Giter VIP home page Giter VIP logo

onur-rgb / docuchat-rag-ai Goto Github PK

View Code? Open in Web Editor NEW
4.0 1.0 0.0 41 KB

DocuChat AI: An intelligent conversational tool, powered by RAG, seamlessly combining OpenAI, Langchain, and Milvus. Effortlessly answers document questions with a Gradio interface, no LLM fine-tuning required. Retrieves documents from a dynamic vector database for insightful conversations across formats.

License: MIT License

Python 100.00%

docuchat-rag-ai's Introduction

DocuChat AI: Retrieval Augmented Generation (RAG) System

Overview

DocuChat AI is an intelligent conversation tool powered by the Retrieval Augmented Generation (RAG) system. It seamlessly combines the capabilities of OpenAI's language model, Langchain, and Milvus to enable users to ask questions about a variety of documents without requiring fine-tuning of the Large Language Model (LLM). This system is designed to retrieve relevant documents from a specialized vector database and generate informative responses, facilitating intelligent conversations with a wide range of document formats. screenshot of program

Key Features

  • Document Compatibility: DocuChat AI supports a diverse set of document formats, including PDFs, text files, docx documents, and classic doc files. You can upload multiple documents at once.

  • RAG Integration: Leveraging OpenAI's RAG model, the system excels at retrieving pertinent documents from the vector database to answer user queries effectively.

  • Efficient Document Processing: The system efficiently processes uploaded documents, splitting and indexing them for optimal retrieval and generation.

  • User-Friendly Interface: The intuitive Gradio interface allows users to interact with DocuChat AI effortlessly.

How it Works

  1. Upload Documents: You can upload multiple documents of various formats, including PDFs, docx, doc, and text files.

  2. Ask Questions: Enter your questions or queries in natural language, and the system will provide informative responses.

  3. RAG Retrieval: Behind the scenes, DocuChat AI employs the RAG model to retrieve relevant documents from the vector database based on your questions.

  4. Intelligent Responses: The system generates intelligent responses using both the retrieved documents and the RAG model, enabling meaningful and context-aware conversations.

How to run

  1. Install and run a Milvus instance

  2. Make sure you have the necessary requirements to run the Python program

    pip install -r requirements.txt

  3. Set up your OpenAI API key by replacing "YOUR_API_KEY" in the app.py with your actual API key. You can obtain an API key by signing up at OpenAI's platform.

  4. Run the chatbot:

    python app.py

docuchat-rag-ai's People

Contributors

onur-rgb avatar

Stargazers

Xyll- avatar  avatar  avatar  avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.