Repository navigation
Tags
Tags
Revert ChainOfThought to pre-dspy.Reasoning (stanfordnlp#8822) behavi… …or (stanfordnlp#9258) * Revert ChainOfThought rationale field handling * Update reasoning tests for legacy ChainOfThought
Fix JSON parsing: Removing initial regex extraction. (stanfordnlp#9182) * Removing initial regex extraction. Only failback regex matching to find JSON. Potentially could be removed all together. * Removed whitespace on blank line. --------- Co-authored-by: Benjamin Grap <benjamin.grap@crowdstrike.com>
fix(dspy): Example.toDict() fails to serialize dspy.History objects (s… …tanfordnlp#9047) * Initial plan * Fix Example.toDict() to serialize dspy.History objects properly Co-authored-by: TomeHirata <33407409+TomeHirata@users.noreply.github.com> * Consolidate History tests into existing test_evaluate.py Co-authored-by: TomeHirata <33407409+TomeHirata@users.noreply.github.com> * Refactor: move toDict() call to merge_dicts for cleaner code Co-authored-by: TomeHirata <33407409+TomeHirata@users.noreply.github.com> * Use isinstance(BaseModel) instead of hasattr for Pydantic check Co-authored-by: TomeHirata <33407409+TomeHirata@users.noreply.github.com> * Simplify _prepare_results_output to always use toDict() Co-authored-by: TomeHirata <33407409+TomeHirata@users.noreply.github.com> * Remove unnecessary try/except for pydantic import since it's a core dependency Co-authored-by: TomeHirata <33407409+TomeHirata@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: TomeHirata <33407409+TomeHirata@users.noreply.github.com>
PreviousNext