0

I want to extract structured text from PDF contracts with the Google Cloud Vision DOCUMENT_TEXT_DETECTION API.

Is the service configurable? For example, can I set the minimum vertical blank space the system uses to split paragraphs?

double-beep
  • 5,031
  • 17
  • 33
  • 41
Théophile Gervet
  • 11
  • 2

1 Answers1

1

I don't think you can do that with DOCUMENT_TEXT_DETECTION. For that level of customization, you can check out Google Cloud Platform's Document AI product.

Brendan
  • 1,017
  • 5
  • 7
  • FYI, Document AI has an actively monitored tag [`[cloud-document-ai]`](https://stackoverflow.com/questions/tagged/cloud-document-ai) --- I recommend referring to these videos/labs about Document AI https://cloud.google.com/document-ai/docs/videos And this page for more information about the data extracted from documents. https://cloud.google.com/document-ai/docs/handle-response – Holt Skinner Mar 28 '23 at 21:36