FROM python:3.12-slim

WORKDIR /app

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

COPY backend/  ./backend/
COPY models/   ./models/
COPY scripts/download_hf_dataset.py ./scripts/download_hf_dataset.py

# Download the full 216M-variant dataset from HF Datasets at build time.
# CACHEBUST invalidates this layer when incremented, forcing a fresh download.
ARG CACHEBUST=12
RUN echo "Cache bust: $CACHEBUST" && python scripts/download_hf_dataset.py

EXPOSE 8000

CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8000"]