Readme.md

RAG Chatbot Application

Project Overview

A modular Retrieval Augmented Generation (RAG) chatbot application built with FastAPI, supporting multiple LLM providers and embedding models.

Project Structure

• config/: Configuration management
• src/: Main application source code
• tests/: Unit and integration tests
• data/: Document storage and ingestion

Prerequisites

• Python 3.9+
• pip
• (Optional) Virtual environment

Installation

1. Clone the repository

git clone https://your-repo-url.git
cd rag-chatbot

2. Create a virtual environment

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install dependencies

pip install -r requirements.txt

4. Set up environment variables

cp .env.example .env
# Edit .env with your credentials

Configuration

Environment Variables

• OPENAI_API_KEY: OpenAI API key
• OLLAMA_BASE_URL: Ollama server URL
• EMBEDDING_MODEL: Hugging Face embedding model
• CHROMA_PATH: Vector store persistence path
• DEBUG: Enable debug mode

Running the Application

Development Server

uvicorn src.main:app --reload

Production Deployment

gunicorn -w 4 -k uvicorn.workers.UvicornWorker src.main:app

Testing

pytest tests/

Features

• Multiple LLM Provider Support
• Retrieval Augmented Generation
• Document Ingestion
• Flexible Configuration
• FastAPI Backend

Contributing

1. Fork the repository
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request