🩺 RAG Medical AI Assistant

An intelligent medical chatbot powered by Retrieval-Augmented Generation (RAG) that helps healthcare professionals and patients get accurate answers from uploaded medical documents.

✨ Features

• 📄 PDF Document Upload: Upload multiple medical PDFs to build your knowledge base
• 🤖 AI-Powered Chat: Ask questions and get contextual answers from your documents
• 🔍 Source Attribution: See which documents your answers come from
• 💾 Chat History: Download your conversation history for record keeping
• ⚡ Real-time Processing: Fast document indexing and query responses
• 🌐 Web Interface: Clean, intuitive Streamlit frontend

🏗️ Architecture

This project uses a modern microservices architecture:

• Frontend: Streamlit web application (client/)
• Backend: FastAPI REST API (server/)
• Vector Database: Pinecone for document embeddings
• LLM: Google Generative AI (Gemini)
• Embeddings: Google Generative AI Embeddings

🚀 Quick Start

Prerequisites

• Python 3.13+
• UV package manager
• Pinecone API key
• Google AI API key

Installation

1. Clone the repository

   git clone <your-repo-url>
   cd RAGMedicalAIAssistant

2. Set up virtual environment

   uv venv
   .venv\Scripts\activate  # Windows
   # or
   source .venv/bin/activate  # macOS/Linux

3. Install dependencies

   uv pip install -r requirements.txt

4. Environment setup Create a .env file in the root directory:

   PINECONE_API_KEY=your_pinecone_api_key
   PINECONE_INDEX_NAME=your_index_name
   GOOGLE_API_KEY=your_google_ai_api_key

Running the Application

1. Start the FastAPI backend

   uvicorn main:app --reload

   Backend will be available at http://localhost:8000

2. Start the Streamlit frontend

   cd client
   streamlit run app.py

   Frontend will be available at http://localhost:8501

📱 Usage

1. Upload Documents: Use the sidebar to upload medical PDF documents
2. Wait for Processing: Documents are automatically processed and indexed
3. Ask Questions: Type your medical questions in the chat interface
4. Get Answers: Receive AI-generated responses based on your documents
5. Download History: Save your chat history for future reference

🛠️ Project Structure

RAGMedicalAIAssistant/
├── client/                 # Streamlit frontend
│   ├── components/         # UI components
│   │   ├── chatUI.py      # Chat interface
│   │   ├── upload.py      # File upload component
│   │   └── history_download.py
│   ├── utils/             # Client utilities
│   │   └── api.py         # API client functions
│   ├── config.py          # Client configuration
│   └── app.py             # Main Streamlit app
├── server/                # FastAPI backend
│   ├── routes/            # API endpoints
│   ├── modules/           # Core business logic
│   ├── middlewares/       # Custom middleware
│   └── logger.py          # Logging configuration
├── main.py                # FastAPI application entry point
├── requirements.txt       # Python dependencies
└── README.MD             # This file

🔧 API Endpoints

• POST /upload_pdfs/ - Upload and process PDF documents
• POST /ask - Submit questions and get AI responses

🧪 Technologies Used

• Frontend: Streamlit, Python
• Backend: FastAPI, Uvicorn
• AI/ML: LangChain, Google Generative AI
• Vector Database: Pinecone
• Document Processing: PyPDF
• Environment: UV, Python-dotenv

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🚨 Disclaimer

This tool is for educational and informational purposes only. Always consult with qualified healthcare professionals for medical advice and decisions.

📞 Support

If you encounter any issues or have questions, please open an issue on GitHub.

---

Built with ❤️ for the healthcare community