Handling AttributeError
on structured citation prompt failure
#445
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Outdated suggestions cannot be applied.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.
Our
ParsingSettings.structured_citation_prompt
extracts a JSON that is supposed to contain the paper's title, DOI, and authors. However, last night I hit a new crash possibility:Casein Kinase 1δ Triggers Giant Ankyrin Expression
had its references on the first page.ParsingSettings.structured_citation_prompt
extracting a list of authors dicts (one dict per reference).list[dict]
was not accounted for inDocs.aadd
, it leads to anAttributeError
and crashes the indexing process.This PR handles the
AttributeError
possibility, and logs a warning if it happens