v1.6.33
Released Jun 22, 2025.
This patch release improves the mobile experience and API documentation, and adds support for new models including Claude 3.5 (Bedrock), Gemini 2.0 Flash, and DeepSeek V3 and R1.
New features​
New model support in this version:
- Claude 3.5 (Bedrock)
- OpenAI o1 (Azure)
- OpenAI o1-mini (Azure)
- Gemini 2.0 Flash
- Gemini 2.0 Flash Thinking
- DeepSeek V3
- DeepSeek R1
- Qwen/Qwen2.5
- Qwen/Qwen2-VL
- Qwen/QwQ
Improvements​
User interface
- Collection management: Fixed collection count display when filtering through search, ensuring accurate result counts
- Error messaging: Enhanced error messages for administrators who lose access to private collections
- Card layouts: Improved username display in card views with cleaner text formatting and responsive design for mobile devices
- Mobile navigation: Better menu handling and responsive design for smaller screens
- Code rendering: Enhanced prompt code block rendering with syntax highlighting headers and improved formatting
API
- Documentation: Added comprehensive async API examples covering authentication, document management, and chat operations
- Code execution: Enhanced agent tool detection for Python and shell code blocks, expanding supported programming languages
Performance
- Enhanced PII (Personally Identifiable Information) detection and redaction with improved accuracy and expanded data type coverage for document processing workflows
- Improved arXiv document downloader reliability for consistent document processing
Bug fixes​
Stability
- Error handling: Improved UI reliability and stability
- Agent sessions: Enhanced error handling for agent chat sessions to reduce failure rates when restarting messages
User interface
- Fixed cursor navigation issues in code blocks for keyboard users
- Resolved mobile button list rendering errors affecting interface stability
- Improved error handling for collection sharing with clearer permission feedback
API
- Enhanced persistence of collection configuration settings, eliminating page refresh requirements
- Fixed non-streamed REST API response handling for better reliability
Feedback
- Submit and view feedback for this page
- Send feedback about Enterprise h2oGPTe to cloud-feedback@h2o.ai