Fix Multimodal & ProductivitySuite Issue (opea-project#1820)

1. add data-prep health check
2. add create conda env

Signed-off-by: letonghan <letong.han@intel.com>
Signed-off-by: cogniware-devops <ambarish.desai@cogniware.ai>

Author: letonghan

MultimodalQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -38,6 +38,11 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${MULTIMODAL_HUGGINGFACEHUB_API_TOKEN}
       MULTIMODAL_DATAPREP: true
       DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_MULTIMODALREDIS"
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 50
     restart: unless-stopped
   embedding-multimodal-bridgetower:
     image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower:${TAG:-latest}
@@ -140,11 +145,16 @@ services:
     image: ${REGISTRY:-opea}/multimodalqna:${TAG:-latest}
     container_name: multimodalqna-backend-server
     depends_on:
-      - redis-vector-db
-      - dataprep-multimodal-redis
-      - embedding
-      - retriever-redis
-      - lvm
+      redis-vector-db:
+        condition: service_started
+      dataprep-multimodal-redis:
+        condition: service_healthy
+      embedding:
+        condition: service_started
+      retriever-redis:
+        condition: service_started
+      lvm:
+        condition: service_started
     ports:
       - "8888:8888"
     environment:

ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml

@@ -32,6 +32,12 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       DATAPREP_TYPE: ${DATAPREP_TYPE}
       LOGFLAG: ${LOGFLAG}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 50
+    restart: unless-stopped
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
@@ -47,7 +53,7 @@ services:
       https_proxy: ${https_proxy}
       host_ip: ${host_ip}
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:6006/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 60
@@ -106,7 +112,7 @@ services:
       HF_HUB_ENABLE_HF_TRANSFER: 0
       host_ip: ${host_ip}
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:8808/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 60
@@ -147,7 +153,7 @@ services:
       HF_HUB_ENABLE_HF_TRANSFER: 0
       host_ip: ${host_ip}
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://${host_ip}:9009/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 100
@@ -176,15 +182,24 @@ services:
     image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
     container_name: chatqna-xeon-backend-server
     depends_on:
-      - redis-vector-db
-      - tei-embedding-service
-      - dataprep-redis-service
-      - retriever
-      - tei-reranking-service
-      - tgi_service
-      - embedding
-      - reranking
-      - llm
+      redis-vector-db:
+        condition: service_started
+      tei-embedding-service:
+        condition: service_healthy
+      dataprep-redis-service:
+        condition: service_healthy
+      retriever:
+        condition: service_started
+      tei-reranking-service:
+        condition: service_healthy
+      tgi_service:
+        condition: service_healthy
+      embedding:
+        condition: service_started
+      reranking:
+        condition: service_started
+      llm:
+        condition: service_started
     ports:
       - "8888:8888"
     environment:
@@ -218,10 +233,10 @@ services:
       HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       host_ip: ${host_ip}
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
-      retries: 30
+      retries: 100
     command: --model-id ${LLM_MODEL_ID_CODEGEN}
   llm_codegen:
     image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}

ProductivitySuite/tests/test_compose_on_xeon.sh

@@ -334,12 +334,18 @@ function validate_frontend() {
     cd $WORKPATH/ui/react
     local conda_env_name="OPEA_e2e"
     export PATH=${HOME}/miniforge3/bin/:$PATH
-#    conda remove -n ${conda_env_name} --all -y
-#    conda create -n ${conda_env_name} python=3.12 -y
+
+    if conda info --envs | grep -q "^${conda_env_name}[[:space:]]"; then
+        echo "[ TEST INFO ]: Conda environment '${conda_env_name}' exists. Activating..."
+    else
+        echo "[ TEST INFO ]: Conda environment '${conda_env_name}' not found. Creating..."
+        conda create -n "${conda_env_name}" python=3.12 -y
+    fi
+
     source activate ${conda_env_name}
     echo "[ TEST INFO ]: --------- conda env activated ---------"
 
-#    conda install -c conda-forge nodejs=22.6.0 -y
+    conda install -c conda-forge nodejs=22.6.0 -y
     npm install && npm ci
     node -v && npm -v && pip list