Dockerfile

FROM python:3.9-slim

WORKDIR /app

# Install system dependencies for tesseract and pdf processing
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    poppler-utils \
    libmagic1 \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Create a non-root user to run the application
RUN groupadd -r appuser && useradd -r -g appuser appuser

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

# Copy application code
COPY . .

# Set environment variables
ENV PYTHONUNBUFFERED=1

# Create directories with proper permissions
RUN mkdir -p /tmp/uploads /tmp/logs && \
    chmod 777 /tmp/uploads /tmp/logs && \
    chown -R appuser:appuser /app

# Expose port for the Flask application
EXPOSE 7860

# Switch to non-root user
USER appuser

# Start the application with gunicorn
CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]