Hi all,
I am trying to extract a data from PDF using the new AI SKILL feature.
Attaching the screenshot of my PDF and Process Model.
The Output is a stored in a CDT with the same field and name.
This service does not give any data after execution and it takes 5 minutes of time for a simple process with 1 node.
Kindly advice how to proceed.
Discussion posts and replies are publicly visible
This is the initial training phase. You will have to add a validation step after the extraction and route to reconciliation.
can you please elaborate more.
What exactly do you want to know?
Maybe my blog post helps you to get started.
https://appian.rocks/2023/05/29/appian-records-evolution/
Maybe the documentation about ai-document-extraction will help:https://docs.appian.com/suite/help/23.2/create-skill-doc-extraction.html
The problem I also had with the documentation is, that it does not mention that the training only works in the reconciliation task. And without adding this to your process, you will never get any data extracted. That confused me a lot in the beginning.
Stefan-
Can you provide some examples/syntax for the Write Records node at the end of the extraction process in your post - https://appian.rocks/2023/05/29/appian-records-evolution/? This was helpful and cleared up some of the confusion I had with the new AI skills. Looks like I'm able to get through the extract from doc finally and I'm trying to write the data to the DB. Here's a screenshot of my AI doc extraction skill. Thanks.
Welcome to my blog :-)
So, you will have to map the extracted data to one or multiple records. Writing the extracted data to DB will not work. What did you try so far?