# LanceDB

> LanceDB is an embedded vector database built on Apache Arrow/Lance format for multimodal data, supports SQL queries, zero-copy reads, disk-based indexes like IVF-PQ. Ideal for ML pipelines and analytics; vs Chroma more columnar/multimodal focus. Features: serverless cloud, Python/Rust SDKs.

- **URL:** https://lancedb.com/
- **Category:** Embedded And Edge Vector Databases
- **Tags:** Columnar Storage, Sql Vector, Multimodal, Arrow Native
- **Updated:** 2026-04-30 11:38
- **Canonical page:** https://vectordb.ever.works/items/lancedb

## Details

## Overview

LanceDB is an embedded columnar database built on Apache Arrow's Lance format, optimized for multimodal vectors (images, text, video).

## Features

- Zero-copy reads leveraging Arrow
- SQL queries for hybrid vector + full-text search
- Cloud sync with LanceDB Cloud
- IVF-PQ indexing and versioning
- Python/Rust bindings, zero dependencies

## Use Cases

- Computer vision search
- Large-scale multimodal analytics
- Edge AI and prototyping

## Comparisons

| Feature          | LanceDB vs Chroma          | LanceDB vs Faiss     |
|------------------|----------------------------|----------------------|
| Storage         | Columnar, multimodal      | Full DB w/ persistence |
| Queries         | SQL                       | Index-only           |
| Deployment      | Embedded, zero-copy       | Library              |

## Pricing

Open-source under Apache 2.0 license.

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/lancedb._