I have been having an issue when trying to implement document understanding. When I train the extractor the files that I have validated get sent to AI Center, but when I try to train those files with a pipeline it fails.
I have validated purchase orders in document understanding and exported those results to AI Center and was able to train those files.
I did notice that the files structure that gets sent to my dataset in AI Center is different when done from the Train ML Extractor activity.
I’m not sure what is the proper way to get this done or if I’m doing something wrong.
Any help would be appreciated.
This what the export from DU looks like when exported to AI Center → Dataset
This is what the is looks like coming from studio