An AI-powered clinical decision support tool designed to help medical practitioners quickly identify and analyze potential drug-drug and drug-disease interactions. Leveraging a Retrieval-Augmented Generation (RAG) system, this application queries a knowledge base built from official FDA drug label data to provide evidence-based insights.

• AI-Powered Analysis: Uses a RAG system to provide answers based on FDA data.
• Dual Interaction Modes: Offers both a simple "Prompt Mode" and a guided "AI Mode" for structured queries.
• User Authentication: Secure login and signup for personalized history.
• Persistent History: Saves and loads user query history from local storage.
• PDF Document Upload: Extracts text from uploaded medical documents for analysis.

• Frontend: React.js, Vite
• Backend: Python, Flask
• AI / ML: LangChain, FAISS, Sentence Transformers, Replicate
• Database: FAISS Vector Store, SQLite (optional)

Follow these instructions to set up and run the project on your local machine.

Make sure you have the following installed on your system:

• Python (version 3.10+)
• Node.js (version 18.x or later)

1. Clone the repository:

   git clone [https://github.com/YourUsername/Comorbid-App.git](https://github.com/YourUsername/Comorbid-App.git)
   cd Comorbid-App

2. Backend Setup:

   # Navigate to the backend directory
   cd backend
   
   # Create and activate a virtual environment
   python -m venv venv
   source venv/bin/activate  # On macOS/Linux
   # venv\Scripts\activate    # On Windows
   
   # Install Python dependencies
   pip install -r requirements.txt

3. Frontend Setup:

   # Navigate to the frontend directory from the root
   cd frontend
   
   # Install Node.js dependencies
   npm install

The backend requires an .env file to store API keys and other configuration.

1. In the /backend directory, create a file named .env.

2. Add the necessary variables. It should look something like this:

   # Example .env file
   REPLICATE_API_TOKEN="your_replicate_api_token_here"
   

You need to run the backend and frontend servers in two separate terminals.

1. Build the Vector Database (One-time setup): Before the first run, you must create the FAISS index from your source data.

   # From the /backend directory, with venv active
   python create_database.py

2. Start the Backend Server:

   # From the /backend directory, with venv active
   python app.py

   The backend will now be running on http://127.0.0.1:5000.

3. Start the Frontend Server:

   # From the /frontend directory
   npm run dev

   Open your browser and navigate to the URL provided (usually http://localhost:5173).

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

Devang - GitHub Profile