[codex] Downgrade invalid extracted terms to strings#67
Merged
Conversation
justinjoy
force-pushed
the
codex/downgrade-invalid-extracted-terms
branch
from
f96c4a1 to
172c4a7
Compare
justinjoy
force-pushed
the
codex/downgrade-invalid-extracted-terms
branch
from
172c4a7 to
ec3ac43
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
kind="term"slots to strings instead of failing the whole source analysis.kind="string".Why
Local Ollama extraction marked a Korean company name as
kind="term", which failed parsing and caused source analysis to fail. The safer review behavior is to keep the invalid slot as aStringLit, preserve the valid compound slot, and surface the downgrade reason in the candidate note.Validation
python -m pytest tests/test_llm_schema.py tests/test_pipeline.py tests/test_fact_term_e2e.py -qpython -m pytest -q