This project provides a private, local Q&A chatbot for interacting with your documents using GPT models, ensuring no data leaves your environment. It's designed for users who need to query sensitive documents without internet access or concerns about data privacy.

How It Works

The application leverages local Large Language Models (LLMs) to process and query documents. It uses Langchain for document handling and interaction with LLMs, enabling offline functionality. The architecture separates a React-based frontend for user interaction from a Python backend that manages document ingestion and LLM querying.

Quick Start & Requirements

• Install:
  • Frontend: npm install and npm run dev in the client folder.
  • Backend: pip install -r requirements.txt and python privateGPT.py in the server folder.
• Access: Open http://localhost:3000.
• Prerequisites: Python 3.8+, NodeJS v18.12.1+, minimum 16GB RAM.
• Setup: Download models and ingest data via the UI.
• Docs: https://github.com/SamurAIGPT/EmbedAI

Highlighted Details

• Supports private, offline interaction with documents using local LLMs.
• Handles various document formats including PDF, DOCX, TXT, HTML, and more.
• Utilizes Langchain for robust document processing and LLM integration.
• Offers a user-friendly interface for uploading, ingesting, and querying documents.

Maintenance & Community

• Community support is available via Discord: https://discord.gg/A6EzvsKX4u.
• Updates are announced by following Anil Chandra Naidu Matcha & Ankur Singh on Twitter.

Licensing & Compatibility

• The README does not specify a license. Users should verify licensing for commercial or closed-source use.

Limitations & Caveats

Data querying is noted as slow, requiring users to wait for responses. The project does not explicitly state which LLM models are supported or how to configure them.