What is your goal?
I want to upload a pdf purchase order in the file column of an item on monday.com and then extract each line item (and certain details ie qty, desc etc) from the pdf and create them as sub items of the parent item for our manufacturing department.
What is the problem & what have you tried?
i have tried different modules, data extractions, parsers etc but i cant seem to extract the correct data or have it map correctly
Screenshots (scenario flow, module settings, errors)
Hey Chanelle,
you want to extract the data from the PDF? Or somewhere else?
If its the PDF, then you need one of the apps that does PDF OCR, there are plenty available to choose from.
its a pdf document that has been uploaded to a monday.com file column, would the PDF OCR work for this?
You can do the OCR before uploading it to Monday.
What does the PDF look like in the first place?
Or you can also download it from monday and then send it to the OCR app too.
Looks like the hard part here is not monday itself, but getting the PDF line items into a clean structured format first.
If the extracted text is messy, mapping will always be unreliable. I’d first focus on turning the PDF into an array of line items, then iterate over that array and create one subitem per line. Trying to parse and map everything in one go usually gets messy fast.
So the main issue is probably the extraction/parsing step, not the subitem creation step.
Use Make AI Content Extractor > Extract text from a document module
