📖DocGPT

Accurate answers and instant citations for your documents.

This is a document knowledge Q&A system that integrates technology chains such as LangChain, ChatGPT, FAISS, etc. You can upload your own documents and have conversations with LLM.

Demo Link

Installation

Follow the instructions below to run the Streamlit server locally.

Pre-requisites

Make sure you have 3.12 > Python ≥3.10 installed.

Steps

1. Clone the repository

git clone https://github.com/wsy258-strar/DocGPT

2. Install dependencies:

pip install -r requirements.txt

3. (Optional) Avoid adding the OpenAI API every time you run the server by adding it to environment variables.
   • Make a copy of .env.example named .env
   • Add your API key to the .env file

Note: Make sure you have a paid OpenAI API key for faster completions and to avoid hitting rate limits.

4. Run the Streamlit server

streamlit run main.py

Open http://localhost:8501 in your browser to access the app.

Tech Stack

• User Interface - Streamlit
• LLM Tooling - Langchain

Roadmap

• Add support for more formats (e.g. webpages, PPTX, etc.)
• Community versions (FREE!) and personal versions
• Highlight relevant phrases in citations
• Support scanned documents with OCR
• More customization options (e.g. chain type, chunk size, etc.)
• Visual PDF viewer
• Support for Local LLMs

Contributing

Thank you for your interest in my application.At present, I haven't linked to the database for backend development. Interested developers can contribute together.All contributions are welcome!

License

Distributed under the MIT License. See LICENSE for more information.