ashvardanian/JaccardIndex

Optimizing bit-level Jaccard Index and Population Counts for large-scale quantized Vector Search via Harley-Seal CSA and Lookup Tables

32
/ 100
Emerging

This project helps data scientists and machine learning engineers significantly speed up the calculation of Jaccard similarity between very large collections of binary data vectors. It takes in collections of these binary vectors and outputs their similarity scores much faster than standard methods. This is particularly useful for those working with large-scale vector search and information retrieval systems.

No commits in the last 6 months.

Use this if you need to calculate Jaccard Index or population counts efficiently on large-scale binary vectors, especially in vector search applications.

Not ideal if your similarity calculations don't involve binary, bit-level data or if you're dealing with very small datasets where performance is not a critical concern.

information-retrieval vector-search data-quantization large-scale-data similarity-scoring
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

21

Forks

2

Language

Python

License

Apache-2.0

Last pushed

May 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/ashvardanian/JaccardIndex"

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