Exception while consuming an ML Skill

Hello everyone,

I’m having and issue while doing the extraction of data using an ML skill deployed in AI Center. The bot throws this exception:

The delegate executed asynchronously through TimeoutPolicy did not complete within the timeout.

In the streaming logs I find this message:

7506837d-ac16-48ca-aa53-947d473c97ec-12-7-6659b99f66-jh7q9:Warning ==> 0/142 nodes are available: 103 Insufficient cpu, 15 Too many pods, 31 node(s) didn’t match node selector, 4 Insufficient memory, 6 node(s) were unschedulable.

The pdf has a size of 8,944 KB.

Updating the Document Understandig package to 2022.2 I get the following error:

Failed to process page range in file due to MLRequestException with message: Invalid server response.
Full Exception: UiPath.DocumentUnderstanding.ML.Activities.Exceptions.MLRequestException: Invalid server response. —> System.Exception: Response status code does not indicate success: 503 (Service Unavailable).
— End of inner exception stack trace —
at System.Activities.Statements.Throw.Execute(CodeActivityContext context)
at System.Activities.CodeActivity.InternalExecute(ActivityInstance instance, ActivityExecutor executor, BookmarkManager bookmarkManager)
at System.Activities.ActivityInstance.Execute(ActivityExecutor executor, BookmarkManager bookmarkManager)
at System.Activities.Runtime.ActivityExecutor.ExecuteActivityWorkItem.ExecuteBody(ActivityExecutor executor, BookmarkManager bookmarkManager, Location resultLocation)
— End of stack trace from previous location where exception was thrown —
at System.Runtime.ExceptionServices.ExceptionDispatchInfo.Throw()
at UiPath.Executor.BaseRunner.EndExecute(IAsyncResult result)
at UiPath.Executor.InProcessRunner.EndExecute(IAsyncResult result)
at UiPath.Core.Activities.ExecutorInvokeActivity.EndExecute(AsyncCodeActivityContext context, IAsyncResult result)
at System.Activities.AsyncCodeActivity.System.Activities.IAsyncCodeActivity.FinishExecution(AsyncCodeActivityContext context, IAsyncResult result)
at System.Activities.AsyncCodeActivity.CompleteAsyncCodeActivityData.CompleteAsyncCodeActivityWorkItem.Execute(ActivityExecutor executor, BookmarkManager bookmarkManager)

Hi, if you’re using Read PDF With OCR, please select the degree of parallelism property = -1.
Otherwise, try with ML Public endpoint with other account.

Thank you for your answer @srinivasmarneni, the problem rises up on the Machine Learning Extractor activity. There’s not a parameter related to parallelism.


Hi @Jorge_Valbuena

can you please try to Increase the time out of the activity as the file size is large.

Also can you please let me know if you are using ML Skill deployed on orchestrator or using an endpoint.

@suraj.setty Thank you so much for your answer. I don’t know why I never thought about increasing the timeout. It worked with all the documents that I couldn’t process before.

1 Like

This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.