Dockerfile

# Base image with Python and common dependencies
FROM python:3.10-slim

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1

# Set working directory
WORKDIR /app

# Copy requirements file and install Python dependencies
COPY requirements.txt requirements.txt 
COPY extract_img_pdf.py extract_img_pdf.py
COPY templates/ /app/templates 
COPY .env .env

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    tesseract-ocr \
    poppler-utils \
    libgl1 \
    && apt-get clean && rm -rf /var/lib/apt/lists/*

RUN pip install -r requirements.txt
RUN mkdir -p /app/cache /app/data && chmod -R 777 /app/cache /app/data
RUN mkdir -p /app/OUTPUTS
RUN chmod -R 777 /app

# Expose the required port for HF Spaces
EXPOSE 7860

# Set the command to run your Flask app
CMD ["python", "extract_img_pdf.py"]