Azure机器学习向量索引-为什么部署验证失败？

7cjasjjr  于 2023-11-21  发布在  其他
关注(0)|答案(1)|浏览(135)

我尝试使用Azure Machine Learning的基于Web的UI创建FAISS向量索引。我按照documentation执行所需步骤，并选择一个正在运行的计算示例进行处理。
我第一次运行它时，它总是在使用azure.core.exceptions.ClientAuthenticationError: No token received.：x1c 0d1x执行“validate_deployments_job”步骤时失败
我应该在哪里提供那个代币？
如果我进入作业详细信息并再次运行作业，相同的“validate_deployments_job”仍然会失败，但是，向量索引将被创建并变得可用。我知道此功能是预览版，但我试图了解我在这里遗漏了什么。日志（见下文）暗示存在某种身份验证问题，但我已登录并可以访问所有必需的组件，并且在创建作业时，不需要提供任何代币。
日志/完整跟踪显示以下内容：

  1. [2023-09-23 16:50:09] INFO     azureml.rag.validate_deployments.validate_deployments - ActivityStarted, validate_deployments (activity.py:108)
  2. [2023-09-23 16:50:09] INFO     azureml.rag.validate_deployments.validate_deployments - [Validate Deployments]: Validating Embeddings model using AOAI (validate_deployments.py:552)
  3. Using llm_config: {
  4.   "type": "azure_open_ai",
  5.   "model_name": "gpt-35-turbo",
  6.   "deployment_name": null,
  7.   "temperature": 0.0,
  8.   "max_tokens": 1500
  9. }
  10. [2023-09-23 16:50:09] INFO     azureml.rag.validate_deployments.validate_deployments - [Validate Deployments]: Received and parsed arguments for validating deployments in RAG.  Starting validation now... (validate_deployments.py:309)
  11. [2023-09-23 16:50:09] INFO     azureml.rag.connections - Getting workspace connection: Default_AzureOpenAI (connections.py:131)
  12. Embedding deployment name: text-embedding-ada-002
  13. Embedding model name: text-embedding-ada-002
  14. [2023-09-23 16:50:10] INFO     azureml.rag.validate_deployments.validate_deployments - [Validate Deployments]: Completion model using Default AOAI connection, parsing ResourceId (validate_deployments.py:389)
  15. Using workspace connection key for OpenAI embeddings
  16. [2023-09-23 16:50:10] INFO     azureml.rag.validate_deployments.validate_deployments - [Validate Deployments]: Embedding workspace connection retrieved and params populated successfully... (validate_deployments.py:400)
  17. [2023-09-23 16:50:10] INFO     azureml.rag.validate_deployments.validate_deployments - [Validate Deployments]: Starting to poll on deployment status validation. (validate_deployments.py:264)
  18. [2023-09-23 16:50:10] INFO     azureml.rag.validate_deployments.validate_deployments - [Validate Deployments]: Default AOAI resource detected. Performing control plane validations now... (validate_deployments.py:174)
  19. _AzureMLOnBehalfOfCredential.get_token failed: No token received.
  20. Using User Identity for authentication
  21. [2023-09-23 16:50:10] ERROR    azureml.rag.validate_deployments.validate_deployments - ValidationFailed: validate_deployments failed with exception: Traceback (most recent call last):
  22.   File "validate_deployments.py", line 585, in main_wrapper
  23.     main(parser_args, activity_logger)
  24.   File "validate_deployments.py", line 554, in main
  25.     validate_aoai_deployments(parser_args, check_aoai_completion, check_aoai_embeddings, activity_logger)
  26.   File "validate_deployments.py", line 415, in validate_aoai_deployments
  27.     poll_on_deployment(completion_params,
  28.   File "validate_deployments.py", line 266, in poll_on_deployment
  29.     polling2.poll(
  30.   File "/azureml-envs/rag/lib/python3.8/site-packages/polling2.py", line 193, in poll
  31.     val = target(*args, **kwargs)
  32.   File "validate_deployments.py", line 267, in <lambda>
  33.     lambda: check_deployment_status(completion_params, "llm", activity_logger) and check_deployment_status(
  34.   File "validate_deployments.py", line 181, in check_deployment_status
  35.     return validate_and_create_default_aoai_resource(ws, model_params, activity_logger)
  36.   File "validate_deployments.py", line 109, in validate_and_create_default_aoai_resource
  37.     response = client.deployments.get(
  38.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/tracing/decorator.py", line 78, in wrapper_use_tracer
  39.     return func(*args, **kwargs)
  40.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/mgmt/cognitiveservices/operations/_deployments_operations.py", line 348, in get
  41.     pipeline_response: PipelineResponse = self._client._pipeline.run(  # pylint: disable=protected-access
  42.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 230, in run
  43.     return first_node.send(pipeline_request)
  44.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 86, in send
  45.     response = self.next.send(request)
  46.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 86, in send
  47.     response = self.next.send(request)
  48.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 86, in send
  49.     response = self.next.send(request)
  50.   [Previous line repeated 2 more times]
  51.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/mgmt/core/policies/_base.py", line 46, in send
  52.     response = self.next.send(request)
  53.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_redirect.py", line 197, in send
  54.     response = self.next.send(request)
  55.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_retry.py", line 531, in send
  56.     response = self.next.send(request)
  57.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_authentication.py", line 124, in send
  58.     self.on_request(request)
  59.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_authentication.py", line 99, in on_request
  60.     self._token = self._credential.get_token(*self._scopes)
  61.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_credentials/aml_on_behalf_of.py", line 36, in get_token
  62.     return self._credential.get_token(*scopes, **kwargs)
  63.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_base.py", line 51, in get_token
  64.     return super(ManagedIdentityBase, self).get_token(*scopes, **kwargs)
  65.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/get_token_mixin.py", line 83, in get_token
  66.     token = self._request_token(*scopes, **kwargs)
  67.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_base.py", line 61, in _request_token
  68.     return cast(ManagedIdentityClient, self._client).request_token(*scopes, **kwargs)
  69.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_client.py", line 127, in request_token
  70.     token = self._process_response(response, request_time)
  71.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_client.py", line 64, in _process_response
  72.     raise ClientAuthenticationError(message="No token received.", response=response.http_response)
  73. azure.core.exceptions.ClientAuthenticationError: No token received.
  74.  (validate_deployments.py:588)
  75. [2023-09-23 16:50:10] ERROR    azureml.rag.validate_deployments.validate_deployments - ActivityCompleted: Activity=validate_deployments, HowEnded=Failure, Duration=759.58 [ms], Exception=ClientAuthenticationError (activity.py:127)
  76. Traceback (most recent call last):
  77.   File "validate_deployments.py", line 616, in <module>
  78.     main_wrapper(parser_args, logger)
  79.   File "validate_deployments.py", line 585, in main_wrapper
  80.     main(parser_args, activity_logger)
  81.   File "validate_deployments.py", line 554, in main
  82.     validate_aoai_deployments(parser_args, check_aoai_completion, check_aoai_embeddings, activity_logger)
  83.   File "validate_deployments.py", line 415, in validate_aoai_deployments
  84.     poll_on_deployment(completion_params,
  85.   File "validate_deployments.py", line 266, in poll_on_deployment
  86.     polling2.poll(
  87.   File "/azureml-envs/rag/lib/python3.8/site-packages/polling2.py", line 193, in poll
  88.     val = target(*args, **kwargs)
  89.   File "validate_deployments.py", line 267, in <lambda>
  90.     lambda: check_deployment_status(completion_params, "llm", activity_logger) and check_deployment_status(
  91.   File "validate_deployments.py", line 181, in check_deployment_status
  92.     return validate_and_create_default_aoai_resource(ws, model_params, activity_logger)
  93.   File "validate_deployments.py", line 109, in validate_and_create_default_aoai_resource
  94.     response = client.deployments.get(
  95.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/tracing/decorator.py", line 78, in wrapper_use_tracer
  96.     return func(*args, **kwargs)
  97.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/mgmt/cognitiveservices/operations/_deployments_operations.py", line 348, in get
  98.     pipeline_response: PipelineResponse = self._client._pipeline.run(  # pylint: disable=protected-access
  99.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 230, in run
  100.     return first_node.send(pipeline_request)
  101.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 86, in send
  102.     response = self.next.send(request)
  103.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 86, in send
  104.     response = self.next.send(request)
  105.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/_base.py", line 86, in send
  106.     response = self.next.send(request)
  107.   [Previous line repeated 2 more times]
  108.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/mgmt/core/policies/_base.py", line 46, in send
  109.     response = self.next.send(request)
  110.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_redirect.py", line 197, in send
  111.     response = self.next.send(request)
  112.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_retry.py", line 531, in send
  113.     response = self.next.send(request)
  114.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_authentication.py", line 124, in send
  115.     self.on_request(request)
  116.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/core/pipeline/policies/_authentication.py", line 99, in on_request
  117.     self._token = self._credential.get_token(*self._scopes)
  118.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_credentials/aml_on_behalf_of.py", line 36, in get_token
  119.     return self._credential.get_token(*scopes, **kwargs)
  120.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_base.py", line 51, in get_token
  121.     return super(ManagedIdentityBase, self).get_token(*scopes, **kwargs)
  122.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/get_token_mixin.py", line 83, in get_token
  123.     token = self._request_token(*scopes, **kwargs)
  124.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_base.py", line 61, in _request_token
  125.     return cast(ManagedIdentityClient, self._client).request_token(*scopes, **kwargs)
  126.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_client.py", line 127, in request_token
  127.     token = self._process_response(response, request_time)
  128.   File "/azureml-envs/rag/lib/python3.8/site-packages/azure/ai/ml/identity/_internal/managed_identity_client.py", line 64, in _process_response
  129.     raise ClientAuthenticationError(message="No token received.", response=response.http_response)
  130. azure.core.exceptions.ClientAuthenticationError: No token received.

字符串

Azure

1条答案

按热度按时间
ubof19bj

ubof19bj1#

再次尝试，但使用不同的compute type。我第一次尝试连接到现有的Compute Instance（一个缓慢/便宜的），遇到了和你一样的错误。一旦我切换到无服务器示例，它就出现了错误。
x1c 0d1x的数据

赞(0）分享  回复(0）举报  2023-11-21
我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com