# Use the official Python image as a base image
FROM python:3.9-slim

# Install system dependencies for Tesseract OCR and Gradio
RUN apt-get update && \
    apt-get install -y \
    tesseract-ocr \
    ghostscript \
    libtesseract-dev \ 
    libleptonica-dev \
    pkg-config \
    poppler-utils \
    && apt-get clean

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

# Copy your Gradio application code into the container
ENV PATH="/usr/local/bin:${PATH}"

# Specify the command to run your Gradio app
CMD ["python", "app.py"]