Does the Dify platform's document extractor not support scanned PDFs?

Discussion
1

Does the Dify platform’s document extractor not support scanned PDFs?

446de0ff049543645c16d9ff194a5ff9
446de0ff049543645c16d9ff194a5ff92773×1280 213 KB

I uploaded a scanned PDF, and after processing it with the file extractor, the output text was “”, so when passed to the large model, it became “No file content detected!”

2

Nope, this node can only extract texts from the PDF files, if you want to extract things in the images, please use minerU or PaddleOCR instead.