andreagrandi Hello, I’m trying to summarise this https://www.datocms-assets.com/30196/1683276599-bilancio-di-esercizio-unicef-italia-2022-copertina.pdf but I get this error: We are sorry, we are not able to extract the source I would expect the document to be summarised
EvacuatedTerminal I suspect the text in the PDF isn't selectable or embedded, which might be why Kagi can't use it. Perhaps OCR could be fix this, but that would probably be another suggestion. The error messages could be more descriptive though.
andreagrandi Vlad thanks for the clarification, but for example I was able to summarise this https://www.wwf.it/uploads/Bilancio-Sociale-2022.pdf which is also in Italian so I assumed that the language wasn't an issue.
Vlad andreagrandi That is a regular PDF and does not require OCR. We support any language as long as it is text. For PDFs/images that need to be OCR'd - only english.
