Question Re: Customizing Extraction Fields in SAP Document Informa... in Technology Q&A

Customizing Extraction Fields in SAP Document Information Extraction (DOX)

kevinkim0908 — Tue, 12 Aug 2025 17:47:26 GMT

Hello,

I’m currently evaluating SAP Document Information Extraction (DOX) in SAP Document AI using a trial account. Although I’ve noticed that it extracts every text very accurately, not every text is being mapped to the extraction fields.

I wanted to add/customize header fields myself to map the extracted text to header fields or line items better (while following this link https://help.sap.com/docs/document-ai/sap-document-ai/add-data-fields to add data fields) but schema configuration doesn’t appear in my trial environment. It also states that I cannot change SAP schemas as shown in the attached image below:

So I was wondering if it's possible to edit/customize extraction fields in the premium version of SAP Document AI? If so, does this customization occur before the optical character recognition (OCR) to guide the model, or only after OCR to map extracted text to fields?

Defining custom field mappings before OCR would be extremely valuable for my team's use case, so I’d greatly appreciate if anyone can explain what’s possible before I consider upgrading to a full subscription. Thank you.

Re: Customizing Extraction Fields in SAP Document Informa...

Chris1973 — Wed, 13 Aug 2025 07:39:55 GMT

Hi @kevinkim0908

Thank you for your question

Yes, it is possible to edit or customize extraction fields in the premium version of SAP Document AI. To your second question, yes, customization and schema editing happen after Optical Character Recognition has processed the document text. Premium tiers also support enhanced features like user correction feedback loops for progressive refinement and schema extensibility for your specific business needs.

Considering that customization to map extracted text to your header fields or line items is critical for your team, I recommend you upgrade to the Premium version. Check below links for more information.

https://www.sap.com/products/artificial-intelligence/ai-foundation-os/document-ai.html

https://news.sap.com/2025/07/sap-business-ai-release-highlights-q2-2025/

I hope this provides the necessary information. I am happy to help if you have further questions.

Best regards

Chris

Re: Customizing Extraction Fields in SAP Document Informa...

TMNielsen — Wed, 20 Aug 2025 07:28:08 GMT

Hi Kevinkim0908

You can also edit schemas in the trial version, but as the error message tells, you can't and shouldn't change the schemas delivered by SAP - this rule is in any version also in premium.

Instead you can copy the schema and then change the copy.

Please also note that you can't edit any schema if it has status activated.

With below screenshots I show an example how to copy a schema.

Click the Schema Configuration button to get the overview of schemas:

I want a modified copy of the SAP_PurchaseOrder_Schema, so I press the copy button on the line for that schema:

In the popup I give the copy a name and description:

Now I have a copy of the SAP standard schema.

Note that the new schema has status DRAFT. You can only edit schemas with status DRAFT.

When you finish your changes, you must activate the schema before it can be used. After activation, you can not edit the schema anymore, but you can create a new version and then edit the new version. You can also deactivate the schema and then edit it without creating a new version. If you just want to play around with a trial, you may not need to use versions, but for real projects that has gone live, there are multiple good reasons to use versions.

After I activate my copy, you can see in below screen that the Edit button is "greyed out", and the buttons Create Version and Deactivate now are the primary options.

Kind regards

Thomas Madsen Nielsen

Re: Customizing Extraction Fields in SAP Document Informa...

kevinkim0908 — Fri, 22 Aug 2025 18:44:20 GMT

Hello Thomas,

Thank you so much for your response. I was able to enhance the mapping between the extraction fields and the extracted text better by creating a copy of the SAP_invoice_schema and customizing it with the extraction fields I needed.

Thank you so much for your help. I look forward to testing SAP Document AI further with my team members.

Best regards,
Kevin

Re: Customizing Extraction Fields in SAP Document Informa...

TMNielsen — Mon, 25 Aug 2025 07:51:30 GMT

Hi Kevin

Good luck with your testing.

Be aware of one important limitation before you really start testing. The Trial version only allows very little test runs. I think the limit is 50 PDF pages per month, so if you for example would like to test performance with big documents and load a PDF with 40 pages, then you can only make one testrun per month.

That limit is ridiculously low - almost useless. When I finally had it running and was going to do some real test, the limit was reached. 😤

So, I set up a new email and a new trial account to keep testing. I am on my 4th trial account, but now I am so lucky that I have a customer and a POC project with a pay-as-you go licence.

There are also other limitations as you can see in the documentation here Free Tier Option and Trial Account Technical Constraints | SAP Help Portal.

So use your 50 test pages wisely.