Extract repeated fields on PDF documents with AI Skill

Hi everyone,

I have this specific use case: I have to extract data from a pdf document using AI Skills. The pdf document has the structure of a table, with multiple rows. So the problem is, when setting up the AI Skill, when I want to label the fields, I can only select one of the rows. I want to extract the same field, say "email", for all the rows in my pdf table. Still haven't found a way to label repeating fields inside a document.

Any workaround or help is much appreciated, thank you.

  Discussion posts and replies are publicly visible

Parents
  • Hi Alteocaka, I have also just started with some thing similar where the client had many clients and each have their own format of reporting. From what I have understood and implemented AI skills is not for ONLY Tabular data. If you have fields to be extracted (label-value) pairs along with that you can specify a table extraction (only during reconciliation) . You cannot use the AI skill to extract data from a document that has just a table. For that the best way is to use the Excel smart service to extract data.

Reply
  • Hi Alteocaka, I have also just started with some thing similar where the client had many clients and each have their own format of reporting. From what I have understood and implemented AI skills is not for ONLY Tabular data. If you have fields to be extracted (label-value) pairs along with that you can specify a table extraction (only during reconciliation) . You cannot use the AI skill to extract data from a document that has just a table. For that the best way is to use the Excel smart service to extract data.

Children
No Data