0"
 						on:click={() => setSortKey('updated_at')}
 					>
 						<div class="flex gap-1.5 items-center justify-end">
@@ -301,7 +295,7 @@
 						</div>
 					</th>
 
-					<th scope="col" class="px-3 py-1.5 text-right cursor-pointer select-none w-0"> </th>
+					<th scope="col" class="px-2.5 py-2 text-right cursor-pointer select-none w-0"> </th>
 				</tr>
 			</thead>
 			<tbody class="">

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

@@ -1,9 +1,4 @@
 <script lang="ts">
-	import * as ort from 'onnxruntime-web';
-	import { env, AutoModel, AutoTokenizer } from '@huggingface/transformers';
-
-	env.backends.onnx.wasm.wasmPaths = '/wasm/';
-
 	import { onMount, getContext } from 'svelte';
 	import { models } from '$lib/stores';
 
@@ -237,6 +232,11 @@
 	//////////////////////
 
 	const loadEmbeddingModel = async () => {
+		const { env, AutoModel, AutoTokenizer } = await import('@huggingface/transformers');
+		if (env.backends.onnx.wasm) {
+			env.backends.onnx.wasm.wasmPaths = '/wasm/';
+		}
+
 		// Check if the tokenizer and model are already loaded and stored in the window object
 		if (!window.tokenizer) {
 			window.tokenizer = await AutoTokenizer.from_pretrained(EMBEDDING_MODEL);
@@ -337,7 +337,7 @@
 />
 
 <div
-	class="pt-0.5 pb-2 gap-1 flex flex-col md:flex-row justify-between sticky top-0 z-10 bg-white dark:bg-gray-900"
+	class="pt-0.5 pb-1 gap-1 flex flex-col md:flex-row justify-between sticky top-0 z-10 bg-white dark:bg-gray-900"
 >
 	<div class="flex md:self-center text-lg font-medium px-0.5 shrink-0 items-center">
 		<div class=" gap-1">
@@ -370,9 +370,7 @@
 	</div>
 </div>
 
-<div
+<div class="scrollbar-hidden relative whitespace-nowrap overflow-x-auto max-w-full rounded-sm">
-	class="scrollbar-hidden relative whitespace-nowrap overflow-x-auto max-w-full rounded-sm pt-0.5"
->
 	{#if loadingLeaderboard}
 		<div class=" absolute top-0 bottom-0 left-0 right-0 flex">
 			<div class="m-auto">
@@ -386,17 +384,15 @@
 		</div>
 	{:else}
 		<table
-			class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto max-w-full rounded {loadingLeaderboard
+			class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto max-w-full {loadingLeaderboard
 				? 'opacity-20'
 				: ''}"
 		>
-			<thead
+			<thead class="text-xs text-gray-800 uppercase bg-transparent dark:text-gray-200">
-				class="text-xs text-gray-700 uppercase bg-gray-50 dark:bg-gray-850 dark:text-gray-400 -translate-y-0.5"
+				<tr class=" border-b-[1.5px] border-gray-50 dark:border-gray-850">
-			>
-				<tr class="">
 					<th
 						scope="col"
-						class="px-3 py-1.5 cursor-pointer select-none w-3"
+						class="px-2.5 py-2 cursor-pointer select-none w-3"
 						on:click={() => setSortKey('rating')}
 					>
 						<div class="flex gap-1.5 items-center">
@@ -418,7 +414,7 @@
 					</th>
 					<th
 						scope="col"
-						class="px-3 py-1.5 cursor-pointer select-none"
+						class="px-2.5 py-2 cursor-pointer select-none"
 						on:click={() => setSortKey('name')}
 					>
 						<div class="flex gap-1.5 items-center">
@@ -440,7 +436,7 @@
 					</th>
 					<th
 						scope="col"
-						class="px-3 py-1.5 text-right cursor-pointer select-none w-fit"
+						class="px-2.5 py-2 text-right cursor-pointer select-none w-fit"
 						on:click={() => setSortKey('rating')}
 					>
 						<div class="flex gap-1.5 items-center justify-end">
@@ -462,7 +458,7 @@
 					</th>
 					<th
 						scope="col"
-						class="px-3 py-1.5 text-right cursor-pointer select-none w-5"
+						class="px-2.5 py-2 text-right cursor-pointer select-none w-5"
 						on:click={() => setSortKey('won')}
 					>
 						<div class="flex gap-1.5 items-center justify-end">
@@ -484,7 +480,7 @@
 					</th>
 					<th
 						scope="col"
-						class="px-3 py-1.5 text-right cursor-pointer select-none w-5"
+						class="px-2.5 py-2 text-right cursor-pointer select-none w-5"
 						on:click={() => setSortKey('lost')}
 					>
 						<div class="flex gap-1.5 items-center justify-end">

src/lib/components/admin/Functions.svelte

@@ -18,7 +18,7 @@
 		toggleGlobalById
 	} from '$lib/apis/functions';
 
-	import ArrowDownTray from '../icons/ArrowDownTray.svelte';
+	import Download from '../icons/Download.svelte';
 	import Tooltip from '../common/Tooltip.svelte';
 	import ConfirmDialog from '../common/ConfirmDialog.svelte';
 	import { getModels } from '$lib/apis';
@@ -222,7 +222,7 @@
 	}}
 />
 
-<div class="flex flex-col mt-1.5 mb-0.5">
+<div class="flex flex-col mt-1.5 mb-0.5 px-[16px]">
 	<div class="flex justify-between items-center mb-1">
 		<div class="flex md:self-center text-xl items-center font-medium px-0.5">
 			{$i18n.t('Functions')}
@@ -317,7 +317,7 @@
 	</div>
 </div>
 
-<div class="mb-5">
+<div class="mb-5 px-[16px]">
 	{#each filteredItems as func (func.id)}
 		<div
 			class=" flex space-x-4 cursor-pointer w-full px-2 py-2 dark:hover:bg-white/5 hover:bg-black/5 rounded-xl"
@@ -330,14 +330,14 @@
 					<div class=" flex-1 self-center pl-1">
 						<div class=" font-semibold flex items-center gap-1.5">
 							<div
-								class=" text-xs font-bold px-1 rounded-sm uppercase line-clamp-1 bg-gray-500/20 text-gray-700 dark:text-gray-200"
+								class=" text-xs font-semibold px-1 rounded-sm uppercase line-clamp-1 bg-gray-500/20 text-gray-700 dark:text-gray-200"
 							>
 								{func.type}
 							</div>
 
 							{#if func?.meta?.manifest?.version}
 								<div
-									class="text-xs font-bold px-1 rounded-sm line-clamp-1 bg-gray-500/20 text-gray-700 dark:text-gray-200"
+									class="text-xs font-semibold px-1 rounded-sm line-clamp-1 bg-gray-500/20 text-gray-700 dark:text-gray-200"
 								>
 									v{func?.meta?.manifest?.version ?? ''}
 								</div>
@@ -482,7 +482,7 @@
 	)}
 </div> -->
 
-<div class=" flex justify-end w-full mb-2">
+<div class=" flex justify-end w-full mb-2 px-[16px]">
 	<div class="flex space-x-2">
 		<input
 			id="documents-import-input"
@@ -562,7 +562,7 @@
 </div>
 
 {#if $config?.features.enable_community_sharing}
-	<div class=" my-16">
+	<div class=" my-16 px-[16px]">
 		<div class=" text-xl font-medium mb-1 line-clamp-1">
 			{$i18n.t('Made by Open WebUI Community')}
 		</div>
@@ -595,7 +595,7 @@
 		deleteHandler(selectedFunction);
 	}}
 >
-	<div class=" text-sm text-gray-500">
+	<div class=" text-sm text-gray-500 truncate">
 		{$i18n.t('This will delete')} <span class="  font-semibold">{selectedFunction.name}</span>.
 	</div>
 </DeleteConfirmDialog>

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

@@ -8,7 +8,7 @@
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
 	import Share from '$lib/components/icons/Share.svelte';
 	import DocumentDuplicate from '$lib/components/icons/DocumentDuplicate.svelte';
-	import ArrowDownTray from '$lib/components/icons/ArrowDownTray.svelte';
+	import Download from '$lib/components/icons/Download.svelte';
 	import Switch from '$lib/components/common/Switch.svelte';
 	import GlobeAlt from '$lib/components/icons/GlobeAlt.svelte';
 	import Github from '$lib/components/icons/Github.svelte';
@@ -41,7 +41,7 @@
 
 	<div slot="content">
 		<DropdownMenu.Content
-			class="w-full max-w-[190px] text-sm rounded-xl px-1 py-1.5 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-lg font-primary"
+			class="w-full max-w-[190px] text-sm rounded-xl p-1 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-lg font-primary"
 			sideOffset={-2}
 			side="bottom"
 			align="start"

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

@@ -8,7 +8,7 @@
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
 	import Share from '$lib/components/icons/Share.svelte';
 	import DocumentDuplicate from '$lib/components/icons/DocumentDuplicate.svelte';
-	import ArrowDownTray from '$lib/components/icons/ArrowDownTray.svelte';
+	import Download from '$lib/components/icons/Download.svelte';
 	import Switch from '$lib/components/common/Switch.svelte';
 	import GlobeAlt from '$lib/components/icons/GlobeAlt.svelte';
 
@@ -42,7 +42,7 @@
 
 	<div slot="content">
 		<DropdownMenu.Content
-			class="w-full max-w-[180px] rounded-xl px-1 py-1.5 border border-gray-100  dark:border-gray-800 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-sm"
+			class="w-full max-w-[180px] rounded-xl p-1 border border-gray-100  dark:border-gray-800 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-sm"
 			sideOffset={-2}
 			side="bottom"
 			align="start"
@@ -63,7 +63,7 @@
 					</div>
 				</div>
 
-				<hr class="border-gray-100 dark:border-gray-850 my-1" />
+				<hr class="border-gray-50 dark:border-gray-850 my-1" />
 			{/if}
 
 			<DropdownMenu.Item
@@ -117,12 +117,12 @@
 					exportHandler();
 				}}
 			>
-				<ArrowDownTray />
+				<Download />
 
 				<div class="flex items-center">{$i18n.t('Export')}</div>
 			</DropdownMenu.Item>
 
-			<hr class="border-gray-100 dark:border-gray-850 my-1" />
+			<hr class="border-gray-50 dark:border-gray-850 my-1" />
 
 			<DropdownMenu.Item
 				class="flex  gap-2  items-center px-3 py-1.5 text-sm  font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-md"

src/lib/components/admin/Settings.svelte

@@ -83,7 +83,7 @@
 <div class="flex flex-col lg:flex-row w-full h-full pb-2 lg:space-x-4">
 	<div
 		id="admin-settings-tabs-container"
-		class="tabs flex flex-row overflow-x-auto gap-2.5 max-w-full lg:gap-1 lg:flex-col lg:flex-none lg:w-40 dark:text-gray-200 text-sm font-medium text-left scrollbar-none"
+		class="tabs mx-[16px] lg:mx-0 lg:px-[16px] flex flex-row overflow-x-auto gap-2.5 max-w-full lg:gap-1 lg:flex-col lg:flex-none lg:w-50 dark:text-gray-200 text-sm font-medium text-left scrollbar-none"
 	>
 		<button
 			id="general"
@@ -433,7 +433,9 @@
 		</button>
 	</div>
 
-	<div class="flex-1 mt-3 lg:mt-0 overflow-y-scroll pr-1 scrollbar-hidden">
+	<div
+		class="flex-1 mt-3 lg:mt-0 px-[16px] lg:pr-[16px] lg:pl-0 overflow-y-scroll scrollbar-hidden"
+	>
 		{#if selectedTab === 'general'}
 			<General
 				saveHandler={async () => {

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

@@ -19,6 +19,7 @@
 
 	import type { Writable } from 'svelte/store';
 	import type { i18n as i18nType } from 'i18next';
+	import Textarea from '$lib/components/common/Textarea.svelte';
 
 	const i18n = getContext<Writable<i18nType>>('i18n');
 
@@ -31,6 +32,7 @@
 	let TTS_ENGINE = '';
 	let TTS_MODEL = '';
 	let TTS_VOICE = '';
+	let TTS_OPENAI_PARAMS = '';
 	let TTS_SPLIT_ON: TTS_RESPONSE_SPLIT = TTS_RESPONSE_SPLIT.PUNCTUATION;
 	let TTS_AZURE_SPEECH_REGION = '';
 	let TTS_AZURE_SPEECH_BASE_URL = '';
@@ -98,18 +100,28 @@
 	};
 
 	const updateConfigHandler = async () => {
+		let openaiParams = {};
+		try {
+			openaiParams = TTS_OPENAI_PARAMS ? JSON.parse(TTS_OPENAI_PARAMS) : {};
+			TTS_OPENAI_PARAMS = JSON.stringify(openaiParams, null, 2);
+		} catch (e) {
+			toast.error($i18n.t('Invalid JSON format for Parameters'));
+			return;
+		}
+
 		const res = await updateAudioConfig(localStorage.token, {
 			tts: {
 				OPENAI_API_BASE_URL: TTS_OPENAI_API_BASE_URL,
 				OPENAI_API_KEY: TTS_OPENAI_API_KEY,
+				OPENAI_PARAMS: openaiParams,
 				API_KEY: TTS_API_KEY,
 				ENGINE: TTS_ENGINE,
 				MODEL: TTS_MODEL,
 				VOICE: TTS_VOICE,
-				SPLIT_ON: TTS_SPLIT_ON,
 				AZURE_SPEECH_REGION: TTS_AZURE_SPEECH_REGION,
 				AZURE_SPEECH_BASE_URL: TTS_AZURE_SPEECH_BASE_URL,
-				AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT
+				AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT,
+				SPLIT_ON: TTS_SPLIT_ON
 			},
 			stt: {
 				OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
@@ -146,6 +158,7 @@
 			console.log(res);
 			TTS_OPENAI_API_BASE_URL = res.tts.OPENAI_API_BASE_URL;
 			TTS_OPENAI_API_KEY = res.tts.OPENAI_API_KEY;
+			TTS_OPENAI_PARAMS = JSON.stringify(res?.tts?.OPENAI_PARAMS ?? '', null, 2);
 			TTS_API_KEY = res.tts.API_KEY;
 
 			TTS_ENGINE = res.tts.ENGINE;
@@ -612,6 +625,22 @@
 								</div>
 							</div>
 						</div>
+
+						<div class="mt-2 mb-1 text-xs text-gray-400 dark:text-gray-500">
+							<div class="w-full">
+								<div class=" mb-1.5 text-xs font-medium">{$i18n.t('Additional Parameters')}</div>
+								<div class="flex w-full">
+									<div class="flex-1">
+										<Textarea
+											className="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+											bind:value={TTS_OPENAI_PARAMS}
+											placeholder={$i18n.t('Enter additional parameters in JSON format')}
+											minSize={100}
+										/>
+									</div>
+								</div>
+							</div>
+						</div>
 					{:else if TTS_ENGINE === 'elevenlabs'}
 						<div class=" flex gap-2">
 							<div class="w-full">

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

@@ -261,7 +261,7 @@
 								<div class="flex flex-col gap-1.5 mt-1.5">
 									{#each OPENAI_API_BASE_URLS as url, idx}
 										<OpenAIConnection
-											{url}
+											bind:url={OPENAI_API_BASE_URLS[idx]}
 											bind:key={OPENAI_API_KEYS[idx]}
 											bind:config={OPENAI_API_CONFIGS[idx]}
 											pipeline={pipelineUrls[url] ? true : false}
@@ -326,7 +326,7 @@
 								<div class="flex-1 flex flex-col gap-1.5 mt-1.5">
 									{#each OLLAMA_BASE_URLS as url, idx}
 										<OllamaConnection
-											{url}
+											bind:url={OLLAMA_BASE_URLS[idx]}
 											bind:config={OLLAMA_API_CONFIGS[idx]}
 											{idx}
 											onSubmit={() => {

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

@@ -10,7 +10,7 @@
 	import Cog6 from '$lib/components/icons/Cog6.svelte';
 	import Wrench from '$lib/components/icons/Wrench.svelte';
 	import ManageOllamaModal from './ManageOllamaModal.svelte';
-	import ArrowDownTray from '$lib/components/icons/ArrowDownTray.svelte';
+	import Download from '$lib/components/icons/Download.svelte';
 
 	export let onDelete = () => {};
 	export let onSubmit = () => {};
@@ -84,7 +84,7 @@
 				}}
 				type="button"
 			>
-				<ArrowDownTray />
+				<Download />
 			</button>
 		</Tooltip>
 

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

@@ -143,7 +143,7 @@
 				</div>
 			</button>
 
-			<hr class="border-gray-100 dark:border-gray-850 my-1" />
+			<hr class="border-gray-50 dark:border-gray-850 my-1" />
 
 			{#if $config?.features.enable_admin_export ?? true}
 				<div class="  flex w-full justify-between">

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

@@ -714,6 +714,21 @@
 									</div>
 								{/if}
 							{/if}
+
+							<div class="flex justify-between w-full mt-2">
+								<div class="self-center text-xs font-medium">
+									<Tooltip content={''} placement="top-start">
+										{$i18n.t('Parameters')}
+									</Tooltip>
+								</div>
+								<div class="">
+									<Textarea
+										bind:value={RAGConfig.DOCLING_PARAMETERS}
+										placeholder={$i18n.t('Enter additional parameters in JSON format')}
+										minSize={100}
+									/>
+								</div>
+							</div>
 						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'document_intelligence'}
 							<div class="my-0.5 flex gap-2 pr-2">
 								<input
@@ -1143,7 +1158,7 @@
 								<div class=" mb-2.5 py-0.5 w-full justify-between">
 									<Tooltip
 										content={$i18n.t(
-											'The Weight of BM25 Hybrid Search. 0 more lexical, 1 more semantic. Default 0.5'
+											'The Weight of BM25 Hybrid Search. 0 more semantic, 1 more lexical. Default 0.5'
 										)}
 										placement="top-start"
 										className="inline-tooltip"

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

@@ -293,7 +293,7 @@
 						<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
 
 						<div class="my-2 -mx-2">
-							<div class="px-3 py-2 bg-gray-50 dark:bg-gray-950 rounded-lg">
+							<div class="px-4 py-3 bg-gray-50 dark:bg-gray-950 rounded-3xl">
 								<AccessControl bind:accessControl />
 							</div>
 						</div>

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

@@ -34,7 +34,7 @@
 
 				<div class="w-full flex flex-col">
 					<div class="flex items-center gap-1">
-						<div class="shrink-0 line-clamp-1">
+						<div class=" line-clamp-1">
 							{model.name}
 						</div>
 					</div>

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

@@ -12,7 +12,8 @@
 		deleteAllModels,
 		getBaseModels,
 		toggleModelById,
-		updateModelById
+		updateModelById,
+		importModels
 	} from '$lib/apis/models';
 	import { copyToClipboard } from '$lib/utils';
 	import { page } from '$app/stores';
@@ -30,7 +31,7 @@
 	import Cog6 from '$lib/components/icons/Cog6.svelte';
 	import ConfigureModelsModal from './Models/ConfigureModelsModal.svelte';
 	import Wrench from '$lib/components/icons/Wrench.svelte';
-	import ArrowDownTray from '$lib/components/icons/ArrowDownTray.svelte';
+	import Download from '$lib/components/icons/Download.svelte';
 	import ManageModelsModal from './Models/ManageModelsModal.svelte';
 	import ModelMenu from '$lib/components/admin/Settings/Models/ModelMenu.svelte';
 	import EllipsisHorizontal from '$lib/components/icons/EllipsisHorizontal.svelte';
@@ -40,6 +41,7 @@
 
 	let shiftKey = false;
 
+	let modelsImportInProgress = false;
 	let importFiles;
 	let modelsImportInputElement: HTMLInputElement;
 
@@ -265,7 +267,7 @@
 								showManageModal = true;
 							}}
 						>
-							<ArrowDownTray />
+							<Download />
 						</button>
 					</Tooltip>
 
@@ -464,47 +466,41 @@
 						accept=".json"
 						hidden
 						on:change={() => {
-							console.log(importFiles);
+							if (importFiles.length > 0) {
-
+								const reader = new FileReader();
-							let reader = new FileReader();
 								reader.onload = async (event) => {
-								let savedModels = JSON.parse(event.target.result);
+									try {
-								console.log(savedModels);
+										const models = JSON.parse(String(event.target.result));
+										modelsImportInProgress = true;
+										const res = await importModels(localStorage.token, models);
+										modelsImportInProgress = false;
 
-								for (const model of savedModels) {
+										if (res) {
-									if (Object.keys(model).includes('base_model_id')) {
+											toast.success($i18n.t('Models imported successfully'));
-										if (model.base_model_id === null) {
+											await init();
-											upsertModelHandler(model);
-										}
 										} else {
-										if (model?.info ?? false) {
+											toast.error($i18n.t('Failed to import models'));
-											if (model.info.base_model_id === null) {
-												upsertModelHandler(model.info);
 										}
+									} catch (e) {
+										toast.error($i18n.t('Invalid JSON file'));
+										console.error(e);
 									}
-									}
-								}
-
-								await _models.set(
-									await getModels(
-										localStorage.token,
-										$config?.features?.enable_direct_connections &&
-											($settings?.directConnections ?? null)
-									)
-								);
-								init();
 								};
-
 								reader.readAsText(importFiles[0]);
+							}
 						}}
 					/>
 
 					<button
 						class="flex text-xs items-center space-x-1 px-3 py-1.5 rounded-xl bg-gray-50 hover:bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 dark:text-gray-200 transition"
+						disabled={modelsImportInProgress}
 						on:click={() => {
 							modelsImportInputElement.click();
 						}}
 					>
+						{#if modelsImportInProgress}
+							<Spinner className="size-3" />
+						{/if}
 						<div class=" self-center mr-2 font-medium line-clamp-1">
 							{$i18n.t('Import Presets')}
 						</div>