AbhisumatK

An open-source RAG platform to explore the unsealed Jeffrey Epstein court documents.

19
5
75% credibility
Found May 29, 2026 at 27 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A web-based research tool that lets you explore unsealed Jeffrey Epstein court documents by asking questions in plain language, with the AI searching through thousands of pages to find relevant answers and their original sources.

How It Works

1
🔍 Discover the Court Documents

You hear about the unsealed Epstein court documents and want to explore what they contain.

2
📦 Install the Explorer Tool

You download and install the application on your computer to start your investigation.

3
💾 Load the Documents

The tool downloads a collection of court documents from a public research database so you can search through them.

4
Choose Your AI Assistant
💻
Run Locally

Your AI runs privately on your own machine - everything stays on your computer

☁️
Use Cloud Service

Connect to a powerful AI service for faster analysis and answers

5
Ask Questions About the Documents

You type questions like 'Who appears in the flight logs?' and the AI searches through thousands of pages to find relevant information.

6
📋 See Answers with Sources

For every answer, you see exactly which documents it came from, so you can verify and explore further.

Understand the Investigation

You now have a powerful research assistant that helps you navigate and understand the court documents.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 27 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Epstein_Files_RAG?

Epstein_Files_RAG is a Python-based RAG chatbot that lets you query unsealed Jeffrey Epstein court documents using natural language. It combines a Streamlit web interface with vector search backed by ChromaDB and LangChain, letting you ask questions and get answers grounded in the actual legal filings. You can run it locally with Ollama for privacy or connect to Groq or OpenRouter for faster cloud inference.

Why is it gaining traction?

This project taps into a real appetite for open-source tools that let anyone analyze public records without relying on paywalled services. The setup is straightforward: clone, configure API keys if using cloud LLMs, run an ingestion script to download and index documents from Hugging Face, then launch the Streamlit app. The guardrails built into the system prompt are a thoughtful touch, keeping responses strictly within the document context rather than letting the model hallucinate or drift into unrelated territory.

Who should use this?

Researchers, journalists, and investigators who want to search through the Epstein court documents without manually skimming thousands of pages. Privacy-conscious users who prefer running queries locally will appreciate the Ollama support. Developers exploring how to build document-focused RAG pipelines with guardrails will find this a useful reference implementation.

Verdict

At 19 stars with minimal documentation, this is an early-stage project that demonstrates a working concept rather than a polished product. The credibility score of 0.75% reflects that maturity gap. Worth exploring if you need to dig into these specific documents or want a starter template for similar legal discovery projects, but do not expect production-ready stability or comprehensive test coverage.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.