Enchance health check in GenAIExample docker-compose (#1410)

Fix service launch issue

1. Update Gaudi TGI image from 2.0.6 to 2.3.1
2. Change the hpu-gaudi TGI health check condition.

Signed-off-by: Wang, Xigui <xigui.wang@intel.com>

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

@@ -37,6 +37,11 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:3006/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
   audioqna-xeon-backend-server:
     image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}

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

@@ -35,7 +35,7 @@ services:
       - SYS_NICE
     restart: unless-stopped
   tgi-service:
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
+    image: ghcr.io/huggingface/tgi-gaudi:2.3.1
     container_name: tgi-gaudi-server
     ports:
       - "3006:80"
@@ -54,6 +54,11 @@ services:
       LIMIT_HPU_GRAPH: true
       USE_FLASH_ATTENTION: true
       FLASH_ATTENTION_RECOMPUTE: true
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:3006/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     runtime: habana
     cap_add:
       - SYS_NICE