I have a field in my form named as description. The description contains value of paragraphs spanning over a couple of pages. While training the model, I selected the data to be extracted from multiple pages by selecting the continue drawing option, but when the model was put into practice, it fetched the data from only one page. Even in the Reconciliation Task, I cannot select data from more than one page. Is there any workaround available for this issue?
Discussion posts and replies are publicly visible
This approach works best for structured or semi-structured documents. Did you consider to use the new AI extraction features to extract that description in a second step?
Please use Document Extraction AI Skill for this, after training the model with these types of documents you can use this to solve your issue. For reference on how to use it, please check academy.appian.com/
I am already using the Document extraction AI skill. I have trained the model as well. The description value that I want to fetch spans over a couple of pages and I want to extract all of that. While training the model I could select the multiple paragraphs in consecutive pages by selecting "continue drawing" on the next page. But in practice, the model only extracts the description from one page, does not fetch from the next page. And, in the reconciliation task, I can only select the description from one page. I want to extract the value of one key- description, which continues on the consecutive pages as well. Will that be possible?
https://docs.appian.com/suite/help/24.2/gen-ai-skills.html#extraction
Hi umam1720 ,
How many pages you are trying to extract.
Around 2-3 pages
After extraction are you using reconsolidation for verifying the data or not. If yes you can select the correct data to the field.
Yes, I am using the reconciliation task. My issue is the data I want is printed over 2 or more pages. When I try to select the data I want, I can only select data from one page. If I select data from page 2, the previously selected data from page 1 is replaced. I want to select the whole data that is printed on 2 or 3 consecutive pages. Below attached is the example of the amount of data I want extract.
Looks like we cannot do selection on multiple pages not even using continue drawing. You can save page 1 as field 1 and page 2 as field 2 and concat them later to display or save accordingly.
Appian recommends using "Google Cloud Vision Connected System." for paragraph types.
That might work, thanks!