XYZhan
4d756066ef
The MemWAL LSM scanner resolved one index and capped SSTable exclusion at that index's catch-up watermark. A query can rely on more than one: a hybrid search reads both a vector and a full-text index, and either may lag the other. Gating on whichever was resolved first dropped SSTables holding rows the other index had not yet indexed, and that arm silently returned fewer rows. exclusion_watermarks now takes every index the query relies on and retains to the lowest of their watermarks, and the resolver collects the vector and full-text arms together rather than returning at the first match. A plain scan still uses the compaction watermark alone. Both remaining behaviours are unchanged: an index with no catch-up entry contributes no cap, and a caught-up index falls back to the compaction watermark. Two parts of the safe-retirement query behaviour are not here because they depend on Lance changes this repository cannot yet see -- lancedb pins lance to the v10.1.0-beta.2 tag: - selecting legacy versus safe semantics from the manifest feature bit, so that on an activated table a *missing* coverage entry means "unknown" and retains SSTables rather than reading as "fully caught up"; - collecting scalar and bitmap-family indexes used as prefilters, which needs the filter's referenced columns and so must handle SQL, Substrait and Datafusion filter forms. Both land once lance carries the feature bit and this crate is bumped.
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