VectorDB-NTU/RaBitQ-Library

A lightweight library for the RaBitQ algorithm and its applications in vector search.

56
/ 100
Established

This library helps you find similar high-dimensional data points quickly and efficiently, even with massive datasets. It takes your raw data vectors, converts them into smaller, quantized codes, and then uses these codes to perform fast similarity searches. This is ideal for machine learning engineers or data scientists who need to manage and query large collections of vector embeddings.

129 stars.

Use this if you need to perform high-accuracy similarity searches on vast datasets of vector embeddings while minimizing memory usage and maximizing query speed.

Not ideal if your dataset is very small, or if you need to perform exact similarity searches rather than approximate ones.

vector-search similarity-matching data-compression machine-learning-ops embedding-retrieval
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 21 / 25

How are scores calculated?

Stars

129

Forks

40

Language

C++

License

Apache-2.0

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/VectorDB-NTU/RaBitQ-Library"

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