Handle zero vectors in quantized codecs to prevent crashes during merge and search#16100
Open
iprithv wants to merge 2 commits into
Open
Handle zero vectors in quantized codecs to prevent crashes during merge and search#16100iprithv wants to merge 2 commits into
iprithv wants to merge 2 commits into
Conversation
This fixes division-by-zero and assertion failures when zero vectors are indexed with COSINE similarity in scalar-quantized codecs: - Add magnitude > 0 guard in normalizeVectors() to skip division for zero vectors - Add divisor > 0 guard in addValue() to avoid adding NaN to dimensionSums - Pass throwOnZero=false to all l2normalize() calls in quantized codec paths - Relax isUnitVector assertions to allow zero vectors in scalarQuantize() - Add test verifying merge + search works with zero vectors in quantized format Fixes apache#15540
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Quantized vector codecs (Lucene104ScalarQuantizedVectorsFormat) crash on zero vectors with COSINE similarity, fixed it!