Impact Score: 5/10
Open WebUI v0.6.7 — Release Notes & Engineering Impact
Source available — automated, not human-reviewed
Component: open-webui · Channel: stable. Automated analysis, not a compatibility certification. How this works.
Analysis updated: 2026-11-01.
⚡ Executive Summary (TL;DR)
Open WebUI v0.6.7. Source highlight: [0.6.7] - 2025-05-07
Who Does This Impact? (Role-Based Analysis)
💻 Software Engineers & Devs
Check the source notes against the package and APIs you use before upgrading.
📊 Product & Engineering Leads
Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.
⚙️ DevOps & Security
Verify the target version, runtime requirements and rollback procedure in the official documentation.
✨ New Features & Capabilities (3)
- 🌐 **Custom Azure TTS API URL Support Added**: You can now define a custom Azure Text-to-Speech endpoint—enabling 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.
🔧 Bug Fixes & Patches (6)
- 🧠 **Embedding with Ollama Proxy Endpoints Restored**: Fixed an issue where missing API config broke embedding for proxied Ollama models—ensuring 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 wasn’t 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.
📄 View Raw Release Notes (Original Developer Log)
## [0.6.7] - 2025-05-07
### Added
- 🌐 **Custom Azure TTS API URL Support Added**: You can now define a custom Azure Text-to-Speech endpoint—enabling 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.
### Fixed
- 🧠 **Embedding with Ollama Proxy Endpoints Restored**: Fixed an issue where missing API config broke embedding for proxied Ollama models—ensuring 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 wasn’t 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 OpenAI’s image generation, ensuring fully functional visual creation workflows.
- 🔎 **Tool Server Settings UI Privacy Restored**: Prevented restricted users from accessing tool server settings via search—restoring tight permissions control and safeguarding sensitive configurations.
- 🎧 **WebM Audio Transcription Now Supported**: Fixed an issue where WebM files failed during audio transcription—these formats are now fully supported, ensuring smoother voice note workflows and broader file compatibility.