add the fix to workflow

Author: Radovan Fuchs

.github/workflows/e2e_tests.yaml

@@ -114,6 +114,20 @@ jobs:
           echo "=== lightspeed-stack.yaml ==="
           grep -A 3 "llama_stack:" lightspeed-stack.yaml
 
+      - name: Cache HuggingFace embedding model
+        uses: actions/cache@v4
+        with:
+          path: /tmp/hf-cache
+          key: hf-sentence-transformers-all-mpnet-base-v2
+
+      - name: Pre-download HuggingFace embedding model
+        env:
+          HF_HOME: /tmp/hf-cache
+        run: |
+          pip install -q sentence-transformers
+          python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('sentence-transformers/all-mpnet-base-v2')"
+          echo "HF_CACHE_PATH=/tmp/hf-cache" >> $GITHUB_ENV
+
       - name: Docker Login for quay access
         if: matrix.mode == 'server'
         env:

deploy/lightspeed-stack/Containerfile

@@ -123,16 +123,6 @@ RUN mkdir -p /opt/app-root/src/.llama/storage /opt/app-root/src/.llama/providers
 RUN mkdir -p /opt/app-root/src/.cache/huggingface && \
     chown -R 1001:1001 /opt/app-root/src/.cache
 
-# Pre-cache embedding model so HF_HUB_OFFLINE=1 works at runtime.
-# ARG defaults to 0: hermetic Konflux builds have no outbound network.
-# docker-compose passes PREBAKE_HF_MODELS=1 for local/CI builds.
-ARG PREBAKE_HF_MODELS=0
-RUN [ "${PREBAKE_HF_MODELS}" != "1" ] || \
-    ( HF_HOME=/opt/app-root/src/.cache/huggingface \
-      /app-root/.venv/bin/python -c \
-          "from sentence_transformers import SentenceTransformer; SentenceTransformer('sentence-transformers/all-mpnet-base-v2')" && \
-      chown -R 1001:1001 /opt/app-root/src/.cache/huggingface )
-
 # Add executables from .venv to system PATH
 ENV PATH="/app-root/.venv/bin:$PATH"
 

deploy/llama-stack/test.containerfile

@@ -37,11 +37,6 @@ RUN mkdir -p /opt/app-root/src/.llama/storage \
     chown -R 1001:0 /opt/app-root && \
     chmod -R 775 /opt/app-root
 
-# Pre-cache embedding model so HF_HUB_OFFLINE=1 works at runtime.
-RUN HF_HOME="/opt/app-root/src/.cache/huggingface" \
-    /opt/app-root/.venv/bin/python -c \
-        "from sentence_transformers import SentenceTransformer; SentenceTransformer('sentence-transformers/all-mpnet-base-v2')"
-
 # Copy enrichment scripts for runtime config enrichment
 COPY src/llama_stack_configuration.py /opt/app-root/llama_stack_configuration.py
 COPY scripts/llama-stack-entrypoint.sh /opt/app-root/enrich-entrypoint.sh

docker-compose-library.yaml

@@ -4,8 +4,6 @@ services:
     build:
       context: .
       dockerfile: deploy/lightspeed-stack/Containerfile
-      args:
-        PREBAKE_HF_MODELS: "1"
     platform: linux/amd64
     container_name: lightspeed-stack
     ports:
@@ -21,6 +19,7 @@ services:
       - ./run.yaml:/app-root/run.yaml:Z
       - ${GCP_KEYS_PATH:-./tmp/.gcp-keys-dummy}:/opt/app-root/.gcp-keys:ro
       - ./tests/e2e/rag:/opt/app-root/src/.llama/storage/rag:Z
+      - ${HF_CACHE_PATH:-./tmp/.hf-cache}:/opt/app-root/src/.cache/huggingface
       - ./tests/e2e/secrets/mcp-token:/tmp/mcp-token:ro,z
       - ./tests/e2e/secrets/invalid-mcp-token:/tmp/invalid-mcp-token:ro,z
     environment:

docker-compose.yaml

@@ -21,6 +21,7 @@ services:
       - llama-storage:/opt/app-root/src/.llama/storage
       - ./tests/e2e/rag:/opt/app-root/src/.llama/storage/rag:z
       - mock-tls-certs:/certs:ro
+      - ${HF_CACHE_PATH:-./tmp/.hf-cache}:/opt/app-root/src/.cache/huggingface
     environment:
       - BRAVE_SEARCH_API_KEY=${BRAVE_SEARCH_API_KEY:-}
       - TAVILY_SEARCH_API_KEY=${TAVILY_SEARCH_API_KEY:-}