Best way to extract PDF to field?

Doesn't https://www.drupal.org/project/search_api_attachments → directly provide the feature you want?

It gets me halfway there. It will store the attachment in the Solr index and allow me to search it.

But I also want to send the text to some AI LLMs using one of the AI modules. I haven't figured out how to get the text out of Solr in a way that they'll accept it. The parts are all there, but I can't make them talk to each other correctly. If you have any suggestions, let me know.

TIA.

I thought, Search API Attachments includes a field type to add to your entities to store the extracted text.

Really? That would be nice. But I don't see it. Is it buried in some other type? Am I missing it some how? Is there a place I should look?

TIA.

FWIW,
there is a field formatter that lets you show the extracted text
the extraction result is cached with key "search_api_attachments:$file_id" (See extractOrGetFromCache)