Accenture/AmpliGraph

Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org

56
/ 100
Established

Implements multiple neural embedding models (TransE, DistMult, ComplEx, HolE, RotatE) that map knowledge graph entities and relations to vector spaces, then score candidate triples using model-specific functions for link prediction. Built on TensorFlow 2 with Keras-style APIs, it provides evaluation protocols (mean reciprocal rank filtering), entity clustering, and duplicate detection through a high-level discovery module for end-to-end knowledge graph completion tasks.

2,228 stars and 737 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 17 / 25
Maturity 18 / 25
Community 21 / 25

How are scores calculated?

Stars

2,228

Forks

254

Language

Python

License

Apache-2.0

Last pushed

Nov 22, 2024

Monthly downloads

737

Commits (30d)

0

Dependencies

20

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Accenture/AmpliGraph"

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