FROM python:3.12-slim

RUN useradd -m -u 1000 user
USER user

ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH \
    PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    ENCODE_DEVICE=cpu \
    ENCODE_RUNTIME_DIR=/home/user/app/outputs/runtime \
    ENCODE_CODE_INDEX_DIR=/home/user/app/outputs/indexes/bge_ft_va \
    ENCODE_MODEL_DIR=/home/user/app/outputs/models/bge_ft_va \
    ENCODE_PARTA_MODEL=/home/user/app/outputs/models/bge_ft_va \
    ENCODE_PARTA_EMB_DIR=/home/user/app/outputs/embeddings/bge_ft_va \
    OMP_NUM_THREADS=2 \
    OPENBLAS_NUM_THREADS=2 \
    MKL_NUM_THREADS=2 \
    TOKENIZERS_PARALLELISM=false \
    HF_HUB_DISABLE_TELEMETRY=1

# Submitted labels are the only runtime write, and /tmp dies with the container.
# This path is a read-write bucket mount (hf spaces volumes ls), so labels outlive
# every restart. Its own instruction: a comment cannot sit inside the ENV block
# above, where an indented # is an argument rather than a comment.
ENV ENCODE_ANNOT_DIR=/home/user/app/annotations

WORKDIR $HOME/app
# Both bucket mount points exist in the image before the mounts land on
# them; hf-mount fails on a missing directory.
RUN mkdir -p ./outputs ./annotations

COPY --chown=user src/requirements.txt ./requirements.txt
RUN python -m pip install --no-cache-dir --upgrade pip && \
    python -m pip install --no-cache-dir \
      --index-url https://download.pytorch.org/whl/cpu "torch==2.13.0" && \
    python -m pip install --no-cache-dir -r requirements.txt

COPY --chown=user src ./src

EXPOSE 7860
STOPSIGNAL SIGTERM

HEALTHCHECK --interval=30s --timeout=3s --start-period=10s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:7860/healthz', timeout=2).read()"

CMD ["uvicorn", "src.backend.app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]