AnkitNayak-eth/EpsteinFiles-RAG

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

51
/ 100
Established

This tool helps researchers and journalists quickly extract precise answers from massive document collections, even if the documents are fragmented. You feed in a large set of raw documents, and it automatically cleans, organizes, and processes them. The output is accurate answers to your questions, directly supported by the source documents, presented through a user-friendly interface.

358 stars.

Use this if you need to rapidly search and get fact-checked answers from hundreds of thousands or even millions of document lines without hallucination.

Not ideal if you're looking to generate creative content or summaries that go beyond the exact information present in your source documents.

investigative-journalism legal-research document-analysis fact-finding information-retrieval
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.