haven-jeon/LegalQA

Korean LegalQA using SentenceKoBART

45
/ 100
Emerging

Combines SentenceKoBART embeddings with approximate nearest-neighbor search (Faiss/Annoy/Hnswlib) via Jina's neural search framework to retrieve relevant legal documents, then augments ChatGPT responses with retrieved context. Includes a curated Korean legal QA dataset (1,830 pairs) and REST API with Streamlit chat interface for end-to-end retrieval-augmented generation workflows.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

97

Forks

28

Language

Python

License

Last pushed

Mar 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/haven-jeon/LegalQA"

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