# quantcore -- portfolio quant service for the DGX Spark (aarch64) and any x86-64 host.
# Build context is the repository root:  docker build -f deploy/Dockerfile -t local/quantcore:0.1 .
FROM python:3.12-slim

ENV PYTHONDONTWRITEBYTECODE=1 PYTHONUNBUFFERED=1 PIP_NO_CACHE_DIR=1 \
    QUANTCORE_DATA_DIR=/data QUANTCORE_CUOPT_URL=http://cuopt:5000 \
    OPENBLAS_NUM_THREADS=4 OMP_NUM_THREADS=4 MKL_NUM_THREADS=4
# BLAS threading: the innovation filter runs thousands of small (N x N) eigendecompositions;
# OpenBLAS with all 20 cores of the Spark is ~50x slower on those than with 1-4 threads.

RUN apt-get update && apt-get install -y --no-install-recommends curl tini \
 && rm -rf /var/lib/apt/lists/*

WORKDIR /app
COPY pyproject.toml README.md ./
COPY quantcore ./quantcore
RUN pip install .

VOLUME ["/data"]
EXPOSE 5001
HEALTHCHECK --interval=60s --timeout=10s --retries=2 CMD curl -sf http://localhost:5001/health >/dev/null || exit 1

ENTRYPOINT ["/usr/bin/tini", "--"]
CMD ["uvicorn", "quantcore.api.app:app", "--host", "0.0.0.0", "--port", "5001", "--workers", "1"]