It would be nice if n8n could natively handle certain PDF functions. Please see https://www.ilovepdf.com/ for ideas.
The most important features are:
- split
- merge
- convert to image
- OCR
It would be nice if n8n could natively handle certain PDF functions. Please see https://www.ilovepdf.com/ for ideas.
The most important features are:
Oh yes! It would be awesome!
Looking for this feature aswell ![]()
Yes it will be nice ![]()
Being able to export PDFs to images would be a game changer to enable multi-modal RAG using vision LLMs in n8n cloud. Right now, the only option is to build/use an external API to convert the PDF to images. Alternative would be to support a javascript and/or python package for pdf operations (also PDF to markdown would be great for LLMs) in n8n cloud.
I found out that Edit Image node can input PDF and turn it to PNG while resizing if the ImageMagic is installed at least in self hosted n8n.
any update here?
There’s a new approved node by PDFAPIHub that supports PDF Split Merge and other PDF operations.
You can find it here: PDF API Hub integrations | Workflow automation with n8n