SQLite Vector

Use sqlite-vec when you need a lightweight, embedded solution for vector similarity search. It is ideal for applications that require vector data handling on-device or at the edge, such as mobile apps, IoT devices, or local AI model inference.


pip install sqlite-vec

import sqlite3
import sqlite_vec
from sqlite_vec import serialize_float32

db = sqlite3.connect(":memory:")
db.enable_load_extension(True)

sqlite_vec.load(db)
db.enable_load_extension(False)

embedding = [0.1, 0.2, 0.3, 0.4]
result = db.execute('SELECT vec_length(?)',
        [serialize_float32(embedding)])

print(result.fetchone()[0])  # Outputs: 4

For NumPy arrays, cast to 32-bit floats with .astype(np.float32)

Introducing sqlite-vec v0.1.0: a vector search SQLite extension that runs everywhere

Install with Python, Node.js, Deno, Bun Rust, Go, C, WASM...

https://alexgarcia.xyz/blog/2024/sqlite-vec-stable-release/index.html

SQLite Vector

Recommendations