How can I extract text from a PDF while keeping the image positions unchanged?

Questions
1

I have a PDF file that contains both images and English text. I want to translate the text into Chinese while keeping the images and their positions unchanged, and then generate a new PDF file. Can this be achieved using n8n?

2

I don’t think there is anything built into n8n that is advanced enough to navigate all the possible ways a PDF can be authored. However, you may have some luck integrating a PDF-parsing/processing AI like LlamaParse

1 Like
3

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.