Get the entire text of a document after Decode

[aropb]

What is the easiest way to get the entire text of a document after Decode?

[dluc]

@aropb I'm not sure I understand what you're trying to do. If you only need to extract text from documents, you can use the classes available here https://github.com/microsoft/kernel-memory/tree/main/service/Core/DataFormats

[aropb]

I need to get the all extracted text of the entire document after the ImportDocument. That is, not parts, but the whole text.

[dluc]

The solution does not store the full text in the Vector Store, only chunks.
In the Document Store you can find the full text of each document if that works, though there is no API to retrieve that file, so you'd have to write code to access your specific storage and retrieve that file manually.

[aropb]

I'm a little surprised by the response, I've added a new step to the pipeline. There I take all the extracted text and summary.

[dluc]

Looks good, using custom handlers is one of the intended ways to extend the solution. You can also use handlers to store new synthetic memories and later use the Search API to retrieve them