Hey everyone,
I’m trying to process two PDF files that have been uploaded via n8n’s native form trigger.
The problem is, there doesn’t seem to be a “data” field that I can use for a next step.
I can only map the file name, type, and mime.
Does anyone have a solution to access the “data” for these PDF files and make them usable?
Thank you.
It looks like your topic is missing some important information. Could you provide the following if applicable.
Welcome to the community @Avery_Hooks !
Ensure to copy your n8n workflow and paste it in the code block, that is in between the pairs of triple backticks, which also could be achieved by clicking </> (preformatted text) in the editor and pasting in your workflow.
```
<your workflow>
```
That implies to any JSON output you would like to share with us.
Make sure that you have removed any sensitive information from your workflow and include dummy or pinned data with it!
What do you imply by usable? If you want to query your PDF document with AI, take a look at this template for an inspiration, Ask questions about a PDF using AI | n8n workflow template.
If no AI is needed, check out this tutorial, https://www.youtube.com/watch?v=2OpXdY4LXqw
Hey @ihortom, thanks for this response.
The video is definitely helpful and along the right lines, but I’m trying to directly upload the PDF through the built in form submission node.
The node works to accept the PDF, but there’s no actual data that I can pass in to a converting to text node, or anything at all.
Just can’t figure out how to get the uploads into a format that I can use in the rest of the workflow.
Hey @Avery_Hooks , looks like you missed the point showing how to extract the text (if that is what you are after). I’ll make it really simple for you. Run this workflow
The data is in the binary variables, which in your case are called “Scope_of_Work” and “Pitch_Deck”. In my example it is just “data”.