Serverless, low-latency vector database for AI applications

Documentation • Blog • Discord • Twitter

---

LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies storage, retrieval and filtering for vectors and more.

The key features of Lance include:

• Scale vector-search without managing servers.

• Combine attribute-based information with vectors and store them as a single source-of-truth.

• Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure.

• Ecosystem integrations: Apache-Arrow, Pandas, Polars, DuckDB and more on the way.

Lance's core is written in Rust 🦀 and is built using Lance, an open-source columnar format designed for performant ML workloads.

Quick Start

Installation

pip install lancedb

Quickstart

import lancedb

db = lancedb.connect(uri)
table = db.create_table("my_table",
                         data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
                               {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
result = table.search([100, 100]).where("price < 15").limit(1).to_df()