Dockerfile

# Use a lightweight Python base image
FROM python:3.10-slim

# Create a non-root user with UID 1000 (Required by Hugging Face Spaces)
RUN useradd -m -u 1000 user

# Install system dependencies for OCR and PDF processing
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-spa \
    tesseract-ocr-ara \
    tesseract-ocr-chi-sim \
    tesseract-ocr-ita \
    tesseract-ocr-msa \
    poppler-utils \
    libgl1 \
    && rm -rf /var/lib/apt/lists/*

# Switch to the non-root user
USER user
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH

# Set the working directory
WORKDIR $HOME/app

# Copy requirements and install
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the rest of your app files
COPY --chown=user . .

# Hugging Face Spaces expose port 7860 by default
EXPOSE 7860

# Start the FastAPI app
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]