Enhance CI/CD Test (opea-project#2176)

Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: alexsin368 <alex.sin@intel.com>

Author: chensuyue

.github/workflows/manual-example-workflow.yml

@@ -30,7 +30,7 @@ on:
         type: string
       examples:
         default: "ChatQnA"
-        description: 'List of examples to test [AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,FaqGen,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA,AvatarChatbot,Text2Image,WorkflowExecAgent,DBQnA,EdgeCraftRAG,GraphRAG]'
+        description: 'List of examples to test [AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA,AvatarChatbot,Text2Image,WorkflowExecAgent,DBQnA,EdgeCraftRAG,GraphRAG]'
         required: true
         type: string
       tag:
@@ -88,12 +88,9 @@ jobs:
 
   build-comps-base:
     needs: [get-test-matrix]
-    strategy:
-      matrix:
-        node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
     uses: ./.github/workflows/_build_comps_base_image.yml
     with:
-      node: ${{ matrix.node }}
+      node: gaudi
       build: ${{ fromJSON(inputs.build) }}
       tag: ${{ inputs.tag }}
       opea_branch: ${{ inputs.opea_branch }}

.github/workflows/push-image-build.yml

@@ -63,6 +63,6 @@ jobs:
       fail-fast: false
     uses: ./.github/workflows/_example-workflow.yml
     with:
-      node: ${{ matrix.hardware }}
+      node: gaudi
       example: ${{ matrix.example }}
     secrets: inherit

.github/workflows/weekly-example-test.yml

@@ -39,12 +39,9 @@ jobs:
       attestations: read
       models: read
       security-events: read
-    strategy:
-      matrix:
-        node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
     uses: ./.github/workflows/_build_comps_base_image.yml
     with:
-      node: ${{ matrix.node }}
+      node: gaudi
 
   run-examples:
     permissions:

ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml

@@ -90,6 +90,11 @@ services:
       HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:9009/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
   chatqna-xeon-backend-server:
     image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}

ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml

@@ -95,6 +95,11 @@ services:
       HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:6042/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
   chatqna-xeon-backend-server:
     image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}

ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml

@@ -79,6 +79,11 @@ services:
       HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:9009/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
   chatqna-xeon-backend-server:
     image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}