freelawproject/inception

Our microservice for generating embeddings from blocks of text

50
/ 100
Established

Combines SentenceTransformers with intelligent sentence-boundary chunking to embed legal documents efficiently—queries run on CPU for speed, while longer court opinions leverage GPU acceleration with configurable token limits and overlap ratios. Built as a FastAPI service with Prometheus metrics, Sentry error tracking, and batch processing capabilities, it targets legal document similarity and semantic search workflows.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

33

Forks

10

Language

Python

License

BSD-2-Clause

Last pushed

Feb 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/freelawproject/inception"

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