Enabling persistent text extraction

Enable persistent text extraction for document classes to store extracted text as annotations for use with content-based retrieval indexing, vector indexing, document summarization, and generative AI inferences.

Before you begin

Ensure that the Persistent Text Extraction add-on is installed. For more information about the classes and properties used for persistent text extraction, see Persistent Text Extract Extensions.

About this task

By default, document classes are not enabled for persistent text extraction. When you enable persistent text extraction for a document class, the feature applies to the class and all subclasses. Text is automatically extracted from new documents that are added to the object store.

Procedure

To enable persistent text extraction for a document class:

  1. In the administration console, navigate to the object store where you want to enable text extraction.
    1. In the domain navigation pane, select the object store.
    2. In the object store navigation pane, select Data Design > Classes.
  2. Select Document or any document subclass for which you want to enable persistent text extraction.
    To extract text from all incoming documents, enable persistent text extraction for the base Document class.
  3. On the General tab, select the Persistent Text Extracts enabled checkbox.
    If the checkbox is already selected and appears unavailable, the option is inherited from the parent class.
  4. Click Save to apply the changes to the document class.

Results

Persistent text extraction is enabled for the document class and all subclasses. Text is automatically extracted from new documents and stored as Text Extraction Annotation objects.