OpenWebUI - Package Updates

[Package Updates]

[2.13.5]

• Update open-webui to 0.6.4
• Full Changelog
• RAG_TEMPLATE Display Issue Resolved: Fixed a formatting problem where the custom RAG_TEMPLATE wasn't correctly rendered in the interfaceensuring that custom retrieval prompts now appear exactly as intended for more reliable prompt engineering.
• Auto-Artifact Detection Toggle: Automatically detects artifacts in resultsbut now you can disable this behavior under advanced settings for full control.
• Widescreen Mode for Shared Chats: Shared link conversations now support widescreen layoutsperfect for presentations or easier review across wider displays.
• Reindex Knowledge Files on Demand: Admins can now trigger reindexing of all knowledge files after changing embeddingsensuring immediate alignment with new models for optimal RAG performance.
• OpenAPI YAML Format Support: External tools can now use YAML-format OpenAPI specsmaking integration simpler for developers familiar with YAML-based configurations.
• Message Content Copy Behavior: Copy action now excludes 'details' tagsstreamlining clipboard content when sharing or pasting summaries elsewhere.
• Sougou Web Search Integration: New search engine option addedenhancing global relevance and diversity of search sources for multilingual users.
• Frontend Web Loader Engine Configuration: Admins can now set preferred web loader engine for RAG workflows directly from the frontendoffering more control across setups.
• Multi-Model Chat Permission Control: Admins can manage access to multi-model chats per user groupallowing tighter governance in team environments.
• Persistent Configuration Can Be Disabled: New environment variable lets advanced users and hosts turn off persistent configsideal for volatile or stateless deployments.

[Package Updates]

[2.13.6]

• Update open-webui to 0.6.5
• Full Changelog
• Granular Voice Feature Permissions Per User Group: Admins can now separately manage access to Speech-to-Text (record voice), Text-to-Speech (read aloud), and Tool Calls for each user groupgiving teams tighter control over voice features and enhanced governance across roles.
• Toggle Voice Activity Detection (VAD) for Whisper STT: New environment variable lets you enable/disable VAD filtering with built-in Whisper speech-to-text, giving you flexibility to optimize for different audio quality and response accuracy levels.
• Copy Formatted Response Mode: You can now enable Copy Formatted in Settings > Interface to copy AI responses exactly as styled (with rich formatting, links, and structure preserved), making it faster and cleaner to paste into documents, emails, or reports.
• Backend Stability and Performance Enhancements: General backend refactoring improves system resilience, consistency, and overall reliabilityoffering smoother performance across workflows whether chatting, generating media, or using external tools.
• Translation Refinements Across Multiple Languages: Updated translations deliver smoother language localization, clearer labels, and improved international usability throughout the UIensuring a better experience for non-English speakers.
• LDAP Login Reliability Restored: Resolved a critical issue where some LDAP setups failed due to attribute parsingensuring consistent, secure, and seamless user authentication across enterprise deployments.
• Image Generation in Temporary Chats Now Works Properly: Fixed a bug where image outputs werent generated during temporary chatsvisual content can now be used reliably in all chat modes without interruptions.

[Package Updates]

[2.13.7]

• Update ollama to 0.6.6
• Full Changelog
• New, faster model downloading: OLLAMA_EXPERIMENT=client2 ollama serve will run Ollama using a new downloader with improved performance and reliability when running ollama pull. Please share feedback here!
• Fixed memory leak issues when running Gemma 3, Mistral Small 3.1 and other models on Ollama
• Improved performance of ollama create when importing models from Safetensors
• Ollama will now allow tool function parameters with either a single type or an array of types by @rozgo
• Fixed certain out of memory issues from not reserving enough memory at startup
• Fix nondeterministic model unload order by @IreGaddr
• Include the items and $defs fields to properly handle array types in the API by @sheffler
• OpenAI-Beta headers are now included in the CORS safelist by @drifkin
• Fixed issue where model tensor data would be corrupted when importing models from Safetensors

[Package Updates]

[2.13.8]

• Update ollama to 0.6.7

[Package Updates]

[2.13.9]

• Update ollama to 0.6.8

[Package Updates]

[2.13.10]

• Update open-webui to 0.6.6
• Full Changelog
• AI-Enhanced Notes (With Audio Transcription): Effortlessly create notes, attach meeting or voice audio, and let the AI instantly enhance, summarize, or refine your notes using audio transcriptionsmaking your documentation smarter, cleaner, and more insightful with minimal effort.
• Meeting Audio Recording & Import: Seamlessly record audio from your meetings or capture screen audio and attach it to your notesmaking it easier to revisit, annotate, and extract insights from important discussions.
• Import Markdown Notes Effortlessly: Bring your existing knowledge library into Open WebUI by importing your Markdown notes, so you can leverage all advanced note management and AI features right away.
• Notes Permissions by User Group: Fine-tune access and editing rights for notes based on user roles or groups, so you can delegate writing or restrict sensitive information as needed.
• OneDrive & SharePoint Integration: Keep your content in sync by connecting notes and files directly with OneDrive or SharePointunlocking fast enterprise import/export and seamless collaboration with your existing workflows.
• Tighter HTML Token Security: HTML rendering is now restricted to admin-uploaded tokens only, reducing any risk of XSS and keeping your data safe.
• Refined HTML Security and Token Handling: Further hardened how HTML tokens and content are handled, guaranteeing even stronger resistance to security vulnerabilities and attacks.
• Correct Model Usage with Ollama Proxy Prefixes: Enhanced model reference handling so proxied models in Ollama always download and run correctlyeven when using custom prefixes.
• Video File Upload Handling: Prevented video files from being misclassified as text, fixing bugs with uploads and ensuring media files work as expected.
• No More Dependent WebSocket Sequential Delays: Streamlined WebSocket operation to prevent delays and maintain snappy real-time collaboration, especially in multi-user environments.

[Package Updates]

[2.13.11]

• Update open-webui to 0.6.7
• Full Changelog
• Custom Azure TTS API URL Support Added: You can now define a custom Azure Text-to-Speech endpointenabling flexibility for enterprise deployments and regional compliance.
• TOOL_SERVER_CONNECTIONS Environment Variable Suppor: Easily configure and deploy tool servers via environment variables, streamlining setup and enabling faster enterprise provisioning.
• Enhanced OAuth Group Handling as String or List: OAuth group data can now be passed as either a list or a comma-separated string, improving compatibility with varied identity provider formats and reducing onboarding friction.
• Embedding with Ollama Proxy Endpoints Restored: Fixed an issue where missing API config broke embedding for proxied Ollama modelsensuring consistent performance and compatibility.
• OIDC OAuth Login Issue Resolved: Users can once again sign in seamlessly using OpenID Connect-based OAuth, eliminating login interruptions and improving reliability.
• Notes Feature Access Fixed for Non-Admins: Fixed an issue preventing non-admin users from accessing the Notes feature, restoring full cross-role collaboration capabilities.
• Tika Loader Image Extraction Problem Resolved: Ensured TikaLoader now processes 'extract_images' parameter correctly, restoring complete file extraction functionality in document workflows.
• Automatic1111 Image Model Setting Applied Properly: Fixed an issue where switching to a specific image model via the UI wasnt reflected in generation, re-enabling full visual creativity control.
• Multiple XML Tags in Messages Now Parsed Correctly: Fixed parsing issues when messages included multiple XML-style tags, ensuring clean and unbroken rendering of rich content in chats.
• OpenAI Image Generation Issues Resolved: Resolved broken image output when using OpenAIs image generation, ensuring fully functional visual creation workflows.

[Package Updates]

[2.13.12]

• Update open-webui to 0.6.9
• Full Changelog
• Edit Attached Images/Files in Messages: You can now easily edit your sent messages by removing attached filesstreamlining document management, correcting mistakes on the fly, and keeping your chats clutter-free.
• Clear Alerts for Private Task Models: When interacting with private task models, the UI now clearly alerts youmaking it easier to understand resource availability and access, reducing confusion during workflow setup.
• Confirm Dialog Focus Trap Reliability: The focus now stays correctly within confirmation dialogs, ensuring keyboard navigation and accessibility is seamless and preventing accidental operationsespecially helpful during critical or rapid workflows.
• Temporary Chat Admin Controls & Session Cleanliness: Admins are now able to properly enable temporary chat mode without errors, and previous session prompts or tool selections no longer carry overdelivering a fresh, predictable, and consistent temporary chat experience every time.
• External Reranker Integration Functionality Restored: External reranker integrations now work correctly, allowing you to fully leverage advanced ranking services for sharper, more relevant search results in your RAG and knowledge base workflows.
• External Reranker Support for Knowledge Base Search: Supercharge your Retrieval-Augmented Generation (RAG) workflows with the new External Reranker integration; easily plug in advanced reranking services via the UI to deliver sharper and more relevant search results, accelerating research and insight discovery.
• Unstylized PDF Export Option (Reduced File Size): When exporting chat transcripts or documents, you can now choose an unstylized PDF export for snappier downloads, minimal file size, and clean data archivingperfect for large-scale storage or sharing.
• Vazirmatn Font for Persian & Arabic: Arabic and Persian users will now see their text beautifully rendered with the specialized Vazirmatn font for an improved localized reading experience.
• SharePoint Tenant ID Support for OneDrive: You can now specify a SharePoint tenant ID in OneDrive settings for seamless authentication and granular enterprise integration.
• Refresh OAuth Profile Picture: Your OAuth profile picture now updates in real-time, ensuring your presence and avatar always match your latest identity across integrated platforms.

[Package Updates]

[2.14.0]

• Update ollama to 0.7.0

[Package Updates]

[2.14.1]

• Update open-webui to 0.6.10
• Full Changelog
• Experimental Azure OpenAI Support: Instantly connect to Azure OpenAI endpoints by simply pasting your Azure OpenAI URL into the model connectionsbringing 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 regulationsperfect 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 anywherequickly 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 inputgiving 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 editorenabling 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 connectionwhether OpenAI, Ollama, or othersas 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 transcriptionvery 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 buttonspeeding up review and streamlining analysis.

[Package Updates]

[2.14.2]

• Update ollama to 0.7.1

[Package Updates]

[2.14.3]

• Update open-webui to 0.6.11
• Full Changelog
• Ollama Model Status Indicator in Model Selector: Instantly see which Ollama models are currently loaded with a clear indicator in the model selector, helping you stay organized and optimize local model usage.
• Unload Ollama Model Directly from Model Selector: Easily release memory and resources by unloading any loaded Ollama model right in the model selectorstreamline hardware management without switching pages.
• User-Configurable Speech-to-Text Language Setting: Improve transcription accuracy by letting individual users explicitly set their preferred STT language in their settingsideal for multilingual teams and clear audio capture.
• Granular Audio Playback Speed Control: Instead of just presets, you can now choose granular audio speed using a numeric input, giving you complete control over playback pace in transcriptions and media reviews.
• GZip, Brotli, ZStd Compression Middleware: Enjoy significantly faster page loads and reduced bandwidth usage with new server-side compressiongiving users a snappier, more efficient experience.
• Configurable Weight for BM25 in Hybrid Search: Fine-tune search relevance by adjusting the weight for BM25 inside hybrid search from the UI, letting you tailor knowledge search results to your workflow.
• Bypass File Creation with CTRL + SHIFT + V: When Paste Large Text as File is enabled, use CTRL + SHIFT + V to skip the file creation dialog and instantly upload text as a fileperfect for rapid document prep.
• Bypass Web Loader in Web Search: Choose to bypass web content loading and use snippets directly in web search for faster, more reliable results when page loads are slow or blocked.
• Environment Variable: WEBUI_AUTH_TRUSTED_GROUPS_HEADER: Now sync and manage user groups directly via trusted HTTP header, unlocking smoother single sign-on and identity integrations for organizations.
• Workspace Models Visibility Controls: You can now hide workspace-level models from both the model selector and shared environmentskeep your team focused and reduce clutter from rarely-used endpoints.

[Package Updates]

[2.14.4]

• Write webui url directly into the DB, otherwise errors will happen

[ApplegateR]

@Package-Updates this one broke our open web ui.. but before update it work fine.

[nebulon]

The package is revoked until fixed. Please your app instance to the version prior to the update if yours already got auto-updated.

[ApplegateR]

@nebulon Thank you. No, it is not set to auto-update. I saw that an update was available and applied it, but it caused a crash. James found the issue and will be pushing an update soon. Looking forward to it!

[Package Updates]

[2.14.5]

• Update open-webui to 0.6.12
• Full Changelog
• Custom Advanced Model Parameters: You can now add your own tailor-made advanced parameters to any model, empowering you to fine-tune behavior and unlock greater flexibility beyond just the built-in optionsaccelerate your experimentation.
• Datalab Marker API Content Extraction Support: Seamlessly extract content from files and documents using the Datalab Marker API directly in your workflows, enabling more robust structured data extraction for RAG and document processing with just a simple engine switch in the UI.
• Parallelized Base Model Fetching: Experience noticeably faster startup and model refresh timesbase model data now loads in parallel, drastically shortening delays in busy or large-scale deployments.
• Efficient Function Loading and Caching: Functions are now only reloaded if their content changes, preventing unnecessary duplicate loads, saving bandwidth, and boosting performance.
• Localization & Translation Enhancements: Improved and expanded Simplified, Traditional Chinese, and Russian translations, providing smoother, more accurate, and context-aware experiences for global users.
• Stable Message Input Box: Fixed an issue where the message input box would shift unexpectedly (especially on mobile or with screen reader support), ensuring a smooth and reliable typing experience for every user.
• Reliable Read Aloud (Text-to-Speech): Read aloud now works seamlessly across messages, so users depending on TTS for accessibility or multitasking will experience uninterrupted and clear voice playback.
• Image Preview and Download Restored: Fixed problems with image preview and downloads, ensuring frictionless creation, previewing, and downloading of images in your chatsno more interruptions in creative or documentation workflows.
• Improved Mobile Styling for Workspace Capabilities: Capabilities management is now readable and easy-to-use even on mobile devices, empowering admins and users to manage access quickly on the go.
• /api/v1/retrieval/query/collection Endpoint Reliability: Queries to retrieval collections now return the expected results, bolstering the reliability of your knowledge workflows and citation-ready responses.

[firmansi]

@Package-Updates Still not seen in package update OpenWebUI

[Package Updates]

[2.14.6]

• Re-release with shell escaping fix to start.sh

[Package Updates]

[2.14.7]

• Update open-webui to 0.6.13
• Full Changelog
• Azure OpenAI Embedding Support: You can now select Azure OpenAI endpoints for text embeddings, unlocking seamless integration with enterprise-scale Azure AI for powerful RAG and knowledge workflowsno more workarounds, connect and scale effortlessly.
• Smarter Custom Parameter Handling: Instantly enjoy more flexible model setupany JSON pasted into custom parameter fields is now parsed automatically, so you can define rich, nested parameters without tedious manual adjustment. This streamlines advanced configuration for all models and accelerates experimentation.
• General Backend Refactoring: Significant backend improvements deliver a cleaner codebase for better maintainability, faster performance, and even greater platform reliabilitymaking all your workflows run more smoothly.
• Localization Upgrades: Experience highly improved user interface translations and clarity in Simplified, Traditional Chinese, Korean, and Finnish, offering a more natural, accurate, and accessible experience for global users.
• Robust Message Handling on Chat Load: Fixed an issue where chat pages could fail to load if a referenced message was missing or undefined; now, chats always load smoothly and missing IDs no longer disrupt your workflow.
• Correct Prompt Access Control: Ensured that the prompt access controls register properly, restoring reliable permissioning and safeguarding your prompt workflows.
• Open WebUI-Specific Params No Longer Sent to Models: Fixed a bug that sent internal WebUI parameters to APIs, ensuring only intended model options are transmittedrestoring predictable, error-free model operation.
• Refined Memory Error Handling: Enhanced stability during memory-related operations, so even uncommon memory errors are gracefully managed without disrupting your sessionresulting in a more reliable, worry-free experience.