Dockerfile

# Extractor service for Hugging Face Spaces (Docker SDK).
# HF free CPU tier gives 16GB RAM — no more OOM from PDF/OCR rendering.
FROM python:3.13-slim

# System dep: tesseract for OCR (the engine shells out to the `tesseract` CLI).
RUN apt-get update \
    && apt-get install -y --no-install-recommends tesseract-ocr \
    && rm -rf /var/lib/apt/lists/*

# HF Spaces run containers as uid 1000; set up a matching non-root user + writable home.
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH \
    PYTHONUNBUFFERED=1 \
    EBS_WORK_DIR=/home/user/app/_work

WORKDIR /home/user/app

# Install Python deps first (better layer caching).
COPY --chown=user:user requirements.txt .
RUN pip install --no-cache-dir --user -r requirements.txt

# App code + a writable work dir for uploads/OCR temp images.
COPY --chown=user:user . .
RUN mkdir -p /home/user/app/_work

# HF Spaces expect the app on port 7860.
EXPOSE 7860
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]