fix(ocr): install torchvision from CPU index alongside torch

torchvision installed from PyPI expects CUDA torch operator
registrations. Installing from the CPU whl index ensures torchvision
matches the CPU-only torch build. Fixes 'torchvision::nms does not
exist' RuntimeError on startup.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

ocr-service/Dockerfile

@@ -9,8 +9,10 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     && rm -rf /var/lib/apt/lists/*
 
 # PyTorch CPU-only — separate layer; the whl/cpu index strips all CUDA variants (~2 GB saved)
+# torchvision must also come from the CPU index to match torch's operator registrations
 RUN pip install --no-cache-dir \
     torch==2.7.1 \
+    torchvision==0.22.1 \
     --index-url https://download.pytorch.org/whl/cpu
 
 COPY requirements.txt .