Dockerfile

# Use NVIDIA CUDA base image
FROM nvidia/cuda:11.8.0-runtime-ubuntu22.04

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    git \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first to leverage Docker cache
COPY requirements.txt .

# Install Python dependencies
RUN pip3 install --no-cache-dir -r requirements.txt

# Copy the rest of the application
COPY . .

# Create model directory
RUN mkdir -p /app/model/medical_llama_3b

# Expose port
EXPOSE 7860

# Set environment variables
ENV MODEL_PATH=/app/model/medical_llama_3b

# Command to run the application
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]