Contributing¶
Development Setup¶
Linting¶
Testing¶
Adding to the Golden Dataset¶
- Add examples to
raghelm/eval/golden_dataset.json - Use unique IDs matching the pattern
source_NNN - Use valid categories:
factual_lookup,comparison,synthesis,temporal,contradictory - Run validation:
uv run python -c "from raghelm.eval.golden_dataset import *; d=load_golden_dataset('raghelm/eval/golden_dataset.json'); print(validate_dataset(d))" - Run the test suite to ensure nothing breaks