Closed NumberChiffre closed 2 months ago
Attention: Patch coverage is 98.66667%
with 1 line
in your changes missing coverage. Please review.
Project coverage is 94.25%. Comparing base (
f11e9f2
) to head (20bb681
). Report is 12 commits behind head on main.
Files with missing lines | Patch % | Lines |
---|---|---|
nano_graphrag/entity_extraction/extract.py | 96.77% | 1 Missing :warning: |
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
Description
DSPy has typed predictors/CoT that uses pydantic models as schema for their return types, however this is not as reliable as non-typed like CoT (because if something goes wrong with the formatting, you can catch it and resolve it yourself, often times some JSON parsing error or response from
outputfield
ends up in theprediction.rationale
of CoT). Therefore, this PR is here to resolve these formatting issues with DSPy once and for all (hopefully) and run MIPROv2 to generate optimal prompt instructions for entity relationship extraction.Misc: