Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.9-slim

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive

# Install Tesseract OCR and its dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    libleptonica-dev \
    pkg-config \
    poppler-utils \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

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

# Copy the application code
COPY app.py .

# Expose the port Streamlit will run on
EXPOSE 7860

# Command to run the application
CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]