Release v0.2.46

.github/workflows/e2e-tests.yaml

@@ -265,6 +265,13 @@ jobs:
           kubectl get pods -A
           kubectl get crds | grep route || echo "Route CRD check"
 
+      - name: Build RAG UI image and load into Kind
+        run: |
+          IMAGE_TAG=$(grep '^version:' deploy/helm/rag/Chart.yaml | awk '{print $2}')
+          echo "Building image with tag: ${IMAGE_TAG}"
+          docker build -t quay.io/rh-ai-quickstart/llamastack-dist-ui:${IMAGE_TAG} frontend/ -f frontend/Containerfile
+          kind load docker-image quay.io/rh-ai-quickstart/llamastack-dist-ui:${IMAGE_TAG} --name rag-e2e
+
       - name: Add Helm repository
         run: |
           helm repo add rag-charts https://rh-ai-quickstart.github.io/ai-architecture-charts
@@ -602,6 +609,13 @@ jobs:
           kubectl wait --for condition=established --timeout=60s crd/routes.route.openshift.io
           echo "✅ All required CRDs installed successfully"
 
+      - name: Build RAG UI image and load into Kind
+        run: |
+          IMAGE_TAG=$(grep '^version:' deploy/helm/rag/Chart.yaml | awk '{print $2}')
+          echo "Building image with tag: ${IMAGE_TAG}"
+          docker build -t quay.io/rh-ai-quickstart/llamastack-dist-ui:${IMAGE_TAG} frontend/ -f frontend/Containerfile
+          kind load docker-image quay.io/rh-ai-quickstart/llamastack-dist-ui:${IMAGE_TAG} --name rag-e2e-ui
+
       - name: Add Helm repository
         run: |
           helm repo add rag-charts https://rh-ai-quickstart.github.io/ai-architecture-charts

.github/workflows/release.yml

@@ -8,7 +8,9 @@ on:
 
 jobs:
   cleanup-branch:
-    if: startsWith(github.event.pull_request.head.ref, 'release/')
+    if: |
+      github.event.pull_request.merged == true &&
+      startsWith(github.event.pull_request.head.ref, 'release/')
     runs-on: ubuntu-latest
     permissions:
       contents: write

deploy/helm/rag-values.yaml.example

@@ -169,6 +169,17 @@ global:
     #     operator: Exists
     #     effect: NoSchedule
 
+    # Example Xeon configurations:
+    # llama-3-2-3b-instruct:
+    #   id: meta-llama/Llama-3.2-3B-Instruct
+    #   enabled: true
+    #   device: "xeon"
+    #   args:
+    #   - --max-model-len
+    #   - "14336"
+    #   - --max-num-seqs
+    #   - "32"
+
   # MCP servers configuration
   mcp-servers: {}
 

deploy/helm/rag/Chart.lock

@@ -1,21 +1,21 @@
 dependencies:
 - name: pgvector
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.5.5
+  version: 0.5.6
 - name: llm-service
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.5.9
+  version: 0.5.10
 - name: configure-pipeline
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.5.8
+  version: 0.5.9
 - name: ingestion-pipeline
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.7.4
+  version: 0.7.5
 - name: llama-stack
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.8.6
+  version: 0.8.7
 - name: mcp-servers
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.5.15
-digest: sha256:3c8f3da85c35fec034c56cd43813e80ca7c223354de23b46747e9fcc44c527e0
-generated: "2026-06-09T09:12:30.763414-04:00"
+  version: 0.5.18
+digest: sha256:e0a207e133ea7ff565c5431f00272829ae9d041ac0e4869472eb06ba6b44ba58
+generated: "2026-07-13T15:48:14.880319387-07:00"

deploy/helm/rag/Chart.yaml

@@ -2,31 +2,31 @@ apiVersion: v2
 name: rag
 description: A Helm chart for Kubernetes
 type: application
-version: 0.2.45
-appVersion: "0.2.45"
+version: 0.2.46
+appVersion: "0.2.46"
 
 dependencies:
   - name: pgvector
-    version: 0.5.5
+    version: 0.5.6
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: pgvector.enabled
   - name: llm-service
-    version: 0.5.9
+    version: 0.5.10
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: llm-service.enabled
   - name: configure-pipeline
-    version: 0.5.8
+    version: 0.5.9
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: configure-pipeline.enabled
   - name: ingestion-pipeline
-    version: 0.7.4
+    version: 0.7.5
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: ingestion-pipeline.enabled
   - name: llama-stack
-    version: 0.8.6
+    version: 0.8.7
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: llama-stack.enabled
   - name: mcp-servers
-    version: 0.5.15
+    version: 0.5.18
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: mcp-servers.enabled

deploy/helm/rag/values.yaml

@@ -3,7 +3,7 @@ replicaCount: 1
 image:
   repository: quay.io/rh-ai-quickstart/llamastack-dist-ui
   pullPolicy: Always
-  tag: 0.2.45
+  tag: 0.2.46
 
 service:
   type: ClusterIP