Skip to content

jerpint/RAGTheDocs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

title emoji colorFrom colorTo sdk sdk_version app_file pinned license
RAGTheDocs
👀
gray
yellow
gradio
3.50.2
app.py
false
mit

RAGtheDocs

Introduction 📚

RAGTheDocs is an open-source library that allows you to one-click deploy retrieval augmented generation (RAG) on any readthedocs documentation on huggingface 🤗 spaces!

Usage 👉

  1. Go to the example space
  2. Duplicate the space:

image

  1. Set your environment variables:
  • OPENAI_API_KEY (required): Needed for the app to work, e.g. sk-...
  • READTHEDOCS_URL (required): The url of the website you are interested in scraping (must be built with sphinx/readthedocs). e.g. https://orion.readthedocs.io
  • READTHEDOCS_VERSION (optional): This is important if there exist multiple versions of the docs (e.g. en/v0.2.7 or en/latest). If left empty, it will scrape all available versions (there can be many for open-source projects!).

Features 🚀

  • Web Scraping and embeddings: RAGtheDocs automatically scrapes and embeds documentation from any website generated by ReadTheDocs/Sphinx using OpenAI embeddings

  • RAG Interface: It comes built-in with a gradio UI for users to interact with Buster 🤖 our RAG agent.

  • Customization Options: Tailor RAGtheDocs prompts and settings with customizable settings and options.

Disclaimers ❗

  • This is a quickly hacked together side-project. This code should be considered experimental at best.

  • This library will automatically call OpenAI APIs for you (for embeddings and chatGPT).

  • Use at your own risk! ⚠️

About

RAG for any docs hosted on readthedocs

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages