LanceDB

LanceDB is an open-source database for vector search and multimodal AI data, built on the Lance columnar format. It stores vectors alongside metadata and raw data such as text, images and video, and runs locally or in your own cloud. LanceDB Inc. also offers a managed Cloud and an Enterprise version.

LanceDB runs embedded inside your application, with no server to set up, and works from Python, TypeScript and Rust SDKs or a REST API. It combines vector similarity search, full-text search and SQL filtering, versions every write automatically, and can use GPUs to build vector indexes. It integrates with LangChain, LlamaIndex, Apache Arrow, Pandas, Polars and DuckDB.

LanceDB is the vector database you can start with a single import: it runs inside your app like SQLite, keeps data in an open columnar format, and handles images and video next to the vectors. It is Apache-licensed, written in Rust.

Stars

0

Forks

0

Commits

0

Repository

lancedb/lancedb

• PineconeManaged vector database for AI applications.
• MilvusNo. 215Open-source vector database built to scale across a cluster.
• QdrantNo. 150Open-source vector database written in Rust.
• WeaviateNo. 033Open-source AI-native vector database.

See every open-source alternative to Pinecone in the collection.