Document Understanding with ML Extractor facing issue


In D.U i want to do more number of Extraction in PDF in this ML Extractor (Ex.Voucher Number,Claim No,Payment, …,…,…,…) in configure extractor more than 20 we can’t doing extration. there is asking date,PO-No,Currency,etc., we cannot adding currency two times. it is deselecting automatically.

I want to extract specific data (>20) with dynamic changing PDF’s formats

please help me out from this


Hi @absithyd

Welcome to Community,

Are you using ML Extractor by providing the Endpoint for certain type and Api key, if so there are predefined fields in the ML Extractor those fields only show up, if you want to add any custom fields you can add and use Form Extractor or Intelligent Form Extractor to extract the data.


@suraj.setty I have tried Form Extractor and Intelligent Form Extractor but I didn’t getting specific output.
Which one is use full for Specific PDF data extraction.
I have used so many types of methods (Ex. OCR,Regex,D.U,GetPDFText) But I didn’t get Output.
Please help me out from this problem.

Have you tried combining the extractors for extracting specific data.


No I Haven’t tried.


For fixed fields you can use “ML Extractor” and for the additional fields you can try with "Intelligent form Extractor " by clicking on Configure Extractor and tag the fields based on the Extractors.


1 Like