UiPath Activities

The UiPath Activities Guide

About the Document Understanding ML Activities Pack

The UiPath.DocumentUnderstanding.ML.Activities pack contains activities that integrate ML models for Document Understanding workflows, as follows:

  • The Machine Learning Extractor activity which enables the usage of UiPath provided machine learning models to perform data extraction from documents. The activity is capable of consuming ML models in the context of document understanding, thus enabling RPA workflows to use such models for data extraction from documents.

  • The Machine Learning Extractor Trainer activity which collects the human feedback for you, in a directory of your choice.

  • The Machine Learning Classifier activity which allows users to perform document classification, enabling the use of extraction techniques matching the document type. This activity consumes classification ML models, generated in the context of Document Understanding, from AI Center.

  • The Machine Learning Classifier Trainer activity which allows the collection of human feedback data in AI Center datasets for creating and updating document classification models on AI.


C# Project Flavor Support

Starting with version 1.5.0, this activity package is validated for use in C# projects.



The UiPath.DocumentUnderstanding.ML.Activities package is an improved version of the obsolete UiPath.MachineLearningExtractor.Activities package. Avoid any possible errors caused by the name difference by removing any prior installation of this package and replacing it with the new one.


Docotic.Pdf Library

If you use in your project either one of the following packages: UiPath.DocumentUnderstanding.ML.Activities version 1.7.0 or UiPath.IntelligentOCR.Activities version 4.13.0 or UiPath.PDF.Activities version 3.4.0, then you need to update the rest of the packages to the mentioned versions.

Updated 4 months ago

About the Document Understanding ML Activities Pack

Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.