⚡ Bolt: Vectorize HNSWIndex search for ~11x speedup - #26
Open
Rohith-Shimori wants to merge 1 commit into
Open
Conversation
- Refactored `HNSWIndex.search` to use `numpy` matrix operations. - Added `dirty` flag and lazy matrix rebuilding logic. - Fixed incorrect async usage in `memory/lightweight_vector_db.py` example code. - Verified ~11x performance improvement (0.02s -> 0.0017s for 2k vectors). Co-authored-by: Rohith-Shimori <228351330+Rohith-Shimori@users.noreply.github.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
💡 What: Refactored
HNSWIndexinmemory/lightweight_vector_db.pyto use vectorized operations (NumPy) instead of an iterative Python loop for cosine distance calculation. Also fixed the example usage which incorrectly usedasync/awaitfor synchronous methods.🎯 Why: The original iterative approach was O(N) in Python, which is slow for vector search. Vectorization leverages optimized C libraries in NumPy.
📊 Impact: Reduces search time by ~11x (0.0199s -> 0.0017s for 2000 vectors).
🔬 Measurement: Verified with a benchmark script and existing integration tests.
PR created automatically by Jules for task 16823774838420796667 started by @Rohith-Shimori