LanceDB Rust

LanceDB Rust SDK, a serverless vector database.

Read more at: https://lancedb.com/

lib.rs:

VectorDB (LanceDB) -- Developer-friendly, serverless vector database for AI applications

LanceDB is an open-source database for vector-search built with persistent storage, which greatly simplifies retrevial, filtering and management of embeddings.

The key features of LanceDB include:

• Production-scale vector search with no servers to manage.
• Store, query and filter vectors, metadata and multi-modal data (text, images, videos, point clouds, and more).
• Support for vector similarity search, full-text search and SQL.
• Native Rust, Python, Javascript/Typescript support.
• Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure.
• GPU support in building vector indices[^note].
• Ecosystem integrations with LangChain 🦜️🔗, LlamaIndex 🦙, Apache-Arrow, Pandas, Polars, DuckDB and more on the way.

[^note]: Only in Python SDK.

Getting Started

LanceDB runs in process, to use it in your Rust project, put the following in your Cargo.toml:

cargo install vectordb

Quick Start

Connect to a database.

use vectordb::connect;
let db = connect("data/sample-lancedb").await.unwrap();

LanceDB accepts the different form of database path:

• /path/to/database - local database on file system.
• s3://bucket/path/to/database or gs://bucket/path/to/database - database on cloud object store
• db://dbname - Lance Cloud

You can also use ConnectOptions to configure the connectoin to the database.

use vectordb::{connect_with_options, ConnectOptions};
let options = ConnectOptions::new("data/sample-lancedb")
    .index_cache_size(1024);
let db = connect_with_options(&options).await.unwrap();

LanceDB uses arrow-rs to define schema, data types and array itself. It treats FixedSizeList<Float16/Float32> columns as vector columns.

For more details, please refer to LanceDB documentation.

Create a table

To create a Table, you need to provide a arrow_schema::Schema and a arrow_array::RecordBatch stream.

use arrow_schema::{DataType, Schema, Field};
use arrow_array::{RecordBatch, RecordBatchIterator};

let schema = Arc::new(Schema::new(vec![
  Field::new("id", DataType::Int32, false),
  Field::new("vector", DataType::FixedSizeList(
    Arc::new(Field::new("item", DataType::Float32, true)), 128), true),
]));
// Create a RecordBatch stream.
let batches = RecordBatchIterator::new(vec![
    RecordBatch::try_new(schema.clone(),
        vec![
            Arc::new(Int32Array::from_iter_values(0..1000)),
            Arc::new(FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(
                (0..1000).map(|_| Some(vec![Some(1.0); 128])), 128)),
        ]).unwrap()
   ].into_iter().map(Ok),
    schema.clone());
db.create_table("my_table", Box::new(batches), None).await.unwrap();

Create vector index (IVF_PQ)

tbl.create_index(&["vector"])
    .ivf_pq()
    .num_partitions(256)
    .build()
    .await
    .unwrap();

Open table and run search

let results = table
    .search(&[1.0; 128])
    .execute_stream()
    .await
    .unwrap()
    .try_collect::<Vec<_>>()
    .await
    .unwrap();