General tab - Properties of Auto Extract Locator window

The Auto Extract Locator method uses a large language model alongside natural language instructions to extract data from a document. This means users can provide a simple worded description to explain what data you want to extract. There is no need for additional configuration, scripts, or training.

Use the table on this tab to Manage subfields and their description.

The table has the following columns:

Subfield Name

The name of the subfield.

Description

This column contains a list of description for the subfield. There must be a description for each subfield.

When you select a subfield, click Edit to open the Description for Subfield window and provide a description for the corresponding subfield.

Below the table is the following setting:

Number of pages

This setting restricts the number of pages that are processed in a document. (Default: 10)

This also restricts the number of pages that are recognized. If you have a 50-page document and the value for this setting is set to 15, OCR is performed for the first 15 pages only.

The more pages processed increases the cost due to the higher consumption of volume licenses.

Use the following buttons to manage the table of subfields and their descriptions:

Button

Description

   Add

Adds a blank subfield and alias row to the table so you can edit the two columns as needed.

  Delete

Removes the selected row from the table.

  Up

Moves the selected row one position higher in the table.

  Down

Moves the selected row one position lower in the table.

The following buttons are available at the bottom of this window:

Button

Description

Close

Closes the window and saves your changes.

Test icon   Test

Tests the locator settings. The results are displayed on the Test Results tab that is displayed automatically when you click this button.

Depending on the locator method, this button may have additional modes if the locator uses other locators as input.

Help icon  Help

Displays the help for the open window.

Related topics: