Dockerfile

FROM python:3.11-slim

# System dependencies for OCR (tesseract + ghostscript) and PDF rendering
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    tesseract-ocr-eng \
    ghostscript \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender1 \
    && rm -rf /var/lib/apt/lists/*

# Create a non-root user (Hugging Face Spaces requirement)
RUN useradd -m -u 1000 user
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH

WORKDIR /home/user/app

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Ensure the non-root user owns the app directory
RUN chown -R user:user /home/user/app

USER user

# Hugging Face Spaces expects port 7860
EXPOSE 7860

CMD ["python", "app.py", "--host", "0.0.0.0", "--port", "7860"]