README.md

metadata

title: Medical Chatbot API
emoji: 🏥
colorFrom: blue
colorTo: green
sdk: docker
sdk_version: '1.0'
app_file: app/main.py
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Medical Chatbot API

A FastAPI-based medical chatbot API powered by LangChain and custom models.

Configuration

Environment Variables

Create a .env file with the following variables:

QDRANT_URL=your_qdrant_url
QDRANT_API_KEY=your_qdrant_api_key
HF_TOKEN=your_huggingface_token

Model Configuration

The application expects the following model structure:

models/
    ├── embeddings/
    └── llm/

Dependencies

Key dependencies include:

• LangChain ecosystem
• Qdrant for vector storage
• Unsloth for optimized model loading
• FastAPI for the web framework

Development Setup

1. Install dependencies:

pip install -r requirements.txt

2. Run the development server:

uvicorn app.main:app --reload --host 0.0.0.0 --port 7860

Docker Deployment

Build and run with Docker:

docker build -t medical-chatbot .
docker run -p 7860:7860 --env-file .env medical-chatbot

API Endpoints

• GET /health: Health check endpoint
• POST /chat: Chat endpoint

  {
    "question": "What are the symptoms of diabetes?",
    "context": "Optional medical context"
  }
  

Production Deployment

For Hugging Face Spaces:

1. Set repository secrets in Space settings
2. Deploy using the provided Dockerfile
3. Ensure model weights are properly configured