lancedb/lancedb

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

What it solves

LanceDB is a multimodal AI lakehouse that provides a fast, scalable, and production-ready way to store, index, and search over petabytes of multimodal data and vectors. It eliminates the need for complex infrastructure by allowing developers to build, train, and analyze AI workloads in a central location.

How it works

Built on the Lance columnar format, LanceDB enables efficient storage and analytics. It supports multiple search types, including vector similarity search, full-text search, and SQL queries. It can handle various data types such as text, images, videos, and point clouds, and offers GPU support for building vector indexes.

Who it’s for

Developers and researchers building AI/ML applications that require high-performance vector search and multimodal data management at scale.

Highlights

  • Multimodal Support: Store and query vectors, metadata, and diverse data types like images and videos.
  • Fast Vector Search: Millisecond search across billions of vectors using state-of-the-art indexing.
  • Comprehensive Search: Combines vector similarity, full-text search, and SQL.
  • Zero-copy and Versioning: Includes automatic versioning and zero-copy capabilities to manage data versions without extra infrastructure.
  • Broad Integration: Native support for Python, Node.js, and Rust, with integrations for LangChain, LlamaIndex, Apache-Arrow, Pandas, and Polars.

Related

  • Project
    lance-format/lance

    An open lakehouse format for multimodal AI that provides high-performance vector search, random access, and native storage for images, video, and audio.

  • Project
    laminlabs/lamindb

    An open-source data management tool for multimodal AI that provides end-to-end traceability, versioning, and governance for datasets and the code that produces them.

  • Project
    ArcadeData/arcadedb

    A high-performance multi-model DBMS that supports graph, document, key-value, time-series, and vector data in a single ACID-compliant engine.

  • Project
    heavyai/heavydb

    HeavyDB is an open-source, GPU-accelerated SQL database engine that enables millisecond queries on multi-billion row datasets without needing indexes or pre-aggregation.

  • Project
    ModernRelay/omnigraph

    A lakehouse graph database for AI agents that provides multimodal retrieval and Git-style branching for versioned coordination and memory.