Having Issues Extracting Data from semi structured pdf

[Jay_Chacko (JC)]

So have this multi page document (see image below) where i need to extract the red marked items

I setup document understanding activities per the official demo video, My pdf is 2 pages(for now since i am using community edition) and i am trying to use the machine learning extraction to get some data. I don’t fully understand the activities and what it does, i am guessing its learning in each try ? I did not use regex extraction yet , trying to get some kind of result with machine learning only, havn’t used any other extraction method , not an expert either in any of them. Any other Extractor more suite in my case? .

Here is my project , i removed the api key since its orchestrator based, add your own for testing.

GitHub - jaychacko/BCDocumentUnderstanding

[Ioana_Gligan]

There is no “custom” model for your needs so it will not work unless you start configuring and training your own DU model. Please reach out to your UiPath contact (if you are an enterprise) and ask about these features.