arize-phoenix-evals-v2.8.0
📦 arize-phoenixView on GitHub →
✨ 3 features🐛 1 fixes
Summary
Version 2.8.0 introduces a new correctness evaluator and enhances the LLM constructor by enabling sync/async client kwargs. It also fixes an issue related to newlines in built-in prompts.
✨ New Features
- Introduced a correctness evaluator.
- Enabled sync- and async- client kwargs for the LLM constructor.
- Added built-in tool selection correctness metric to evals.
🐛 Bug Fixes
- Removed newlines from built-in prompts.