# CLOAK model API: PII detection, document classification and Policy Copilot.
#
# Built by Hugging Face as a Docker Space (README front-matter: sdk: docker), and runs the
# same way on a customer's own host:
#
#   docker build -t cloak-model-api .
#   docker run -p 7860:7860 -e API_SECRET=<long random value> -e HF_TOKEN=<model read token> cloak-model-api
#
# Python 3.11.9 exactly: the document model is a scikit-learn pickle built on 3.11.9, and
# requirements.txt pins the libraries it was pickled with (see README).
FROM python:3.11.9-slim

# Shared libraries the OCR engine (rapidocr / OpenCV) loads. Nothing else is added.
RUN apt-get update \
 && apt-get install -y --no-install-recommends libgl1 libglib2.0-0 \
 && rm -rf /var/lib/apt/lists/*

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    PORT=7860 \
    HOME=/home/app \
    HF_HOME=/home/app/.cache/huggingface \
    MODEL_DIR=/home/app/model

WORKDIR /srv/cloak
COPY requirements.txt .
RUN pip install -r requirements.txt

# The code is owned by root and read-only to the service user; only $HOME (model cache) is writable.
COPY . .

# Hugging Face runs Docker Spaces as uid 1000.
RUN useradd --create-home --home-dir /home/app --uid 1000 app
USER app

EXPOSE 7860
# The first start downloads the models, hence the long start period.
HEALTHCHECK --interval=30s --timeout=5s --start-period=300s --retries=3 \
  CMD python -c "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:7860/health', timeout=4).status == 200 else 1)"

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