When datalog is enabled, this API allows you to import document extractions into FormX's training database. These stored documents serve as training samples to improve Smart Learning accuracy over time.

The document_data parameter must contain the ground truth (correct extraction values) for the document. Using incorrect data will negatively impact model accuracy. The required schema matches the data object structure returned by the /v2/extract endpoint.

All imported documents are retained according to your configured retention period and automatically become available as training samples for the Smart Learning system.

Note: Datalog is an enterprise feature. Please contact sales if you are interested in enabling this capability for your account.