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/

# 构建时预下载模型（需要实际转换才会触发 HuggingFace 模型下载）
RUN python -c "\
import tempfile, os; \
pdf = b'%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj\n2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj\n3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Parent 2 0 R/Contents 4 0 R/Resources<</Font<</F1 5 0 R>>>>>>endobj\n4 0 obj<</Length 44>>stream\nBT /F1 12 Tf 100 700 Td (hello) Tj ET\nendstream\nendobj\n5 0 obj<</Type/Font/Subtype/Type1/BaseFont/Helvetica>>endobj\nxref\n0 6\n0000000000 65535 f \n0000000009 00000 n \n0000000058 00000 n \n0000000115 00000 n \n0000000266 00000 n \n0000000360 00000 n \ntrailer<</Size 6/Root 1 0 R>>\nstartxref\n454\n%%EOF'; \
f = tempfile.NamedTemporaryFile(suffix='.pdf', delete=False); f.write(pdf); f.close(); \
from docling.document_converter import DocumentConverter; \
conv = DocumentConverter(); \
try: conv.convert(f.name) \
except: pass \
finally: os.unlink(f.name); \
print('Models pre-downloaded successfully')"

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"]