FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04

# Prevent interactive prompts during package installation
ENV DEBIAN_FRONTEND=noninteractive

# Install Python and system dependencies
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    python3-dev \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    wget \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy requirements first for better caching
COPY requirements.txt .

# Install Python dependencies (with pip cache for faster rebuilds)
RUN --mount=type=cache,target=/root/.cache/pip \
    pip3 install -r requirements.txt

# Download YOLO11s model (small, efficient)
RUN python3 -c "from ultralytics import YOLO; YOLO('yolo11s.pt')"

# Copy application code
COPY main.py .

# Expose port
EXPOSE 5002

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:5002/health')" || exit 1

# Run the service
CMD ["python3", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "5002"]