fix(pgvector): order retrieval by distance operator#3370
Merged
julian-risch merged 2 commits intoJun 1, 2026
Conversation
Contributor
Coverage report (pgvector)Click to see where and how coverage changed
This report was generated by python-coverage-comment-action |
||||||||||||||||||||||||
julian-risch
approved these changes
Jun 1, 2026
Member
julian-risch
left a comment
There was a problem hiding this comment.
Looks good to me and I ran integration tests locally. Thank you for this contribution @2830500285 !
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pgvector currently computes Haystack-facing scores correctly, but then orders embedding retrieval by the
scorealias. For cosine similarity that turns the pgvector distance operator into an expression and orders it descending, so HNSW/IVFFlat indexes cannot satisfy theORDER BYshape pgvector expects.This keeps the selected
scorecolumn unchanged, while sorting by the raw pgvector distance operator in ascending order. The result ordering stays the same for cosine similarity and inner product,l2_distanceremains distance-ascending, and Postgres can use the vector index for the retrieval sort.Fixes #2199