chore: format fix#4
Merged
Merged
Conversation
mterenzi
added a commit
to mterenzi/cocoindex-code-dart
that referenced
this pull request
May 8, 2026
Pure vector search ranked short identifier queries poorly — the literal- match chunk got buried behind chunks that "look semantically similar" (searching `CvoFile` returned the defining `class CvoFile` at rank cocoindex-io#8). Pair vec0 KNN with an FTS5 keyword index, mirror it from vec0 after each indexing pass, and merge ranks via Reciprocal Rank Fusion so neither retriever's score scale dominates. FTS rows are inserted into the score map first so keyword matches win stable-sort tie-breaks against vec-only chunks at the same rank — the right call for identifier queries. On real codebases the defining chunk now consistently lands in the top 3 (was cocoindex-io#4-cocoindex-io#8 before). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.