What's Changed
Optimizers
- Fix Evaluate call bug in GEPA by @LakshyAAAgrawal in #8647
- Lazy import of gepa package by @TomeHirata in #8638
LMs & Adapters
- Use pydantic's
ConfigDict
for config; filter litellm warnings by @kurtmckee in #8659 - Remove hardcoded model list from OpenAIProvider file by @chenmoneygithub in #8649
- Raise explicit error on not meeting reasoning model's requirement by @chenmoneygithub in #8650
- Flexible handling of
dspy.ToolCalls
parsing by @chenmoneygithub in #8563
Maintenance
- fix(evaluate): Raise TypeError on return_outputs in evaluate kwargs by @isaacbmiller in #8644
- Add type hints for UsageTracker by @TomeHirata in #8636
New Contributors
- @bogireddytejareddy made their first contribution in #8646
Full Changelog: 3.0.0...3.0.1