The impossible flow: OpenAI + PDF files

[Digital_Humanism]

Hello everyone.
I’ve searched through all the posts about the same thing for a while, and no one seems to give a clear solution. It is like an unsolvable problem

I’m trying to pass a PDF that I pull from Google Drive to the OpenAI node, but it’s literally impossible. It doesn’t matter if I put the G.Drive Download File node first and pass the result to a chat completion or an assistant or if I first pass it through an OpenAI Upload File node, nothing. And i did check the File retrieval function with the same result.
I see that there is a field to easily attach an image, why doesn’t the same exist for attaching files?

If anyone has achieved this, could you describe to me what I should pass to the OpenAI node and where to put it?

Thank you

[Mit]

I’m trying to do the exact same, but from OneDrive. I’m stuck on the last bit which is the openAI section.

I found best to use the HTTP to get the file ID and Name and then pass to openAI upload module

My challenge is that I’m stuck on this bit:

I hope this helps in some way

[Mit]

I figured it out!! Made a whole post about it

How to PDF into openAI (Solution!)

Ok, after much messing about I managed to figure it out, as searching wasn’t helping. Hopefully this helps others out there. In summary; use openAI upload module, but make sure the file name has the correct extention. Then you need to move this file into a Vector Store that you have already created (you could create via an api call if you wanted too). Then when you use the openAI assistant module, you use file search feature. It only works with GPT-4, and file search only works with vector …