Dockerfile

# infra/hf_spaces/reranker/Dockerfile
# Bakes cross-encoder/ms-marco-MiniLM-L-6-v2 weights into the image at build time.

FROM python:3.11-slim

WORKDIR /app

ENV HF_HOME=/app/model_cache \
    PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1

RUN pip install --no-cache-dir \
    fastapi>=0.115.0 \
    uvicorn[standard]>=0.29.0 \
    sentence-transformers>=3.0.0

# Bake model weights into this Docker layer.
RUN python -c "\
from sentence_transformers import CrossEncoder; \
CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2', cache_folder='/app/model_cache')"

COPY app.py .

EXPOSE 7860

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