/EmbedAI

An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks

Primary LanguageJavaScriptMIT LicenseMIT

PrivateGPT

Create a QnA chatbot on your documents without relying on the internet by utilizing the capabilities of local LLMs. Ensure complete privacy and security as none of your data ever leaves your local execution environment. Seamlessly process and inquire about your documents even without an internet connection. Inspired from imartinez

pgpt

Contents

Getting started

Code is up, ⭐ (Star) the repo meanwhile to receive updates

Follow Anil Chandra Naidu Matcha & Ankur Singh on twitter for updates

Requirements

  • Python 3.8 or later
  • NodeJS v18.12.1 or later
  • Minimum 16GB of memory

How to run

  1. Go to client folder and run the below commands

    npm install   
    npm run dev
  2. Go to server folder and run the below commands

    pip install -r requirements.txt
    python privateGPT.py
  3. Open http://localhost:3000, click on download model to download the required model initially

  4. Upload any document of your choice and click on Ingest data. Ingestion is fast

  5. Now run any query on your data. Data querying is slow and thus wait for sometime

Support

Join our discord https://discord.gg/A6EzvsKX4u to get support

Data

The supported extensions for documents are:

  • .csv: CSV,
  • .docx: Word Document,
  • .enex: EverNote,
  • .eml: Email,
  • .epub: EPub,
  • .html: HTML File,
  • .md: Markdown,
  • .msg: Outlook Message,
  • .odt: Open Document Text,
  • .pdf: Portable Document Format (PDF),
  • .pptx : PowerPoint Document,
  • .txt: Text file (UTF-8),

Check repos