Enable dataprep health check for examples (#1800)

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

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

@@ -20,7 +20,7 @@ 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: 100
@@ -42,7 +42,7 @@ 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: 100
@@ -84,7 +84,10 @@ services:
     image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
     container_name: codegen-xeon-backend-server
     depends_on:
-      - llm-base
+      llm-base:
+        condition: service_started
+      dataprep-redis-server:
+        condition: service_healthy
     ports:
       - "7778:7778"
     environment:
@@ -139,6 +142,11 @@ services:
       INDEX_NAME: ${INDEX_NAME}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       LOGFLAG: true
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
     restart: unless-stopped
   tei-embedding-serving:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -156,7 +164,7 @@ services:
       host_ip: ${host_ip}
       HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
       timeout: 6s
       retries: 48

CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -23,7 +23,7 @@ services:
       USE_FLASH_ATTENTION: true
       FLASH_ATTENTION_RECOMPUTE: true
     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: 100
@@ -53,7 +53,7 @@ services:
       NUM_CARDS: ${NUM_CARDS:-1}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 100
@@ -99,7 +99,10 @@ services:
     image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
     container_name: codegen-gaudi-backend-server
     depends_on:
-      - llm-base
+      llm-base:
+        condition: service_started
+      dataprep-redis-server:
+        condition: service_healthy
     ports:
       - "7778:7778"
     environment:
@@ -155,6 +158,11 @@ services:
       INDEX_NAME: ${INDEX_NAME}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       LOGFLAG: true
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
     restart: unless-stopped
   tei-embedding-serving:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -172,7 +180,7 @@ services:
       host_ip: ${host_ip}
       HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
       timeout: 6s
       retries: 48

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

@@ -20,8 +20,6 @@ services:
         condition: service_healthy
     ports:
       - "6007:5000"
-      - "6008:6008"
-      - "6009:6009"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
@@ -32,6 +30,12 @@ services:
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       LOGFLAG: ${LOGFLAG}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
+    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"
@@ -48,7 +52,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       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 +110,7 @@ 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
@@ -134,11 +138,18 @@ services:
     image: ${REGISTRY:-opea}/doc-index-retriever:${TAG:-latest}
     container_name: doc-index-retriever-server
     depends_on:
-      - redis-vector-db
+      redis-vector-db:
-      - tei-embedding-service
+        condition: service_started
-      - embedding
+      tei-embedding-service:
-      - retriever
+        condition: service_healthy
-      - reranking
+      embedding:
+        condition: service_started
+      dataprep-redis-service:
+        condition: service_healthy
+      retriever:
+        condition: service_started
+      reranking:
+        condition: service_started
     ports:
       - "8889:8889"
     environment:

DocIndexRetriever/docker_compose/intel/cpu/xeon/compose_milvus.yaml

@@ -78,6 +78,11 @@ services:
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       LOGFLAG: ${LOGFLAG}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
     restart: unless-stopped
     depends_on:
       tei-embedding-service:
@@ -105,7 +110,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       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
@@ -167,7 +172,7 @@ 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
@@ -199,11 +204,18 @@ services:
     image: ${REGISTRY:-opea}/doc-index-retriever:${TAG:-latest}
     container_name: doc-index-retriever-server
     depends_on:
-      - milvus-standalone
+      milvus-standalone:
-      - tei-embedding-service
+        condition: service_healthy
-      - embedding
+      tei-embedding-service:
-      - retriever
+        condition: service_healthy
-      - reranking
+      embedding:
+        condition: service_started
+      dataprep-milvus:
+        condition: service_healthy
+      retriever:
+        condition: service_started
+      reranking:
+        condition: service_started
     ports:
       - "8889:8889"
     environment:

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

@@ -17,8 +17,6 @@ services:
       - redis-vector-db
     ports:
       - "6007:5000"
-      - "6008:6008"
-      - "6009:6009"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
@@ -29,6 +27,12 @@ services:
       TEI_ENDPOINT: http://tei-embedding-service:80
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       LOGFLAG: ${LOGFLAG}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
+    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"
@@ -45,7 +49,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       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
@@ -89,10 +93,16 @@ services:
     image: ${REGISTRY:-opea}/doc-index-retriever:${TAG:-latest}
     container_name: doc-index-retriever-server
     depends_on:
-      - redis-vector-db
+      redis-vector-db:
-      - tei-embedding-service
+        condition: service_started
-      - embedding
+      tei-embedding-service:
-      - retriever
+        condition: service_healthy
+      embedding:
+        condition: service_started
+      dataprep-redis-service:
+        condition: service_healthy
+      retriever:
+        condition: service_started
     ports:
       - "8889:8889"
     environment:

DocIndexRetriever/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -29,6 +29,12 @@ services:
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
+    restart: unless-stopped
   tei-embedding-service:
     image: ghcr.io/huggingface/tei-gaudi:1.5.0
     entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
@@ -52,7 +58,7 @@ services:
       ENABLE_EXPERIMENTAL_FLAGS: true
       host_ip: ${host_ip}
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:8090/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 60
@@ -110,7 +116,7 @@ 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
@@ -138,11 +144,18 @@ services:
     image: ${REGISTRY:-opea}/doc-index-retriever:${TAG:-latest}
     container_name: doc-index-retriever-server
     depends_on:
-      - redis-vector-db
+      redis-vector-db:
-      - tei-embedding-service
+        condition: service_started
-      - embedding
+      tei-embedding-service:
-      - retriever
+        condition: service_healthy
-      - reranking
+      embedding:
+        condition: service_started
+      dataprep-redis-service:
+        condition: service_healthy
+      retriever:
+        condition: service_started
+      reranking:
+        condition: service_started
     ports:
       - "8889:8889"
     environment:

DocIndexRetriever/docker_compose/intel/hpu/gaudi/compose_milvus.yaml

@@ -78,6 +78,11 @@ services:
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       LOGFLAG: ${LOGFLAG}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
     restart: unless-stopped
     depends_on:
       tei-embedding-service:
@@ -112,7 +117,7 @@ services:
       ENABLE_EXPERIMENTAL_FLAGS: true
       host_ip: ${host_ip}
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:8090/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 60
@@ -173,7 +178,7 @@ 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
@@ -205,11 +210,18 @@ services:
     image: ${REGISTRY:-opea}/doc-index-retriever:${TAG:-latest}
     container_name: doc-index-retriever-server
     depends_on:
-      - milvus-standalone
+      milvus-standalone:
-      - tei-embedding-service
+        condition: service_healthy
-      - embedding
+      tei-embedding-service:
-      - retriever
+        condition: service_healthy
-      - reranking
+      embedding:
+        condition: service_started
+      dataprep-milvus:
+        condition: service_healthy
+      retriever:
+        condition: service_started
+      reranking:
+        condition: service_started
     ports:
       - "8889:8889"
     environment:

GraphRAG/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -48,7 +48,7 @@ services:
       host_ip: ${host_ip}
       HF_TOKEN: ${HF_TOKEN}
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
       timeout: 6s
       retries: 48
@@ -83,7 +83,7 @@ services:
       - SYS_NICE
     ipc: host
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://${host_ip}:${LLM_ENDPOINT_PORT}/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 100
@@ -122,6 +122,11 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_TOKEN: ${HF_TOKEN}
       MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS:-4096}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
     restart: unless-stopped
   retriever-neo4j:
     image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
@@ -157,10 +162,16 @@ services:
     image: ${REGISTRY:-opea}/graphrag:${TAG:-latest}
     container_name: graphrag-gaudi-backend-server
     depends_on:
-      - neo4j-apoc
+      neo4j-apoc:
-      - tei-embedding-serving
+        condition: service_healthy
-      - retriever-neo4j
+      tei-embedding-serving:
-      - tgi-gaudi-server
+        condition: service_healthy
+      dataprep-neo4j-llamaindex:
+        condition: service_healthy
+      retriever-neo4j:
+        condition: service_started
+      tgi-gaudi-server:
+        condition: service_healthy
     ports:
       - "8888:8888"
       - "${MEGA_SERVICE_PORT:-8888}:8888"

MultimodalQnA/docker_compose/amd/gpu/rocm/compose_vllm.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: 10
     restart: unless-stopped
   embedding-multimodal-bridgetower:
     image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower:${TAG:-latest}
@@ -144,11 +149,16 @@ services:
     image: ${REGISTRY:-opea}/multimodalqna:${TAG:-latest}
     container_name: multimodalqna-backend-server
     depends_on:
-      - redis-vector-db
+      redis-vector-db:
-      - dataprep-multimodal-redis
+        condition: service_started
-      - embedding
+      dataprep-multimodal-redis:
-      - retriever-redis
+        condition: service_healthy
-      - lvm
+      embedding:
+        condition: service_started
+      retriever-redis:
+        condition: service_started
+      lvm:
+        condition: service_started
     ports:
       - "8888:8888"
     environment:

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

@@ -52,6 +52,11 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${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: 10
     restart: unless-stopped
   embedding-multimodal-bridgetower:
     image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower:${TAG:-latest}
@@ -145,11 +150,16 @@ services:
     image: ${REGISTRY:-opea}/multimodalqna:${TAG:-latest}
     container_name: multimodalqna-backend-server
     depends_on:
-      - redis-vector-db
+      redis-vector-db:
-      - dataprep-multimodal-redis
+        condition: service_started
-      - embedding
+      dataprep-multimodal-redis:
-      - retriever-redis
+        condition: service_healthy
-      - lvm
+      embedding:
+        condition: service_started
+      retriever-redis:
+        condition: service_started
+      lvm:
+        condition: service_started
     ports:
       - "${MEGA_SERVICE_PORT}:${MEGA_SERVICE_PORT}"
     environment:

MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -54,6 +54,11 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${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: 10
     restart: unless-stopped
   embedding-multimodal-bridgetower-gaudi:
     image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower-gaudi:${TAG:-latest}
@@ -175,11 +180,16 @@ services:
     image: ${REGISTRY:-opea}/multimodalqna:${TAG:-latest}
     container_name: multimodalqna-backend-server
     depends_on:
-      - redis-vector-db
+      redis-vector-db:
-      - dataprep-multimodal-redis
+        condition: service_started
-      - embedding
+      dataprep-multimodal-redis:
-      - retriever-redis
+        condition: service_healthy
-      - lvm
+      embedding:
+        condition: service_started
+      retriever-redis:
+        condition: service_started
+      lvm:
+        condition: service_started
     ports:
       - "${MEGA_SERVICE_PORT}:${MEGA_SERVICE_PORT}"
     environment:

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

@@ -29,6 +29,12 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     volumes:
       - videoqna-cache:/home/user/.cache
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 10
+    restart: unless-stopped
   embedding:
     image: ${REGISTRY:-opea}/embedding-multimodal-clip:${TAG:-latest}
     container_name: clip-embedding-server
@@ -117,13 +123,20 @@ services:
     image: ${REGISTRY:-opea}/videoqna:${TAG:-latest}
     container_name: videoqna-xeon-backend-server
     depends_on:
-      - vdms-vector-db
+      vdms-vector-db:
-      - dataprep
+        condition: service_started
-      - embedding
+      dataprep:
-      - retriever
+        condition: service_healthy
-      - reranking
+      embedding:
-      - lvm-video-llama
+        condition: service_started
-      - lvm
+      retriever:
+        condition: service_started
+      reranking:
+        condition: service_started
+      lvm-video-llama:
+        condition: service_started
+      lvm:
+        condition: service_started
     ports:
       - "${BACKEND_PORT}:8888"
     environment: