# LanceDB — Multimodal Vector Database for AI

> LanceDB is a multimodal vector database for AI/ML applications with 9.7K+ GitHub stars. Fast vector search across billions of vectors, full-text search, SQL queries. Python, Node.js, Rust clients. Apa

## Install

Save in your project root:

## Quick Use

```bash
# Install Python client
pip install lancedb

# Or JavaScript
npm install lancedb

# Quick start
python -c "
import lancedb
db = lancedb.connect('~/.lancedb')
table = db.create_table('docs', [
    {'text': 'LanceDB is fast', 'vector': [0.1, 0.2, 0.3]},
    {'text': 'Vector search in milliseconds', 'vector': [0.4, 0.5, 0.6]},
])
results = table.search([0.1, 0.2, 0.3]).limit(1).to_list()
print(results)
"
```

---

## Intro

LanceDB is the multimodal data platform for AI/ML applications, providing fast, scalable, and production-ready vector search built on the Lance columnar format. With 9,700+ GitHub stars and Apache 2.0 license, LanceDB performs vector similarity search across billions of vectors in milliseconds. It supports multimodal data (text, images, videos, point clouds), combines vector search with full-text and SQL queries, and offers zero-copy architecture with automatic versioning and GPU-accelerated indexing. Available in Python, Node.js, Rust, and REST API.

**Best for**: Developers building RAG pipelines, multimodal search, or AI applications needing fast vector retrieval
**Works with**: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
**Integrations**: LangChain, LlamaIndex, DuckDB, Polars

---

## Key Features

- **Billion-scale vector search**: Millisecond query latency across massive datasets
- **Multimodal support**: Text, images, videos, and point clouds in one database
- **Hybrid search**: Combine vector similarity, full-text search, and SQL queries
- **Zero-copy architecture**: Automatic versioning with no data duplication
- **GPU-accelerated indexing**: Fast index building for large datasets
- **Multi-language clients**: Python, Node.js, Rust, REST API
- **Rich ecosystem**: LangChain, LlamaIndex, DuckDB, Polars integrations

---

### FAQ

**Q: What is LanceDB?**
A: LanceDB is a multimodal vector database with 9.7K+ stars for AI/ML applications. Built on the Lance columnar format, it provides millisecond vector search across billions of vectors with support for text, images, and video. Apache 2.0 licensed.

**Q: How do I install LanceDB?**
A: Run `pip install lancedb` for Python or `npm install lancedb` for JavaScript. No external server needed — it runs embedded in your application.

**Q: How does LanceDB compare to Chroma or Pinecone?**
A: LanceDB is built on a columnar format (Lance) optimized for ML workloads, supports true multimodal data, and scales to billions of vectors. Chroma is simpler but less scalable. Pinecone is cloud-only; LanceDB runs locally or in the cloud.

---

## Source & Thanks

> Created by [LanceDB](https://github.com/lancedb). Licensed under Apache 2.0.
> [lancedb/lancedb](https://github.com/lancedb/lancedb) — 9,700+ GitHub stars

---
Source: https://tokrepo.com/en/workflows/3ce6f2b1-ad97-4894-9b7d-af90cb4928bb
Author: AI Open Source