Dockerfile.nvidia

ARG NVIDIA_BASE=nvidia/cuda:12.6.3-cudnn-runtime-ubuntu22.04@sha256:46cb48a4abfbc40c836fe57bc05a07101b6458fffc63bbdfd6a50db98c9358bd
ARG UV_IMAGE=ghcr.io/astral-sh/uv@sha256:90bbb3c16635e9627f49eec6539f956d70746c409209041800a0280b93152823

FROM ${UV_IMAGE} AS uv-bin

FROM --platform=linux/amd64 ${NVIDIA_BASE} AS builder

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

WORKDIR /app

RUN apt-get update && \
    apt-get install -y --no-install-recommends python3 python3-pip python3-venv ca-certificates && \
    rm -rf /var/lib/apt/lists/*

COPY --from=uv-bin /uv /uvx /usr/local/bin/

COPY pyproject.toml uv.lock README.md ./
COPY src/ src/

RUN uv sync --python python3 --frozen --no-dev && \
    uv pip install --python .venv/bin/python "mineru[pipeline]==3.0.9"

FROM --platform=linux/amd64 ${NVIDIA_BASE} AS runtime

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    NEWSDOM_MINERU_BIN=mineru \
    NVIDIA_VISIBLE_DEVICES=all \
    NVIDIA_DRIVER_CAPABILITIES=compute,utility \
    PATH="/app/.venv/bin:${PATH}"

WORKDIR /app

RUN apt-get update && \
    apt-get install -y --no-install-recommends python3 ca-certificates && \
    rm -rf /var/lib/apt/lists/*

RUN useradd --create-home --home-dir /home/newsdom --shell /usr/sbin/nologin newsdom

COPY --from=builder /app /app

RUN chown -R newsdom:newsdom /app

USER newsdom

EXPOSE 8000

HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=5 \
  CMD python3 -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health').read()"

CMD ["uvicorn", "newsdom_api.main:app", "--host", "0.0.0.0", "--port", "8000"]