fix: warn on empty/whitespace content in InMemoryDocumentStore.write_documents#11542
Closed
michaelxer wants to merge 1 commit into
Closed
fix: warn on empty/whitespace content in InMemoryDocumentStore.write_documents#11542michaelxer wants to merge 1 commit into
michaelxer wants to merge 1 commit into
Conversation
…documents Documents with empty or whitespace-only content are stored but never retrieved meaningfully by BM25 retrieval, since they produce zero tokens. Add a warning log when such documents are written to help users identify the issue early. Fixes deepset-ai#11541
|
@michaelxer is attempting to deploy a commit to the deepset Team on Vercel. A member of the Team first needs to authorize it. |
|
|
Contributor
|
See #11541 |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Related Issues
Proposed Changes
InMemoryDocumentStore.write_documents()now logs a warning when a document has empty or whitespace-only content. Previously, these documents were silently stored and would appear in BM25 retrieval results with meaningless scores, since they produce zero tokens during BM25 tokenization.The warning is non-breaking — documents are still stored as before. This helps users identify the issue early without changing existing behavior.
How did you test it?
hatch run test:unit test/document_stores/test_in_memory.py— 148 passed, 4 skippedtest_write_documents_warns_on_empty_contentthat verifies the warning is logged for empty and whitespace-only content, and not logged for valid contentNotes for the reviewer
The warning is logged at
WARNINGlevel using the existingloggerinstance. Documents are still stored regardless of content — this is intentional to avoid breaking existing pipelines that might use metadata-only documents.The async path (
write_documents_async) delegates towrite_documents, so it's covered automatically.