VectorDB-NTU/Extended-RaBitQ

[SIGMOD 2025] Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search

44
/ 100
Emerging

This project offers a new way for developers to compress high-dimensional data, making it faster and more accurate to find similar data points. By taking raw, high-dimensional vectors and applying an advanced quantization algorithm, it outputs significantly smaller, compressed vectors. This is for developers building search or recommendation systems that deal with large amounts of complex data, especially where quick and precise similarity searches are critical.

No commits in the last 6 months.

Use this if you are a developer looking for a state-of-the-art method to compress high-dimensional vectors for Approximate Nearest Neighbor (ANN) search, seeking both speed and high accuracy.

Not ideal if you are a non-technical user or if your application does not involve high-dimensional vector data and approximate nearest neighbor search.

vector-search-development similarity-search data-compression-algorithms database-optimization information-retrieval
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

62

Forks

14

Language

C++

License

Apache-2.0

Last pushed

Jun 04, 2025

Commits (30d)

0

Get this data via API

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

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