AnkitNayak-eth/EpsteinFiles-RAG

A RAG pipeline implementation built on the 'Epstein Files 20K' dataset from Hugging Face (Teyler).

51
/ 100
Established

Implements document cleaning, intelligent chunking, and MMR-based retrieval to process 2.5M+ lines into a searchable vector index using Chroma and Sentence Transformers. Serves grounded answers via FastAPI and Streamlit UI, powered by LLaMA 3.3 through Groq's inference API, ensuring responses cite only source documents without hallucination.

358 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 20 / 25

How are scores calculated?

Stars

358

Forks

58

Language

Python

License

MIT

Last pushed

Feb 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/AnkitNayak-eth/EpsteinFiles-RAG"

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