jasonz-lanceandClaude Opus 5
e907ff8c0e
The background prefetch added in ecf44fed topped up its queue by walking
raw plan positions ahead of the read watermark, bounded by
`2 * max_shuffle_distance`, until it had found `prefetch_depth` distinct
blocks not already loaded or in flight.
That bound is a count of *ranks*, not of blocks, so with the default
`max_shuffle_distance` of 16384 the scan window covers 32768 ranks but
only ~8 distinct blocks -- fewer than the prefetch depth of 16. The loop
could therefore never satisfy its exit condition and ran all 32768
iterations, each one a Python-level scalar extraction out of a numpy
array, on *every* `__getitems__` call. Prefetching upcoming blocks
regressed 2-phase read throughput by ~5.6x (107 -> 19 MB/s on a local
NVMe benchmark).
Precompute the distinct blocks in first-needed order once, in __init__,
and have prefetch walk that instead: one step per block rather than one
per rank, so the scan is bounded by the block count (~24 here) and exits
as soon as the queue is full. Blocks whose last plan position is already
behind the watermark are skipped -- they can never be needed again.
Restores local-NVMe 2-phase read throughput to 78.7 MB/s.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The Multimodal AI Lakehouse
How to Install ✦ Detailed Documentation ✦ Tutorials and Recipes ✦ Contributors
The ultimate multimodal data platform for AI/ML applications.
LanceDB is designed for fast, scalable, and production-ready vector search. It is built on top of the Lance columnar format. You can store, index, and search over petabytes of multimodal data and vectors with ease. LanceDB is a central location where developers can build, train and analyze their AI workloads.
Demo: Multimodal Search by Keyword, Vector or with SQL
Star LanceDB to get updates!
⭐ Click here ⭐ to see how fast we're growing!
Key Features:
- Fast Vector Search: Search billions of vectors in milliseconds with state-of-the-art indexing.
- Comprehensive Search: Support for vector similarity search, full-text search and SQL.
- Multimodal Support: Store, query and filter vectors, metadata and multimodal data (text, images, videos, point clouds, and more).
- Advanced Features: Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure. GPU support in building vector index.
Products:
- Open Source & Local: 100% open source, runs locally or in your cloud. No vendor lock-in.
- Cloud and Enterprise: Production-scale vector search with no servers to manage. Complete data sovereignty and security.
Ecosystem:
- Columnar Storage: Built on the Lance columnar format for efficient storage and analytics.
- Seamless Integration: Python, Node.js, Rust, and REST APIs for easy integration. Native Python and Javascript/Typescript support.
- Rich Ecosystem: Integrations with LangChain 🦜️🔗, LlamaIndex 🦙, Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
How to Install:
Follow the Quickstart doc to set up LanceDB locally.
API & SDK: We also support Python, Typescript and Rust SDKs
| Interface | Documentation |
|---|---|
| Python SDK | https://lancedb.github.io/lancedb/python/python/ |
| Typescript SDK | https://lancedb.github.io/lancedb/js/globals/ |
| Rust SDK | https://docs.rs/lancedb/latest/lancedb/index.html |
| REST API | https://docs.lancedb.com/api-reference/rest |
Join Us and Contribute
We welcome contributions from everyone! Whether you're a developer, researcher, or just someone who wants to help out.
If you have any suggestions or feature requests, please feel free to open an issue on GitHub or discuss it on our Discord server.
Check out the GitHub Issues if you would like to work on the features that are planned for the future. If you have any suggestions or feature requests, please feel free to open an issue on GitHub.
Contributors
Stay in Touch With Us