🩺 Scanalyze-Medical-Chatbot

A multilingual conversational AI API for medical question answering.
This API leverages state-of-the-art language models (Apollo-7B, AraBERT) with retrieval-augmented generation (RAG), built on FastAPI for blazing-fast performance.

It is designed to:

• Understand medical questions in Arabic and English
• Retrieve relevant context from a Qdrant vector database
• Generate accurate, context-aware responses using Hugging Face Transformers
• Run in cloud environments with Azure ML integration

Features

• Multilingual: Supports both Arabic and English medical queries.
• Large Language Models: Uses Apollo-7B for response generation.
• Contextual QA: Retrieves relevant documents from Qdrant to enhance answers.
• Secure Cloud Deployment: Integrated with Azure Machine Learning for model management.
• FastAPI: Lightweight, high-performance REST API.
• Response Cleanup: Removes repetitive or filler content for clean outputs.

Project Structure

• ├── app.py # FastAPI application with endpoints
• ├── model/ # Downloaded model from Azure ML
• ├── requirements.txt # Python dependencies
• ├── Dockerfile # (Optional) Containerization
• └── README.md # Documentation

---

Tech Stack

---

Setup Instructions

Clone the repository

git clone [https://github.com/<your-username>/Scanalyze-Medical-Chatbot.git](https://github.com/khalednabawey/Scanalyze-Medical-Chatbot)
cd Scanalyze-Medical-Chatbot

Install dependencies

• Create a virtual environment and install requirements:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

License

• This project is licensed under the MIT License. See LICENSE for details.