Add CPU-only Docker image and fix release tag naming

- Add Dockerfile.cpu and compose.cpu.yaml for CPU-only deployments
- Use sentence-transformers[onnx] + CPU-only torch for ~4x smaller image
- Fix release script: separate git tags (engine-v*) from Docker tags (v*)
- Add CPU image to release build/push pipeline
- Update README with CPU deployment instructions

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

engine/Dockerfile.cpu

@@ -0,0 +1,36 @@
+FROM ubuntu:24.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3.12 python3.12-venv python3.12-dev python3-pip \
+    libpoppler-cpp-dev poppler-utils \
+    libgl1 libglib2.0-0 \
+    build-essential curl \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
+
+WORKDIR /app
+
+COPY pyproject.toml ./
+COPY kb/ kb/
+COPY main.py ./
+COPY VERSION ./
+
+RUN uv venv .venv && \
+    . .venv/bin/activate && \
+    uv pip install -e . && \
+    uv pip install "sentence-transformers[onnx]" && \
+    uv pip install --reinstall torch torchvision --index-url https://download.pytorch.org/whl/cpu
+
+ENV PATH="/app/.venv/bin:$PATH"
+ENV VIRTUAL_ENV="/app/.venv"
+ENV KB_DEVICE=cpu
+ENV KB_INGEST_DEVICE=cpu
+ENV KB_DATA_DIR=/data
+
+EXPOSE 8000
+VOLUME ["/data"]
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

engine/compose.cpu.yaml

@@ -0,0 +1,17 @@
+services:
+  kb-engine:
+    build:
+      context: .
+      dockerfile: Dockerfile.cpu
+    ports:
+      - "${KB_PORT:-8000}:8000"
+    volumes:
+      - ${KB_DATA_PATH:-./data}:/data
+    environment:
+      - KB_MODEL=${KB_MODEL:-all-MiniLM-L6-v2}
+      - KB_DEVICE=cpu
+      - KB_INGEST_DEVICE=cpu
+      - KB_API_KEY=${KB_API_KEY:-}
+      - KB_SEARCH_THRESHOLD=${KB_SEARCH_THRESHOLD:-0.01}
+      - HF_HUB_OFFLINE=${HF_HUB_OFFLINE:-}
+    restart: unless-stopped