Skip to content

Train-your-own Extraction Model#

Our API Hub offers a wide variety of pre-built extraction workflows. However, your specific business problem may not be included. With our train-your-own extraction capabilities, you can solve any extraction use case outside of our provided models. You have complete control over the entities you want to extract and can get a model up and running in no time.

The steps required to build your own extraction model are fairly simple and straightforward. Just follow our simple wizard:

  • Define the entities you want to extract from your documents step 1
  • Upload your documents: You can specify individual templates, or just upload all your documents in one place if they don't follow specific templates) step 2
  • Annotate your documents by selecting an entity on the left and assigning it to the text boxes on the right. step 3
  • Train your model and explore the analysis for each entity to see what can be improved. step 4

You can check this blog post to see the steps in detail.

Once training is complete, this workflow will provide you with extractions and ocr. Your workflow identifier is a UUID that is automatically generated during the creation process, i.e. you can call the workflow like any other workflow using the at the processing endpoint i.e. POST /processing/{your_workflow_identifier}.

Supported return values#

As automatically included in the response JSON, unless otherwise specified via include query parameters.

Credit cost#

A Freemium account allows for up to 100 pages per month, where the cost is 80 credits per page, and 120 credits per document.

Note

A document is usually a bundle of 10 pages.

Extractions format#

The value of the extractions key for this workflow is based on your specifications in the "Define Fields" wizard step.

Note

For a reference of the structure of each of the extractions objects see Extracted Values. Also, for accessing individual processing results or artifacts, have a look at Fetch Processing Results and Artifacts.

Important

The structure of extractions might contain optional paths. See this and this part of the documentation.

Previewing Workflow Updates#

natif.ai is constantly improving the model architectures and baselines for self-trained workflows which sometimes requires (beneficial) updates to existing workflows. In order to not interfere with productive usage of your workflow, natif.ai will inform you in advance by email about such updates and will provide a preview version of the upcoming workflow update for you to try out before the automatic migration.

Please refer to the preview endpoint documentation to make use of the endpoint to test the upcoming version of your workflow for production usage and provide feedback to us.