/DocsGPT

GPT-powered chat for documentation search & assistance.

Primary LanguagePythonMIT LicenseMIT

DocsGPT 🦖

Open-Source Documentation Assistant

DocsGPT is a cutting-edge open-source solution that streamlines the process of finding information in project documentation. With its integration of the powerful GPT models, developers can easily ask questions about a project and receive accurate answers.

Say goodbye to time-consuming manual searches, and let DocsGPT help you quickly find the information you need. Try it out and see how it revolutionizes your project documentation experience. Contribute to its development and be a part of the future of AI-powered assistance.

example1 example2 example3 example3

Group 9

Roadmap

You can find our Roadmap here, please don't hesitate contributing or creating issues, it helps us make DocsGPT better!

Preview

video-example-of-docs-gpt

Project structure

  • Application - flask app (main application)

  • Extensions - chrome extension

  • Scripts - script that creates similarity search index and store for other libraries.

QuickStart

Please note: current vector database uses pandas Python documentation, thus responses will be related to it, if you want to use other docs please follow a guide below

Make sure you have python 3.10 or 3.11 installed

  1. Navigate to /application folder
  2. Install dependencies pip install -r requirements.txt
  3. Prepare .env file Copy .env_sample and create .env with your openai api token
  4. Run the app python app.py

To start frontend

  1. Navigate to /frontend folder
  2. Install dependencies npm install
  3. In the file .env.development instead of VITE_API_HOST = https://docsapi.arc53.com use VITE_API_HOST=http://localhost:5001
  4. Run the app
  5. npm run dev

Alternatively, you can use docker-compose to run the app via docker

  1. From the root folder run docker-compose build && docker-compose up

Deploy on Railway

How to install the Chrome extension

Built with 🦜️🔗 LangChain