Optimize s3 vector database performance and benchmark #823
Conversation
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
Co-authored-by: oeway007 <oeway007@gmail.com>
Integrates Zarr for chunked, compressed vector storage in S3Vector. This improves performance and reduces storage costs. Includes a new benchmark suite to compare Zarr with existing S3Vector implementations and PgVector. Co-authored-by: oeway007 <oeway007@gmail.com>
|
Cursor Agent can help with this pull request. Just |
github-actions
bot
added
the
documentation
Replaces Parquet shards with Zarr for improved performance and cost savings. Co-authored-by: oeway007 <oeway007@gmail.com>
…rmance-and-benchmark-7fe5
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Outdated suggestions cannot be applied.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.
Implement optimized S3Vector and Zarr-based vector storage engines with comprehensive benchmarks.
This PR addresses significant performance bottlenecks in the existing S3-backed vector database, including slow search, sequential shard loading, and inefficient HNSW, aiming for competitive performance with pgvector at scale.