AI-Tor is an intelligent medical chatbot web application that allows users to upload medical images such as prescriptions, lab reports, or scans—and ask context-based questions.
AI-Tor is a smart medical chatbot that allows users to upload medical images (such as prescriptions, lab reports, or scan results), ask questions about them, and receive helpful, AI-generated responses. It combines OCR and LLMs to make medical documents more understandable to the average person.
- 📸 Upload medical images (PNG, JPG)
- 🔍 Extracts text using Tesseract OCR
- 💬 Accepts natural language questions about the document
- 🤖 Uses LLMs like
llama3-8b-8192to answer queries - 🎨 Clean UI with Tailwind CSS
- 🧾 Display of AI response in markdown format
Coming soon — or run locally to see it in action!
| Layer | Technology |
|---|---|
| Frontend | HTML, TailwindCSS, JS |
| Backend | FastAPI (Python) |
| OCR | Tesseract |
| AI Model | Groq API (LLaMA 3) |
| Templates | Jinja2 |
- Python 3.8+
- Tesseract OCR installed
- Groq API key
git clone https://github.com/yourusername/medical-bot.git
cd medical-botpython -m venv .venv
source .venv/bin/activatepip install -r requirements.txtIf you don’t have a
requirements.txt, install manually:
pip install fastapi uvicorn jinja2 python-multipart pytesseract pillow python-dotenv requestsCreate a file named .env in the root:
GROQ_API_KEY=your-groq-api-key
LLM_MODEL=llama3-8b-8192uvicorn app:app --reloadThen open: http://127.0.0.1:8000
medical-bot/
├── app.py
├── main.py
├── templates/
│ └── index.html
├── static/
├── .env
└── README.md
- 📄 PDF and multi-image support
- 🗂️ History of previous responses
- 🌍 Multilingual OCR
- 📱 Mobile-friendly responsive UI
This tool is for educational and experimental purposes only. It is not a substitute for professional medical advice, diagnosis, or treatment.
Rohan Kumar
If you like this project, consider starring the repo ⭐ to support it!