Dockerfile.airflow

FROM apache/airflow:2.10.5-python3.10

USER root
RUN apt-get update \
    && apt-get install -y --no-install-recommends \
        build-essential \
        libgomp1 \
        libglib2.0-0 \
        libgl1 \
        poppler-utils \
    && rm -rf /var/lib/apt/lists/*

USER airflow
WORKDIR /opt/airflow

COPY requirements.txt /tmp/requirements-app.txt
RUN pip install --no-cache-dir -r /tmp/requirements-app.txt --extra-index-url https://download.pytorch.org/whl/torch_stable.html

COPY cert_study_app /opt/airflow/cert_study_app
COPY pdf_parser_adaptive.py /opt/airflow/pdf_parser_adaptive.py