patrickfrank1/chesspos

Embedding based chess position search and embedding learning for chess positions

58
/ 100
Established

Generates chess position training data via Python scripts, trains neural network embeddings using MLflow experiment tracking, and indexes learned embeddings in Milvus vector database for semantic position search. The architecture supports both .npy file and .pgn file ingestion pipelines, with evaluation workflows provided as Jupyter notebooks.

Available on PyPI.

Maintenance 13 / 25
Adoption 11 / 25
Maturity 18 / 25
Community 16 / 25

How are scores calculated?

Stars

16

Forks

6

Language

Jupyter Notebook

License

AGPL-3.0

Last pushed

Mar 12, 2026

Monthly downloads

187

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/patrickfrank1/chesspos"

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