JaneaSystems/jecq

Faiss-based library for efficient similarity search

28
/ 100
Experimental

This is a library for developers to efficiently search through large collections of high-dimensional vectors. It takes dense vectors as input and outputs a list of the most similar vectors, but with a significantly reduced memory footprint. Developers building applications like recommendation engines, semantic search, or RAG systems would use this to manage large vector databases more cost-effectively.

No commits in the last 6 months.

Use this if you are a developer working with large collections of dense vectors and need to reduce memory usage while maintaining high search accuracy for your application.

Not ideal if your application requires GPU-based search acceleration or needs distance metrics other than inner product.

vector-database-management retrieval-augmented-generation recommendation-systems semantic-search edge-ai
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 3 / 25

How are scores calculated?

Stars

57

Forks

1

Language

C++

License

MIT

Last pushed

Jul 31, 2025

Commits (30d)

0

Get this data via API

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

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