fix(search): filter stopwords from FTS5 queries and proximity reranking#271
Merged
mksglu merged 2 commits intomksglu:nextfrom Apr 14, 2026
Merged
Conversation
Domain-specific stopwords (update, test, fix, run, using, etc.) were defined in STOPWORDS but only used for vocabulary extraction. Search queries passed them through to FTS5, diluting BM25 ranking — e.g. "fix database connection" gave equal weight to "fix" which appears everywhere. Now filtered in sanitizeQuery, sanitizeTrigramQuery, and proximity reranking. Falls back to unfiltered terms when ALL query words are stopwords.
Owner
|
@sebastianbreguel I hope you'd tested on manually also. :) |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
update,test,fix,run,using, etc.) were defined inSTOPWORDSbut only used for vocabulary extraction — search queries passed them through to FTS5 unfiltered, diluting BM25 rankingsanitizeQuery(),sanitizeTrigramQuery(), and#applyProximityReranking()— meaningful terms drive ranking while stopwords are droppedExample
Query
"fix database connection"— before,"fix"got equal BM25 weight despite appearing in most chunks. Now only"database"and"connection"drive the ranking.Test plan