bb01ad5290
Fix broken link to embedding functions testing: broken link was verified after local docs build to have been repaired --------- Co-authored-by: Chang She <chang@lancedb.com>
3.1 KiB
LanceDB
LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrieval, filtering and management of embeddings.
The key features of LanceDB include:
-
Store, query and filter vectors, metadata and multi-modal data (text, images, videos, point clouds, and more).
-
Support for production-scale vector similarity search, full-text search and SQL, with no servers to manage.
-
Native Python and Javascript/Typescript support.
-
Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure.
-
Persisted on HDD, allowing scalability without breaking the bank.
-
Ingest your favorite data formats directly, like pandas DataFrames, Pydantic objects and more.
LanceDB's core is written in Rust 🦀 and is built using Lance, an open-source columnar format designed for performant ML workloads.
Quick Start
=== "Python"
shell pip install lancedb
```python
import lancedb
uri = "data/sample-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]).limit(2).to_list()
```
=== "Javascript"
shell npm install vectordb
```javascript
const lancedb = require("vectordb");
const uri = "data/sample-lancedb";
const db = await lancedb.connect(uri);
const table = await db.createTable("my_table",
[{ id: 1, vector: [3.1, 4.1], item: "foo", price: 10.0 },
{ id: 2, vector: [5.9, 26.5], item: "bar", price: 20.0 }])
const results = await table.search([100, 100]).limit(2).execute();
```
Complete Demos (Python)
- YouTube Transcript Search
- Documentation QA Bot using LangChain
- Multimodal search using CLIP
- Serverless QA Bot with S3 and Lambda
- Serverless QA Bot with Modal
Complete Demos (JavaScript)
Documentation Quick Links
Basic Operations- basic functionality of LanceDB.Embedding Functions- functions for working with embeddings.Indexing- create vector indexes to speed up queries.Full text search- [EXPERIMENTAL] full-text search APIEcosystem Integrations- integrating LanceDB with python data tooling ecosystem.Python API Reference- detailed documentation for the LanceDB Python SDK.Node API Reference- detailed documentation for the LanceDB Node SDK.