Repository navigation
Conversation
EmbeddingGemma vectors alone put the right Drive document first in 0.80 of 25 queries against e5-small's 0.48 and drive's fused search's 0.68, at 2 h 28 min of embedding against 9 min. rerank.mjs takes PASSAGES_OVERRIDE for a document edited after its vectors were made. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
leemour
changed the title
Brute-force search reading vectors from SQLite in pages of 5,000: 33 ms, 271 ms, 821 ms — linear, about 2.7 ms per 1,000 vectors. Answers whether one embeddings table slows search at volume. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Completes the vectors-only comparison on performance/search/local-documents (owner decision NEED-1002 A).
One run, 25 queries; fusion of EmbeddingGemma with the word list not measured. Per-query rows stay in cli-private.
🤖 Generated with Claude Code