From 07c5594ca5158ecbb0ac97f7c6bbb01121337e28 Mon Sep 17 00:00:00 2001 From: alexsin368 Date: Thu, 9 Jul 2026 16:53:03 -0700 Subject: [PATCH 1/4] update helm dependencies for Xeon on 3.4.0 Signed-off-by: alexsin368 --- deploy/helm/rag-values.yaml.example | 11 +++++++++++ deploy/helm/rag/Chart.yaml | 12 ++++++------ 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/deploy/helm/rag-values.yaml.example b/deploy/helm/rag-values.yaml.example index 0c0b3d9..008d59a 100644 --- a/deploy/helm/rag-values.yaml.example +++ b/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: {} diff --git a/deploy/helm/rag/Chart.yaml b/deploy/helm/rag/Chart.yaml index 5635a88..1a7e967 100644 --- a/deploy/helm/rag/Chart.yaml +++ b/deploy/helm/rag/Chart.yaml @@ -7,26 +7,26 @@ appVersion: "0.2.38" 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 From 2e914d6d33e78df0b4b90cb9f7a47494ace9dfaf Mon Sep 17 00:00:00 2001 From: alexsin368 Date: Mon, 13 Jul 2026 16:05:58 -0700 Subject: [PATCH 2/4] update dependencies in chart.lock Signed-off-by: alexsin368 --- deploy/helm/rag/Chart.lock | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/deploy/helm/rag/Chart.lock b/deploy/helm/rag/Chart.lock index e1260f7..6fb2254 100644 --- a/deploy/helm/rag/Chart.lock +++ b/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" From c9dfc2296c6873d7cf5f9dc303a36ebb0fa23b65 Mon Sep 17 00:00:00 2001 From: sauagarwa Date: Mon, 13 Jul 2026 20:07:38 -0400 Subject: [PATCH 3/4] fix: build RAG UI image locally in e2e tests to avoid pull failures The e2e tests fail on release PRs because the image tag is bumped before the release job builds and pushes the image. Build the image from source and load it into Kind so tests don't depend on a pre-pushed registry image. Also fix cleanup-branch to only delete the release branch when the PR is actually merged. Co-Authored-By: Claude Opus 4.6 --- .github/workflows/e2e-tests.yaml | 14 ++++++++++++++ .github/workflows/release.yml | 4 +++- 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/.github/workflows/e2e-tests.yaml b/.github/workflows/e2e-tests.yaml index 40ef75e..126d941 100644 --- a/.github/workflows/e2e-tests.yaml +++ b/.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 diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 2c9a4cc..582a845 100644 --- a/.github/workflows/release.yml +++ b/.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 From 8671fd8f0a4cdec0d6681f076b86f548017b69be Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Tue, 14 Jul 2026 00:24:19 +0000 Subject: [PATCH 4/4] chore: bump version to 0.2.46 --- deploy/helm/rag/Chart.yaml | 4 ++-- deploy/helm/rag/values.yaml | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/deploy/helm/rag/Chart.yaml b/deploy/helm/rag/Chart.yaml index 1a7e967..a2288a1 100644 --- a/deploy/helm/rag/Chart.yaml +++ b/deploy/helm/rag/Chart.yaml @@ -2,8 +2,8 @@ apiVersion: v2 name: rag description: A Helm chart for Kubernetes type: application -version: 0.2.38 -appVersion: "0.2.38" +version: 0.2.46 +appVersion: "0.2.46" dependencies: - name: pgvector diff --git a/deploy/helm/rag/values.yaml b/deploy/helm/rag/values.yaml index 27740f3..2d0b1cc 100644 --- a/deploy/helm/rag/values.yaml +++ b/deploy/helm/rag/values.yaml @@ -3,7 +3,7 @@ replicaCount: 1 image: repository: quay.io/rh-ai-quickstart/llamastack-dist-ui pullPolicy: Always - tag: latest-dev + tag: 0.2.46 service: type: ClusterIP