koaning/whatlies

Toolkit to help understand "what lies" in word embeddings. Also benchmarking!

Archived
43
/ 100
Emerging

Provides composable transformations (PCA, UMAP, vector algebra operations) and interactive Altair-based visualizations for embedding analysis, with support for multiple backends including spaCy, Hugging Face, fastText, and TensorFlow Hub. Implements scikit-learn compatible featurizers enabling embeddings as pipeline stages, allowing bias detection and mitigation through algebraic projection operations on embedding spaces.

475 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

475

Forks

47

Language

Python

License

Apache-2.0

Last pushed

Feb 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/koaning/whatlies"

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