Home
LanceDB
LanceDB
LanceDB is an open-source, developer-friendly, embedded multimodal vector database built on the Lance columnar storage format. It supports vector, full-text, hybrid, and SQL search across billions of vectors and multimodal data (text, images, video, point clouds). LanceDB ships as an embedded OSS library with Python, TypeScript / JavaScript, and Rust SDKs, and is also offered as LanceDB Enterprise - a distributed and managed multimodal lakehouse - with integrations into Apache Arrow, Pandas, Polars, DuckDB, Ray, Apache Spark, LangChain, LlamaIndex, and Hugging Face.
6 APIs
0 Features
Vector Database Multimodal Lance Format RAG Open Source Lakehouse
LanceDB publishes 6 APIs on the APIs.io network. Tagged areas include Vector Database, Multimodal, Lance Format, RAG, and Open Source.
LanceDB’s developer surface includes documentation, GitHub presence, support, and 3 more developer resources.
Open-source, embedded, serverless multimodal vector database. Provides table create / drop / list, insert / upsert / delete, vector / full-text / hybrid / SQL search, automatic ...
Distributed, managed multimodal lakehouse built on the Lance format, offering curation, deduplication, feature engineering with Python UDFs, unified vector / full-text / hybrid ...
Open-source columnar storage format optimized for multimodal AI data - zero-copy reads, automatic versioning, fast random access, and Arrow interop. Powers the LanceDB OSS and E...
Primary client library for LanceDB OSS and Enterprise, with first-class support for Arrow, Pandas, and Polars data frames and pluggable embedding functions.
Node.js / TypeScript client library for LanceDB OSS and Enterprise.
Native Rust client library; the LanceDB core and storage layer are written in Rust.
Sources
aid: lancedb
url: https://raw.githubusercontent.com/api-evangelist/lancedb/refs/heads/main/apis.yml
name: LanceDB
kind: company
description: >-
LanceDB is an open-source, developer-friendly, embedded multimodal vector
database built on the Lance columnar storage format. It supports vector,
full-text, hybrid, and SQL search across billions of vectors and multimodal
data (text, images, video, point clouds). LanceDB ships as an embedded OSS
library with Python, TypeScript / JavaScript, and Rust SDKs, and is also
offered as LanceDB Enterprise - a distributed and managed multimodal lakehouse
- with integrations into Apache Arrow, Pandas, Polars, DuckDB, Ray, Apache
Spark, LangChain, LlamaIndex, and Hugging Face.
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
- Vector Database
- Multimodal
- Lance Format
- RAG
- Open Source
- Lakehouse
created: '2026-05-23'
modified: '2026-05-23'
specificationVersion: '0.19'
apis:
- aid: lancedb:oss
name: LanceDB OSS Library
description: >-
Open-source, embedded, serverless multimodal vector database. Provides
table create / drop / list, insert / upsert / delete, vector / full-text /
hybrid / SQL search, automatic versioning, and pluggable embedding
functions. Apache-2.0 licensed.
humanURL: https://docs.lancedb.com/
baseURL: https://github.com/lancedb/lancedb
tags:
- Open Source
- Embedded
- Vector Database
properties:
- type: Documentation
url: https://docs.lancedb.com/
- type: Repository
url: https://github.com/lancedb/lancedb
- type: Quickstart
url: https://docs.lancedb.com/quickstart
- aid: lancedb:enterprise
name: LanceDB Enterprise
description: >-
Distributed, managed multimodal lakehouse built on the Lance format,
offering curation, deduplication, feature engineering with Python UDFs,
unified vector / full-text / hybrid search, and direct training from
curated tables. Sold to enterprise customers via [email protected] .
humanURL: https://lancedb.com/
baseURL: https://lancedb.com/
tags:
- Enterprise
- Managed
- Lakehouse
properties:
- type: Documentation
url: https://docs.lancedb.com/
- type: Sales
url: https://lancedb.com/contact
- aid: lancedb:lance-format
name: Lance Format
description: >-
Open-source columnar storage format optimized for multimodal AI data -
zero-copy reads, automatic versioning, fast random access, and Arrow
interop. Powers the LanceDB OSS and Enterprise products and integrates
with DuckDB, Pandas, Polars, Ray, Apache Spark, and Hugging Face.
humanURL: https://lance.org
baseURL: https://github.com/lancedb/lance
tags:
- File Format
- Columnar
- Arrow
- Open Source
properties:
- type: Documentation
url: https://lance.org
- type: Repository
url: https://github.com/lancedb/lance
- aid: lancedb:python-sdk
name: LanceDB Python SDK
description: >-
Primary client library for LanceDB OSS and Enterprise, with first-class
support for Arrow, Pandas, and Polars data frames and pluggable embedding
functions.
humanURL: https://docs.lancedb.com/
baseURL: https://github.com/lancedb/lancedb
tags:
- SDK
- Python
properties:
- type: Documentation
url: https://docs.lancedb.com/
- type: Repository
url: https://github.com/lancedb/lancedb
- aid: lancedb:typescript-sdk
name: LanceDB TypeScript SDK
description: >-
Node.js / TypeScript client library for LanceDB OSS and Enterprise.
humanURL: https://docs.lancedb.com/
baseURL: https://github.com/lancedb/lancedb
tags:
- SDK
- TypeScript
- JavaScript
- Node.js
properties:
- type: Documentation
url: https://docs.lancedb.com/
- type: Repository
url: https://github.com/lancedb/lancedb
- aid: lancedb:rust-sdk
name: LanceDB Rust SDK
description: >-
Native Rust client library; the LanceDB core and storage layer are written
in Rust.
humanURL: https://docs.lancedb.com/
baseURL: https://github.com/lancedb/lancedb
tags:
- SDK
- Rust
properties:
- type: Documentation
url: https://docs.lancedb.com/
- type: Repository
url: https://github.com/lancedb/lancedb
common:
- type: Website
url: https://lancedb.com/
- type: Documentation
url: https://docs.lancedb.com/
- type: GitHub
url: https://github.com/lancedb
- type: Discord
url: https://discord.com/invite/G5DcmnZWKB
- type: Trust
url: https://trust.lancedb.com/
- type: Support
url: mailto:[email protected]
integrations:
- name: Apache Arrow
- name: Apache Spark
- name: DuckDB
- name: Pandas
- name: Polars
- name: Ray
- name: Hugging Face
- name: LangChain
- name: LlamaIndex
- name: Databricks
- name: Amazon Web Services
- name: NVIDIA
maintainers:
- FN: Kin Lane
email: [email protected]