Dockerfile.serve

# RADAR serving image — CPU-capable, CUDA-ready when gpus=all is set.
FROM python:3.11-slim

LABEL org.opencontainers.image.title="anima-radar-serve"
LABEL org.opencontainers.image.source="https://github.com/RobotFlow-Labs/project_radar"

ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1

WORKDIR /app

RUN apt-get update \
 && apt-get install -y --no-install-recommends build-essential curl \
 && rm -rf /var/lib/apt/lists/*

COPY pyproject.toml README.md ./
COPY src ./src
COPY configs ./configs

RUN pip install --upgrade pip \
 && pip install "torch>=2.0" --index-url https://download.pytorch.org/whl/cpu \
 && pip install numpy pydantic pydantic-settings safetensors onnx fastapi "uvicorn[standard]" \
 && pip install -e .

ENV RADAR_CONFIG=/app/configs/default.toml
ENV RADAR_CHECKPOINT=/models/radar/best.pth

EXPOSE 8000

HEALTHCHECK --interval=30s --timeout=5s --start-period=15s --retries=3 \
  CMD curl -fsS http://localhost:8000/health || exit 1

CMD ["uvicorn", "anima_radar.serve:create_app", "--factory", "--host", "0.0.0.0", "--port", "8000"]