FROM python:3.11-slim

WORKDIR /app

# 系统依赖（OCR、图像处理所需的共享库）
RUN apt-get update && apt-get install -y --no-install-recommends \
    libgl1 libglib2.0-0 libsm6 libxext6 libxrender1 \
    && rm -rf /var/lib/apt/lists/*

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY app/ ./app/
COPY scripts/ ./scripts/

# 构建时预下载模型（实际执行一次 PDF 转换触发 HuggingFace 模型下载）
RUN python scripts/preload_models.py

EXPOSE 3007

HEALTHCHECK --interval=30s --timeout=10s --retries=3 --start-period=120s \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:3007/health')" || exit 1

CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "3007"]