FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04

# Prevent interactive prompts during install
ENV DEBIAN_FRONTEND=noninteractive

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

WORKDIR /app

# Install PyTorch with CUDA 12.4 support FIRST (before requirements.txt)
# Default pip installs CPU-only PyTorch - must use pytorch.org index for GPU support
RUN --mount=type=cache,target=/root/.cache/pip \
    pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu124

# Install remaining Python dependencies (torch/torchvision already satisfied, with pip cache)
COPY requirements.txt /app/
RUN --mount=type=cache,target=/root/.cache/pip \
    pip3 install -r requirements.txt

COPY app.py /app/

# Default environment variables
ENV CLIP_MODEL=ViT-B/32

EXPOSE 5006

HEALTHCHECK --interval=30s --timeout=10s --start-period=30s --retries=3 \
    CMD curl -f http://localhost:5006/health || exit 1

CMD ["python3", "app.py"]