open-webui/open-webui v0.6.10

on GitHub

[0.6.10] - 2025-05-19

Added

• 🧩 Experimental Azure OpenAI Support: Instantly connect to Azure OpenAI endpoints by simply pasting your Azure OpenAI URL into the model connections—bringing flexible, enterprise-grade AI integration directly to your workflow.
• 💧 Watermark AI Responses: Easily add a visible watermark to AI-generated responses for clear content provenance and compliance with EU AI regulations—perfect for regulated environments and transparent communication.
• 🔍 Enhanced Search Experience with Dedicated Modal: Enjoy a modern, powerful search UI in a dedicated modal (open with Ctrl/Cmd + K) accessible from anywhere—quickly find chats, models, or content and boost your productivity.
• 🔲 "Toggle" Filter Type for Chat Input: Add interactive toggle filters (e.g. Web Search, Image, Code Interpreter) right into the chat input—giving you one-click control to activate features and simplifying the chat configuration process.
• 🧰 Granular Model Capabilities Editor: Define detailed capabilities and feature access for each AI model directly from the model editor—enabling tailored behavior, modular control, and a more customized AI environment for every team or use case.
• 🌐 Flexible Local and External Connection Support: Now you can designate any AI connection—whether OpenAI, Ollama, or others—as local or external, enabling seamless setup for on-premise, self-hosted, or cloud configurations and giving you maximum control and flexibility.
• 🗂️ Allowed File Extensions for RAG: Gain full control over your Retrieval-Augmented Generation (RAG) workflows by specifying exactly which file extensions are permitted for upload, improving security and relevance of indexed documents.
• 🔊 Enhanced Audio Transcription Logic: Experience smoother, more reliable audio transcription—very long audio files are now automatically split and processed in segments, preventing errors and ensuring even challenging files are transcribed seamlessly, all part of a broader stability upgrade for robust media workflows.
• 🦾 External Document Loader Support: Enhance knowledge base building by integrating documents using external loaders from a wide range of data sources, expanding what your AI can read and process.
• 📝 Preview Button for Code Artifacts: Instantly jump from an HTML code block to its associated artifacts page with the click of a new preview button—speeding up review and streamlining analysis.
• 🦻 Screen Reader Support for Response Messages: All chat responses are now fully compatible with screen readers, making the platform more inclusive and accessible for everyone.
• 🧑‍💼 Customizable Pending User Overlay: You can now tailor the overlay title and content shown to pending users, ensuring onboarding messaging is perfectly aligned with your organization’s tone and requirements.
• 🔐 Option to Disable LDAP Certificate Validation: You can now disable LDAP certificate validation for maximum flexibility in diverse IT environments—making integrations and troubleshooting much easier.
• 🎯 Workspace Search by Username or Email: Easily search across workspace pages using any username or email address, streamlining user and resource management.
• 🎨 High Contrast & Dark Mode Enhancements: Further improved placeholder, input, suggestion, toast, and model selector contrasts—including a dedicated placeholder dark mode—for more comfortable viewing in all lighting conditions.
• 🛡️ Refined Security for Pipelines & Model Uploads: Strengthened safeguards against path traversal vulnerabilities during uploads—ensuring your platform’s document and model management remains secure.
• 🌏 Major Localization Upgrades: Comprehensive translation updates and improvements across Korean, Bulgarian, Catalan, Japanese, Italian, Traditional Chinese, and Spanish—including more accurate AI terminology for clarity; your experience is now more natural, inclusive, and professional everywhere.
• 🦾 General Backend Stability & Security: Multiple backend improvements (including file upload, command navigation, and logging refactorings) deliver increased resilience, better error handling, and a more robust platform for all users.

Fixed

• ✅ Evaluation Feedback Endpoint Reliability: Addressed issues with feedback submission endpoints to ensure seamless user feedback collection on model responses.
• 🫰 Model List State Fixes: Resolved issues where model status toggles in the workspace page might inadvertently switch or confuse state, making the management of active/inactive models more dependable.
• ✍️ Admin Signup Logic: Admin self-signup experience and validation flow is smoother and more robust.
• 🔁 Signout Redirect Flow Improved: Logging out now redirects more reliably, reducing confusion and making session management seamless.

👏 Massive thanks to our incredible contributors for their hard work and dedication to making this release possible:
@kiettrinhgg, @hgaiser, @Lutherwaves, @tts-yo-nagase, @tanerim, @hwzhuhao, @Classic298, @tremlin, @loitragg, @Choyeyeong, @mini-777, @Ithanil, @hary777, @Davixk, @aleixdorca, @silentoplayz, @uryukikutani, @athoik, @cableman, @phpia, @TiancongLx, @dongfangzan

Sponsors 🙌

🚀 We'd like to extend a heartfelt thank you to our amazing sponsors for their generous support (Note: We've excluded private sponsors from this list. If you'd like to get featured here, feel free to reach out to us!)

Emerald

• n8n
  
  

@agency-agency, @roosi-gmbh, @Unsupervisedcom, @feddersen-group, @SRKConsulting, @mushmax, @rndmcnlly, @icanbwell, @blogic-cz, @Krambu-Travis, @GenieDev101, @PortlandKyGuy, @CubicleGangster, @GitDatamind, @TOWaB, @TheZigGroup, @Classic298, @comet-ml, @chAyubTahir