You are developing a custom extraction model using Azure AI Document Intelligence Studio. Your training dataset consists of multi-page invoices with varying structures, and some fields appear only on the final page. How should you structure your tagging configuration?
Trap 1: Create a separate custom model for the final page and chain them…
An orchestration model is not needed simply because a field appears on a later page of a multi-page document.
Trap 2: Split every multi-page invoice into individual single-page…
Splitting destroys document boundary context and is unnecessary for multi-page document support.
Trap 3: Define all late-appearing fields as optional metadata parameters in…
Fields are tagged visually in the Studio or defined in the layout schema, not as metadata parameters.
- A
Create a separate custom model for the final page and chain them using an orchestration model.
Why wrong: An orchestration model is not needed simply because a field appears on a later page of a multi-page document.
- B
Split every multi-page invoice into individual single-page documents before uploading.
Why wrong: Splitting destroys document boundary context and is unnecessary for multi-page document support.
- C
Define all late-appearing fields as optional metadata parameters in the training configuration JSON file.
Why wrong: Fields are tagged visually in the Studio or defined in the layout schema, not as metadata parameters.
- D
Tag the fields on whatever page they appear across the sample documents in Document Intelligence Studio.
Document Intelligence custom models support multi-page documents natively, allowing you to tag fields wherever they appear.