Form Extractor Issue with Multi-Page PDFs in UiPath Document Understanding

Help Studio
, ,
1

I’m using UiPath Document Understanding to process PDFs of varying page lengths. I need to extract information from both the first page and the last page (which includes the gross amount). The Form Extractor works fine on single-page PDFs, but on multi-page PDFs, it often fails to capture the gross amount from the last page.

Questions:

-Could this issue be due to the extractor not identifying the last page correctly? If so, how can I make it work for any last page?

-Are there best practices for setting up anchors for multi-page documents?
Would it be better to split the PDF and apply extractors separately to the first and last pages?

Any advice on reliable configurations or alternative approaches would be greatly appreciated!

2

Hi @Eshu_Dhiman

If the gross amount follows a consistent format or label on the last page, the Regex Extractor can be more reliable than the Form Extractor.
Also you can try to split the pages or you can try with generative extractor using prompt

Let me know if you need any help

Thanks