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>

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

@@ -38,6 +38,11 @@ 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
   wav2lip-service:
     image: ${REGISTRY:-opea}/wav2lip:${TAG:-latest}