Classify Document Scope - Classify: Argument can't be empty Parameter name: documentText

Hello,
With my team we are using Document Understanding framework to Classify and Extract informations from pdf.
We start a big execution with around 8000 pdf and we got this error on some of them : “Classify Document Scope - Classify: Argument can’t be empty
Parameter name: documentText”
As you can see on the picture in debug mode we are facing to a strange case, the argument is not empty and the Classify Scope say the reverse.

Cloud you help us with that ?
We are using Studio 2021.10.5.
Have a good day!
BR,

2 Likes

i’m getting the same error

Hi @Mourad_El_Khamkhoumi @Marcelo_de_Alcantara

Does the same always happen on the specific documents? Any chance you could share a sample of such document that still reproduces the issue, maybe together with a sample zip of a dummy project?

It would help us reproduce the issue.

1 Like

Hi @loginerror,
Unfortunately, for privacy reason I’m not able to share doc with you.
I tried to solve by upgrading my dependencies, but no effect.
I tried another way to solve my problem.
When I let only one classifier inside the Classify Scope, it works and the execution pass to the next activity.
But combining several Classifier is not possible :frowning:

BR

No worries. Could you still confirm if the issue happens always to the same file(s)?

Yes, exactly it happens always on the same files.

Hello @Mourad_El_Khamkhoumi @Marcelo_de_Alcantara

How can we reproduce the issue, what documents are you using/what is particular to the documents leading to the documents? Are there native/scanned PDFs?

Thanks in advance,
Monica

Hi @Monica_Secelean,

Nothing special it’s a scanned documents.

For your information, I opened a ticket at the support team and we identify that the problem is coming from the fact that on some documents combining several classifier will result with this error.
Support Answer :
"Hello Mourad,
An issue was identified testing with the sample workflow you have provided.
An internal ticket was opened with the development team for further investigation. For now, there is no ETA provided.
Best regards!
@cristian.oprescu
"

As you can see on the picture I reproduced the issue with the sample project provided by the support.

@Marcelo_de_Alcantara try only with one Classifier and it should works.

A workaround is to put the Classify Scope in a Try Catch and use the Classify Scope with only one classifier when it’s going to the catch bloc.

I hope this could help other guys !

2 Likes

Hi @Mourad_El_Khamkhoumi, i made that and it works, thank you man!!

1 Like

Happy for you guy ! :+1:

Hi all,

This bug was reported as resolved in UiPath.IntelligentOCR activities package v6.5.0

Thanks!
Cristian

Hi UiPath Community,

I am currently working on a Document Understanding workflow using the UiPath.DocumentUnderstanding.Activities package (not IntelligentOCR).

What I have done so far:

I have retrieved a list of PDF file paths using:

pdfFiles = Directory.GetFiles(folderPath, “*.pdf”)

  • I’m looping through each file using a For Each activity.
  • For each PDF file, I’m using the Create Document Path Resource activity to convert the file path to an ILocalResource object.
  • Then, I’m passing that object into the Classify Document activity.

Issue:

When I run the workflow, I get the following error from the Classify Document activity:

Argument can’t be empty (Parameter ‘content’)

My Environment:

  • UiPath Studio Version: 2025.0.161 Enterprise
  • UiPath.DocumentUnderstanding.Activities version: 2.12.0
  • Running locally (not Orchestrator)
  • PDFs are stored in a local directory

Has anyone faced this issue or know what might be missing in the setup for Classify Document?

Thanks in advance!

Hello,

Please check the file path or file size, I got the same issue, in my case, i was downloading the file from storage bucket and file size was 0KB. once good file downloaded error was resolved.