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,…
[](https://lancedb.com)
The Multimodal AI Lakehouse
[How to Install ](#how-to-install) ✦ Detailed Documentation ✦ Tutorials and Recipes ✦ [Contributors](#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
Members
-
lancedb ★ PINNED
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
HTML ★ 11k 20h agoExplain → -
vectordb-recipes
Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs
Jupyter Notebook ★ 969 3mo agoExplain → -
yoloexplorer
YOLOExplorer : Iterate on your YOLO / CV datasets using SQL, Vector semantic search, and more within seconds
Python ★ 144 18d agoExplain → -
lancedb-vercel-chatbot
Build an AI chatbot with website context retrieved from a vector store like LanceDB.
TypeScript ★ 101 2y agoExplain → -
lancedb-go
LanceDB Go SDK
Go ★ 57 2mo agoExplain → -
tantivy-object-store
Tantivy directory implementation backed by object_store
Rust ★ 42 2y agoExplain → -
lancedb-mcp-server
No description.
Python ★ 25 1y agoExplain → -
lance-deeplearning-recipes
Deep Learning how-to's using Lance file format
Jupyter Notebook ★ 25 1y agoExplain → -
lerobot-lancedb
No description.
Python ★ 22 13d agoExplain → -
ragged
No description.
Python ★ 22 1y agoExplain → -
ocra
OCRA: Object-store Cache in Rust for All
Rust ★ 19 9mo agoExplain → -
flight-sql-js-client
A JavaScript client for FlightSQL
JavaScript ★ 17 8mo agoExplain → -
lancedb-c
C bindings for LanceDB
C++ ★ 14 11d agoExplain → -
aifunctools
Utility for OpenAI GPT Functions
Python ★ 14 3y agoExplain → -
docs
Documentation for LanceDB, the Multimodal Lakehouse for AI
Python ★ 9 20h agoExplain → -
liteparse-lancedb-pdf-qa
Turn messy, visual PDF reports into a local, inspectable multimodal evidence store in LanceDB
Python ★ 9 23d agoExplain → -
cocoindex-lancedb-demo
Incremental processing and maintaining data freshness with CocoIndex and LanceDB
Python ★ 8 6mo agoExplain → -
lancedb-claw
No description.
TypeScript ★ 8 3mo agoExplain → -
lance-distributed-training
Examples and guides for distributed training with lance
Python ★ 7 8mo agoExplain → -
lance-research
Research papers from Lance
TeX ★ 7 10mo agoExplain → -
hermes-agent-memory
LanceDB-backed memory provider plugin for Hermes Agent.
Python ★ 5 1mo agoExplain → -
locomo-eval
LOCOMO benchmark for OpenClaw memory stores
Python ★ 5 4mo agoExplain → -
research
repository containing reproducibility code for R&D experiments and benchmarks
Python ★ 5 9mo agoExplain → -
saas-examples-large-scale
No description.
Python ★ 5 7mo agoExplain → -
lancedb-asm
LanceDB rewritten in ASM. No lifetimes. No abstractions. Just pure, uninterrupted, bare metal performance.
★ 4 3mo agoExplain → -
lance-bench
Benchmarking utilities for Lance, LanceDB, etc.
Rust ★ 3 16d agoExplain → -
openclaw-lancedb-demo
Use LanceDB to create a local-first memory layer for OpenClaw
TypeScript ★ 3 4mo agoExplain → -
genkitx-lancedb
Community Plugin for Genkit to use LanceDB
TypeScript ★ 3 1y agoExplain → -
MCPExample
No description.
Python ★ 3 1y agoExplain → -
lance-benchmark-results
History for benchmark results
Python ★ 3 8mo agoExplain → -
semantic-kernel ⑂
Integrate cutting-edge LLM technology quickly and easily into your apps
★ 2 3y agoExplain → -
chat-with-videos
Demo app to allow users to chat with their YouTube videos in LanceDB
Python ★ 2 4mo agoExplain → -
lancedb-cloud-benchmarks
No description.
Python ★ 2 1y agoExplain → -
vercel_blob
Rust client for the vercel blob API
Rust ★ 2 2y agoExplain → -
openai-cookbook ⑂
Examples and guides for using the OpenAI API
Jupyter Notebook ★ 2 3y agoExplain → -
llama_index ⑂
LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.
Python ★ 2 3y agoExplain → -
geneva-examples
No description.
Python ★ 1 1d agoExplain → -
ocr-handwriting-retrieval
How to use LanceDB as the storage & retrieval layer for handwritten documents + OCR-extracted text
Python ★ 1 10d agoExplain → -
community-metrics
Dashboard for tracking downloads and stars for Lance format and LanceDB SDK adoption.
HTML ★ 1 10d agoExplain → -
mcap-lancedb
Ingest MCAP and ROS bag files into LanceDB-ready Lance datasets
Python ★ 1 1mo agoExplain → -
training
All things training with LanceDB
Jupyter Notebook ★ 1 13d agoExplain → -
lancedb-duckdb-demo
Using the Lance extension in DuckDB for querying, joining and materializing on tables in either system
Python ★ 1 2mo agoExplain → -
documentation ▣
No description.
Python ★ 1 11mo agoExplain → -
VectorDBBench ⑂
A Benchmark Tool for VectorDB
Python ★ 1 2y agoExplain → -
langchainjs ⑂
No description.
★ 1 3y agoExplain → -
videos
Source for LanceDB tutorial videos
Python ★ 0 2d agoExplain → -
lancedb-robotics-lakehouse-external
Sanitized external mirror of lancedb-robotics-lakehouse — a reference implementation of a multi-modal lakehouse for physical AI
Python ★ 0 12d agoExplain → -
tmls-2026-demo
Code and slides for the TMLS 2026 Workshop session on LanceDB for training.
Jupyter Notebook ★ 0 1mo agoExplain → -
hf-upload-demo
How to upload a Lance dataset to Hugging Face Hub and query it in LanceDB
Python ★ 0 4mo agoExplain → -
trino ⑂
Official repository of Trino, the distributed SQL query engine for big data, formerly known as PrestoSQL (https://trino.io)
★ 0 2y agoExplain → -
ecommerce
Demo - H&M Online Clothing Store
Python ★ 0 10mo agoExplain → -
assets
LanceDB public assets for docs and presentations
★ 0 1y agoExplain → -
ray ⑂
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Python ★ 0 1y agoExplain → -
rustc-error-repro
No description.
Rust ★ 0 1y agoExplain → -
datasets ⑂
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
★ 0 2y agoExplain →
No repos match these filters.