rragundez/chunkdot

Multi-threaded matrix multiplication and cosine similarity calculations for dense and sparse matrices. Appropriate for calculating the K most similar items for a large number of items by chunking the item matrix representation (embeddings) and using Numba to accelerate the calculations.

42
/ 100
Emerging

Implements memory-efficient chunked processing with configurable RAM budgets and supports both self-similarity and cross-similarity queries, returning results as sparse CSR matrices. Provides a scikit-learn transformer interface for end-to-end pipelines with structured data, enabling direct integration into preprocessing workflows. Numba JIT compilation accelerates the core similarity computations while multi-threading parallelizes chunk processing across CPU cores.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 8 / 25

How are scores calculated?

Stars

86

Forks

5

Language

Python

License

MIT

Last pushed

Dec 28, 2024

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/rragundez/chunkdot"

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