stanfordnlp/dspy 2.6.12

on GitHub

What's Changed

• dspy.MIPROv2: Fix error handling and add tests for eval_candidate_program by @TomeHirata in #7936

• dspy.Refine and dspy.BestOfN: Adds Improved Error Handling, Documentation, and Tests by @cezarc1 in #7926

• Simplify dspy.LM by @chenmoneygithub in #7940

• Fix unnecessary mlflow calls by @TomeHirata in #7942

• Remove upper bound on datasets version by @shermansiu in #7933

• Reorder dependencies by @TomeHirata in #7946

• Add callback_metadata to evaluate by @TomeHirata in #7952

New Contributors

• @shermansiu made their first contribution in #7933

Full Changelog: 2.6.11...2.6.12