Dockerfile

# Use an official Python 3.10 slim image as the base image.
FROM python:3.10-slim

# Install system dependencies
# - tesseract-ocr: for OCR text extraction
# - poppler-utils: for PDF to image conversion (used by pdf2image)
# - gcc: required to compile any C extensions
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    poppler-utils \
    gcc \
    && rm -rf /var/lib/apt/lists/*

# Set the working directory in the container
WORKDIR /app

# Copy the requirements file first (so that dependency installation is cached)
COPY requirements.txt .

# Upgrade pip and install Python dependencies.
RUN pip install --upgrade pip
RUN pip install --no-cache-dir -r requirements.txt

# Copy the rest of the application code into the container
COPY app.py .

# Expose the default port (7860) used by Gradio
EXPOSE 7860

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