hhy-joseph / ChatDoc

This is a simple implementation of Retrieval-augmented generation (RAG) on LLM.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ChatDoc

This is a implement of a Q&A systems over docx documents using GPT-3. Retrieval-augmented generation (RAG) with langchain framework is used. A Gradio interface is available. This is a jupyter notebook used for Q&A over docx documents using GPT-3 This library provides a simple and easy-to-use interface for building Q&A systems over docx documents using GPT-3. It takes care of all the details of loading and preprocessing the data, creating the retrieval chain, and generating answers.

Interface

Features

Simple and easy-to-use interface Supports docx documents Uses GPT-3 to generate answers Can be used to build Q&A systems over any domain

Requirements

Python 3.7+ langchain OpenAI API key Gradio

License

This library is licensed under the MIT License.

About

This is a simple implementation of Retrieval-augmented generation (RAG) on LLM.


Languages

Language:Jupyter Notebook 100.0%