Dockerfile

FROM python:3.11-slim
WORKDIR /app

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

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

# Bake the embedding model at build time so a cold Space makes zero
# network calls for inference (fastembed caches under HF_HOME).
ENV HF_HOME=/app/models
RUN python3 -c "from fastembed import TextEmbedding; list(TextEmbedding('sentence-transformers/all-MiniLM-L6-v2').embed(['warm']))" \
    && echo "[BUILD] embedding model baked"

COPY app/ ./app/

EXPOSE 7860
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]