analyticsinmotion/symrank

🐍📦 High-performance cosine similarity ranking for Retrieval-Augmented Generation (RAG) pipelines.

36
/ 100
Emerging

Implements SIMD-accelerated cosine similarity scoring with an inlined heap selection algorithm optimized for top-k retrieval, eliminating full-sort overhead. Offers two complementary APIs: a high-performance matrix mode for pre-computed embedding batches, and a flexible list mode supporting streaming candidates from mixed sources. Integrates seamlessly with NumPy arrays and Python sequences, making it suitable for vector databases, embedding services, and RAG reranking workflows without external dependencies.

Available on PyPI.

No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/analyticsinmotion/symrank"

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