deployment/Dockerfile.ml-inference

# =============================================================================
# Hardened Dockerfile — ML Inference Server
# =============================================================================

FROM python:3.12-slim AS builder

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

WORKDIR /build
COPY requirements.txt .
RUN pip install --no-cache-dir --require-hashes -r requirements.txt

COPY src/ /build/src/

# --- Runtime ---
FROM python:3.12-slim AS runtime

RUN apt-get update && apt-get install -y --no-install-recommends \
    libgomp1 && \
    rm -rf /var/lib/apt/lists/*

RUN groupadd -g 1000 mluser && \
    useradd -u 1000 -g mluser -s /bin/bash mluser

COPY --from=builder /usr/local/lib/python3.12/site-packages /usr/local/lib/python3.12/site-packages
COPY --from=builder /build/src/ /app/src/

WORKDIR /app

ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    TRANSFORMERS_CACHE=/cache/huggingface

USER mluser

EXPOSE 8000

HEALTHCHECK --interval=30s --timeout=10s --retries=3 \
    CMD ["python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]

ENTRYPOINT ["python", "-m", "vllm.entrypoints.openai.api_server", \
    "--host", "0.0.0.0", "--port", "8000", \
    "--model", "/models/latest"]