lqhl/rabitq-rs

Rust implementation of RaBitQ + IVF and MSTG (multi-scale tree graph)

34
/ 100
Emerging

This project helps developers working with large datasets of high-dimensional vectors (like embeddings from AI models) to find the most similar vectors very quickly while using significantly less memory. It takes your raw vector data and outputs a compact, searchable index, enabling efficient approximate nearest neighbor searches. This is ideal for backend engineers, data scientists, or MLOps engineers building similarity search features in applications.

Use this if you need to perform high-speed, memory-efficient similarity searches on large collections of vectors, especially in Rust-based applications.

Not ideal if you are working on ARM64-based systems (like Apple Silicon Macs or ARM servers), as there are known issues affecting accuracy.

similarity-search vector-databases machine-learning-inference information-retrieval data-compression
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Rust

License

Apache-2.0

Last pushed

Feb 26, 2026

Monthly downloads

44

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/lqhl/rabitq-rs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.