PDF-Extractor / Dockerfile
Archie0099's picture
Add PDF extractor app and Dockerfile
b9d34d8 verified
Raw
History Blame Contribute Delete
1.23 kB
FROM python:3.10-slim
# System libraries PaddleOCR / OpenCV need at runtime.
RUN apt-get update && apt-get install -y --no-install-recommends \
libgl1 \
libglib2.0-0 \
libgomp1 \
&& rm -rf /var/lib/apt/lists/*
# Hugging Face Spaces runs the container as uid 1000. Create that user and a
# writable home so model weights and caches have somewhere to live.
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
PATH=/home/user/.local/bin:$PATH \
PYTHONUNBUFFERED=1
WORKDIR /home/user/app
# Install Python dependencies first so the layer caches across code changes.
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir --upgrade pip \
&& pip install --no-cache-dir -r requirements.txt
# Pre-download the English PP-OCRv4 weights at build time so the first visitor
# does not wait for the download. A network blip here is non-fatal: the app
# downloads them on first use anyway.
RUN python -c "from paddleocr import PaddleOCR; PaddleOCR(use_angle_cls=True, lang='en', show_log=False)" \
|| echo "weight prewarm skipped; will download at runtime"
# Application code.
COPY --chown=user . .
EXPOSE 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]