3.0.1

stanfordnlp/dspy3.0.1Aug 14, 2025by okhat

AI Summary

Maintenance release fixing GEPA evaluation calls, lazy importing of gepa, and removing hardcoded model lists from OpenAIProvider.

Key Highlights

Fixed Evaluate call bug in GEPA.
Lazy import of gepa package.
Removed hardcoded model list from OpenAIProvider.
Flexible handling of dspy.ToolCalls parsing.

New Features

Lazy import gepa.
Removed hardcoded model list.
Flexible ToolCalls parsing.

Full Release Notes

## What's Changed

Optimizers
* Fix Evaluate call bug in GEPA by @LakshyAAAgrawal in https://github.com/stanfordnlp/dspy/pull/8647
* Lazy import of gepa package by @TomeHirata in https://github.com/stanfordnlp/dspy/pull/8638

LMs & Adapters
* Use pydantic's `ConfigDict` for config; filter litellm warnings by @kurtmckee in https://github.com/stanfordnlp/dspy/pull/8659
* Remove hardcoded model list from OpenAIProvider file by @chenmoneygithub in https://github.com/stanfordnlp/dspy/pull/8649
* Raise explicit error on not meeting reasoning model's requirement  by @chenmoneygithub in https://github.com/stanfordnlp/dspy/pull/8650
* Flexible handling of `dspy.ToolCalls` parsing by @chenmoneygithub in https://github.com/stanfordnlp/dspy/pull/8563

Maintenance
* fix(evaluate): Raise TypeError on return_outputs in evaluate kwargs by @isaacbmiller in https://github.com/stanfordnlp/dspy/pull/8644
* Add type hints for UsageTracker by @TomeHirata in https://github.com/stanfordnlp/dspy/pull/8636


## New Contributors
* @bogireddytejareddy made their first contribution in https://github.com/stanfordnlp/dspy/pull/8646

**Full Changelog**: https://github.com/stanfordnlp/dspy/compare/3.0.0...3.0.1