Inserting multiple images at ones in OpenAI Vision Node

Help me Build my Workflow
1

I’m trying to convert PDFs into images so I can process them with the Vision API. The issue is that these PDFs have multiple pages, meaning that when I convert them, I end up with multiple images (e.g., data0, data1, data2, etc.).

My challenge is dynamically handling the images since the number of pages varies with each iteration. Is there a way to upload all the images at once and get the extracted text for all of them, or do I need to process them one by one? If so, how should I do it?

2

Hello, if I understand well, you want to have all the text from a single PDF but you are processing each chunk of text you get from the vision API separately ?

You could aggregate all the outputs at the end of the loop and give them all to process ?