Agada - AI Medical Assistant

Agada is a hybrid AI-powered medical assistant designed to provide accurate information about medicines, their uses, side effects, and pricing in India. It combines a curated local knowledge base with real-time web search and Large Language Model (LLM) capabilities to deliver reliable responses.

🚀 Features

• Hybrid Search Engine: Prioritizes local verified data (Indian Medicine Dataset) and falls back to real-time web search for the latest information.
• Intelligent Query Processing: Uses Groq (LLM) to understand natural language queries and format responses.
• Real-time Web Search: Integrated with DuckDuckGo (via ddgs) to fetch current medical data when local data is insufficient.
• Indian Context: Specifically tuned for Indian medicine brands, substitutes, and pricing (₹).
• Deployment Ready: Configured for serverless deployment on Vercel.

🛠️ Tech Stack

• Backend: Django 6.0.2
• AI/LLM: Groq API (Llama 3 / Mixtral)
• Search: Custom CSV-based Knowledge Base + DuckDuckGo (ddgs)
• Database: Supabase (Optional for cloud persistence)
• Static Files: Whitenoise

📦 Installation

1. Clone the repository

   git clone https://github.com/Vigneshwaren333/Agada.git
   cd Agada

2. Create and activate a virtual environment

   python -m venv venv
   # Windows
   .\venv\Scripts\activate
   # macOS/Linux
   source venv/bin/activate

3. Install dependencies

   pip install -r requirements.txt

4. Set up Environment Variables Create a .env file in the root directory:

   GROQ_API_KEY=your_groq_api_key
   SUPABASE_URL=your_supabase_url  # Optional
   SUPABASE_KEY=your_supabase_key  # Optional
   DJANGO_SECRET_KEY=your_django_secret
   DEBUG=True

5. Run Migrations

   python manage.py migrate

6. Start the Development Server

   python manage.py runserver

📂 Project Structure

• agent.py: Core logic for the Hybrid Medical Agent.
• knowledge_base.py: Manages local dataset (CSV) and Supabase interactions.
• web_search.py: Handles real-time web queries using ddgs.
• data/medicines.csv: The local dataset containing Indian medicine information.
• core/: Django app containing views and API endpoints.

🚀 Deployment (Vercel)

This project is configured for Vercel deployment.

1. Install Vercel CLI: npm i -g vercel
2. Deploy:

   vercel

   Note: Ensure you add your Environment Variables in the Vercel Project Settings.

⚠️ Disclaimer

This tool is for informational purposes only and is not a substitute for professional medical advice, diagnosis, or treatment. Always consult with a qualified healthcare provider.