Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.10-slim

# Set working directory
WORKDIR /app

# Install system dependencies (poppler-utils and tesseract-ocr)
RUN apt-get update && apt-get install -y \
    poppler-utils \
    tesseract-ocr \
    libtesseract-dev \
    && rm -rf /var/lib/apt/lists/*

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

# Copy the app code
COPY app.py .

# Expose the port Gradio will run on
EXPOSE 7860

# Set environment variables
ENV GRADIO_SERVER_NAME="0.0.0.0"
ENV GRADIO_SERVER_PORT=7860

# Run the Gradio app
CMD ["python", "app.py"]