Dockerfile

FROM python:3.11-slim
WORKDIR /app
ENV HF_HOME=/app/hf-cache \
    PYTHONUNBUFFERED=1

COPY requirements.txt .
RUN pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu \
 && pip install --no-cache-dir -r requirements.txt

# Bake BOTH switchable CLIP models into the image (Space disk is non-persistent at runtime).
RUN python - <<'PY'
from transformers import CLIPVisionModelWithProjection, CLIPImageProcessor
for mid in ("openai/clip-vit-base-patch32", "openai/clip-vit-large-patch14", "geolocal/StreetCLIP"):
    CLIPVisionModelWithProjection.from_pretrained(mid)
    CLIPImageProcessor.from_pretrained(mid)
PY

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