V0.12.6
Version 0.12.6
This release includes several enhancements and new features aimed at improving the functionality and user experience of our software. Key updates include refinements in agent setup, benchmarking tools, and significant improvements in our logging and UI components.
New Features
- Introduced a new HTML endpoint for rendering the main experiment view page, enhancing user interaction with experiment data. (47c4be4) (Eric Ma)
- Added a main prompt comparison page endpoint to facilitate easier access and comparison of different prompts. (be39a28) (Eric Ma)
- Implemented detailed run metadata tracking for AgentBot, enhancing monitoring and debugging capabilities. (98c9694) (Eric Ma)
- Added run metadata tracking for StructuredBot to monitor validation attempts and outcomes, improving reliability and performance insights. (5f57e63) (Eric Ma)
- Enhanced QueryBot with run metadata tracking to provide detailed insights into query performance and efficiency. (3849731) (Eric Ma)
- Introduced run metadata tracking for SimpleBot, allowing detailed monitoring of call metrics and tool usage. (d6418dc) (Eric Ma)
- Added new tools and metrics for agent performance measurement in agents.py, improving the setup and benchmarking process. (2a49bde) (Eric Ma)
- Updated agentbot tutorial to include the use of the gpt-4.1 model and introduced a section on using the planner bot. (d1f48ab) (Eric Ma)
- Added column visibility controls for metrics in the experiment details view, enhancing user interface flexibility. (0b49f33) (Eric Ma)
Bug Fixes
- No specific bug fixes were noted in this release.
Deprecations
- No deprecations were introduced in this release.