Repository navigation
feat: Reuse ranking embeddings when selecting representatives, refresh benchmarks - #91
Merged
Merged
Conversation
…h benchmarks and bump to 0.5.0 Representative selection encoded its top candidates again after ranking. The ranking now returns the embeddings in ranked order (index vectors in self mode, the query embeddings in cross mode) and diversification reuses them. Benchmarks are rerun on a MacBook Pro (Apple M5, 48 GB RAM) to reflect #89 and #90, and the version is bumped to 0.5.0 for their breaking changes.
Codecov Report✅ All modified and coverable lines are covered by tests.
🚀 New features to boost your workflow:
|
stephantul
approved these changes
Sep 30, 2026
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
find_representativeandself_find_representativeencoded their top candidates a second time, even though those embeddings were already computed while ranking. The ranking now returns them and diversification reuses them. This barely matters with our default model but does have a big effect when you use a slower encoder.I also reran the benchmarks.