All ideas

As a user I would like to retrieve coordinates of values found in a document while using the Prompt Builder

Add classification to automatically book invoices for both OCR and e-invoices. For example, classify lineitems in categories like drinks, food, and parking. Adhere to the "RGS" standard or provide a mapping for categories provided by Klippa.

If something goes wrong while processing a document with the Klippa APIs, a meaningful message is not always returned. Instead of "something went wrong", provide the actual or a more meaningful error message.

When a document has many pages or contains a lot of text, there's a risk that it cannot be handled within the time limit and cannot be processed. Improve handling of such large documents.

Currently it's required to send two separate images or a PDF with two pages. It would be more convenient to also support cases where the front and back side of an ID/driver's license is on the same page.

Improve reading table structures on invoices or similar documents and correctly extracting and mapping their contents. Currently, when the table structure is complex, doesn't have clear headers and/or contains a lot of text, the extraction quality...

When line tems span multiple lines, the second part of the description often isn't picked up completely. Support the extraction of the additional information in the second/third line.

I would like to be able to download my statistics from my project

To validate the authenticity of a photo created with the Klippa Scanner SDK. Can be used in combination with the fraud module to validate that the photo was taken with the SDK.

Implement external APIs to validate Google Maps locations, check if someone is on a terrorism or PEP list