Dockerfile

# UPDATE: Changed from 3.9 to 3.11 to support newer NumPy/Pandas versions
FROM python:3.11-slim

# Set the working directory in the container
WORKDIR /app

# Install system dependencies
# Added 'poppler-utils' (required for pdf2image)
# Added 'libgl1' & 'libglib2.0-0' (required for OpenCV headless)
# Added 'curl' just in case, though we use python requests for healthcheck
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-deu \
    tesseract-ocr-fra \
    tesseract-ocr-spa \
    tesseract-ocr-por \
    tesseract-ocr-ita \
    tesseract-ocr-rus \
    tesseract-ocr-chi-sim \
    tesseract-ocr-jpn \
    tesseract-ocr-kor \
    poppler-utils \
    libgl1 \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

# Upgrade pip, setuptools, and wheel before installing deps
COPY requirements.txt .
RUN pip install --upgrade pip setuptools wheel \
    && pip install --default-timeout=100 --retries=10 --no-cache-dir -r requirements.txt

# Copy the current directory contents into the container
COPY . .

# Create a non-root user for security (Production Best Practice)
RUN useradd -m appuser && chown -R appuser /app
USER appuser

# Healthcheck as requested
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:8000/api/v1/ping', timeout=5)" || exit 1

# Run the application
CMD ["python", "main.py"]