# Use an official Python runtime as the base image
FROM python:3.8-slim

# Set working directory
WORKDIR /app

# Install system dependencies for pdfplumber, pytesseract, and general compatibility
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

# Copy application code
COPY . /app

# Install Python dependencies, including sentencepiece for Pegasus
RUN pip install --no-cache-dir \
    flask \
    flask-cors \
    pdfplumber \
    pillow \
    pytesseract \
    numpy \
    torch \
    transformers \
    datasets \
    scikit-learn \
    gunicorn \
    sentencepiece

# Create uploads and cache directories with proper permissions
RUN mkdir -p /app/uploads /app/cache && \
    chmod -R 777 /app/uploads /app/cache

# Set environment variable for Hugging Face cache (using HF_HOME as per latest transformers recommendation)
ENV HF_HOME=/app/cache

# Expose port (Hugging Face Spaces typically uses 7860, but we'll stick to 5000 and adjust in app.py if needed)
EXPOSE 5000

# Run with Gunicorn
CMD ["gunicorn", "--bind", "0.0.0.0:5000", "app:app"]