PLEASE NOTE: UiPath Communications Mining's Knowledge Base has been fully migrated to UiPath Docs. Please navigate to equivalent articles in UiPath Docs (here) for up to date guidance, as this site will no longer be updated and maintained.

Knowledge Base

Model Training & Maintenance

Guides on how to create, improve and maintain Models in Communications Mining, using platform features such as Discover, Explore and Validation

Delete verbatims via the UI

User permissions required: ‘Edit verbatims’


There may be instances where verbatims have been uploaded to sources that you may not want in the platform. This could be because:

 

  • The verbatim has been corrupted in some way and is unusable
  • The verbatim contains sensitive information that should not be shared
  • The verbatim adds no value to the dataset

 

Whatever the reason may be, you can delete verbatims from a source in the UI via a dataset containing that source. This functionality is also available via the API (see here).


Please Note: Deleting a verbatim from a source whilst in one dataset will remove that verbatim from any other dataset containing that source, so do not take this action lightly. The verbatim could be acting as training data in another dataset and removing it would impact the model in that dataset. If a verbatim in a source does not add value for your use case, confirm that it is not providing value for other datasets before deleting it. The sources page gives an indication of other datasets that are connected to the source in question.

 

To delete a verbatim, simply click the delete button in the bottom right-hand corner of the verbatim as shown below. This button will only show up if you have the required 'Edit verbatims' permission.

 

Delete verbatim button in the UI

 

 

You will then be prompted with a warning and a confirmation request as shown below. If you're happy to proceed despite the warning, click 'Delete'.

  

Delete verbatim confirmation modal



Previous: Amend a dataset's settings     |     Next: Delete a dataset

Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.

Sections

View all