Dockerfile

# Fast Space image: prebuilt SPA + prebuilt mmap index (no Node, no Kaikki parse).
# Index is fetched from the published HF dataset artifact during image build.

FROM python:3.12-slim-bookworm

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PYTHONPATH=/app \
    PORT=7860 \
    MALLOC_ARENA_MAX=2

WORKDIR /app

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

COPY requirements.space.txt ./requirements.txt
RUN pip install --no-cache-dir -r requirements.txt \
    && find /usr/local -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null || true

COPY backend ./backend
COPY scripts/space_entrypoint.sh ./scripts/space_entrypoint.sh
RUN chmod +x ./scripts/space_entrypoint.sh

# Prebuilt Vite output (built on the deploy host; keeps image builds off Node).
COPY frontend/dist ./frontend/dist

# Pinned prebuilt index artifact (update when republishing the dataset).
ARG INDEX_URL=https://huggingface.co/datasets/Mongoosetross/reverse-etymology-index/resolve/main/index.tar.zst
ARG INDEX_SHA256=51f60c37cb3219268f7852363860f7d17650cf2079888de75573f28412bb6d71
RUN mkdir -p data/index \
    && curl -fsSL "$INDEX_URL" -o /tmp/index.tar.zst \
    && if [ -n "$INDEX_SHA256" ]; then echo "$INDEX_SHA256  /tmp/index.tar.zst" | sha256sum -c -; fi \
    && tar -I zstd -xf /tmp/index.tar.zst -C data/index \
    && rm -f /tmp/index.tar.zst \
    && test -f data/index/atlas.sqlite \
    && test -f data/index/mmap/rev_off.i32

EXPOSE 7860
CMD ["./scripts/space_entrypoint.sh"]