How to extract multiple tables from a pdf using UiPath Document Understanding

Help AI Center
, , ,
1

Hi,

Currently I’m working on a use case where, there are 2-3 tables within a pdf and I need to extract the information using UiPath Document Understanding. The challenge over here is - we can only set the number of columns, but not tables while labelling the forms. The tables in the form are going to be right below of each other and the column names might be similar.

The tables in the form would look something looks like this:

image
image914×490 6.37 KB

So, in order to extract this information I’m looking for an approach to process them as separate tables and also use action center.

Thanks in advance!! :slight_smile:

2

you can write a simple python code to extract table from python using tabula library. Try following the link:

3

Thanks for suggestion,
but how can we use it to update the Data extraction scope of ML extractor. Because we need to present action center and to retrain the model?