FROM python:3.9-slim

# Install system dependencies for OCR and PDF processing
RUN apt-get update --fix-missing && \
    apt-get install -y --no-install-recommends \
    poppler-utils \
    tesseract-ocr \
    tesseract-ocr-eng \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY . .

CMD ["python", "app.py"]