调用Vertex AI端点预测时遭遇503 DNS解析失败错误的求助

我现在正尝试调用自定义Vertex AI端点做预测，但一直碰到下面的错误，完全摸不着头脑。我已经试过这些排查步骤了：

• 反复核对了端点ID和项目编号
• 所有Python包都是最新版本
• Google Cloud日志里没找到相关错误
• Vertex AI API已经启用
• Vertex AI API服务账号权限配置正确
• 没有触发配额或其他限制
• 创建端点时勾选了DNS选项
• 尝试过用VPN连接
• 换了两个操作系统、三种不同网络环境测试，排除本地网络问题

代码示例 #

from google.cloud import aiplatform

PROJECT_NUMBER = "..."
REGION = "us-central1"
ENDPOINT_ID = "..."  

# Initialize Vertex AI with the dedicated domain name
aiplatform.init(
    project=PROJECT_NUMBER,
    location=REGION,
    api_endpoint=f"{ENDPOINT_ID}.us-central1-{PROJECT_NUMBER}.prediction.vertexai.goog"
)

endpoint_name = f"projects/{PROJECT_NUMBER}/locations/{REGION}/endpoints/{ENDPOINT_ID}"
endpoint = aiplatform.Endpoint(endpoint_name=endpoint_name)

response = endpoint.predict(instances=[{"content": "Hello world"}], use_dedicated_endpoint=True)
print(response)

错误信息 #

Traceback (most recent call last):
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\api_core\grpc_helpers.py", line 76, in error_remapped_callable
    return callable_(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\grpc\_interceptor.py", line 277, in __call__
    response, ignored_call = self._with_call(
                             ^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\grpc\_interceptor.py", line 332, in _with_call
    return call.result(), call
           ^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\grpc\_channel.py", line 440, in result
    raise self
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\grpc\_interceptor.py", line 315, in continuation
    response, call = self._thunk(new_method).with_call(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\grpc\_channel.py", line 1198, in with_call
    return _end_unary_response_blocking(state, call, True, None)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\grpc\_channel.py", line 1006, in _end_unary_response_blocking
    raise _InactiveRpcError(state)  # pytype: disable=not-instantiable
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
        status = StatusCode.UNAVAILABLE
        details = "DNS resolution failed for ENDPOINT_ID.us-central1-PROJECT_NUMBER.prediction.vertexai.goog:443: UNAVAILABLE: getaddrinfo: WSA Error (No such host is known.
 -- 11001)"
        debug_error_string = "UNKNOWN:Error received from peer  {created_time:"2025-03-31T12:27:51.0519886+00:00", grpc_status:14, grpc_message:"DNS resolution failed for ENDPOINT_ID.us-central1-PROJECT_NUMBER.prediction.vertexai.goog:443: UNAVAILABLE: getaddrinfo: WSA Error (No such host is known.\r\n -- 11001)"}"
>

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\api_core\retry\retry_unary.py", line 144, in retry_target
    result = target()
             ^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\api_core\grpc_helpers.py", line 78, in error_remapped_callable
    raise exceptions.from_grpc_error(exc) from exc
google.api_core.exceptions.ServiceUnavailable: 503 DNS resolution failed for ENDPOINT_ID.us-central1-PROJECT_NUMBER.prediction.vertexai.goog:443: UNAVAILABLE: getaddrinfo: WSA Error (No such host is known. -- 11001)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "c:\Users\zacis\Desktop\New folder\FootySphere (1)\Code\site\d.py", line 17, in <module>
    response = endpoint.predict(instances=[{"content": "Hello world"}], use_dedicated_endpoint=True)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\cloud\aiplatform\models.py", line 2384, in predict
    self._sync_gca_resource_if_skipped()
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\cloud\aiplatform\models.py", line 742, in _sync_gca_resource_if_skipped
    self._gca_resource = self._get_gca_resource(
                         ^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\cloud\aiplatform\base.py", line 692, in _get_gca_resource
    return getattr(self.api_client, self._getter_method)(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\cloud\aiplatform_v1\services\endpoint_service\client.py", line 1133, in get_endpoint
    response = rpc(
               ^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\api_core\gapic_v1\method.py", line 131, in __call__
    return wrapped_func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\api_core\retry\retry_unary.py", line 293, in retry_wrapped_func
    return retry_target(
           ^^^^^^^^^^^^^
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\api_core\retry\retry_unary.py", line 153, in retry_target
    _retry_error_helper(
  File "c:\Users\zacis\AppData\Local\Programs\Python\Python311\Lib\site-packages\google\api_core\retry\retry_base.py", line 221, in _retry_error_helper
    raise final_exc from source_exc
google.api_core.exceptions.RetryError: Timeout of 120.0s exceeded, last exception: 503 DNS resolution failed for ENDPOINT_ID.us-central1-PROJECT_NUMBER.prediction.vertexai.goog:443: UNAVAILABLE: getaddrinfo: WSA Error (No such host is known.
 -- 11001)

备注：内容来源于stack exchange，提问作者ahmedquran12