FTS: Hybrid search query pipeline #42885
Open
+1,313
−113
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Outdated suggestions cannot be applied.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.
Description
This PR adds Full text search and hybrid search support.
HybridSearchDocumentQueryExecutionContext
HybridSearch
HybridSearchQueryInfo
Design doc
FTS queries supported now:
SELECT TOP 50 c.id, c.abstract, c.title FROM c WHERE FullTextContains(c.abstract, 'quantum')
SELECT TOP 50 c.id, c.abstract, c.title FROM c WHERE FullTextContainsAll(c.abstract, 'quantum', 'theory')
SELECT TOP 50 c.id, c.abstract, c.title FROM c WHERE FullTextContainsAny(c.abstract, 'quantum', 'theory')
SELECT TOP 50 c.id, c.abstract, c.title FROM c ORDER BY RANK FullTextScore(c.abstract, ['quantum', 'theory'])
SELECT TOP 50 c.id, c.abstract, c.title FROM c ORDER BY RANK RRF(FullTextScore(c.abstract, ['quantum', 'theory']), FullTextScore(c.abstract, ['model']))
SELECT TOP 50 c.id, c.abstract, c.title FROM c ORDER BY RANK RRF(FullTextScore(c.abstract, ['quantum', 'theory']), FullTextScore(c.abstract, ['model']), VectorDistance(c.Embedding, [%s]))",vector)
Hybrid Search queries guide
All SDK Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines