Hello, so in my workflow i have a node that extracts PDF tekst from pdf and then sends it to code node that searches for a pages in thats teks that i need to extract, is there a way to put another code node that will extract only the tekst from those pages and then send it to next node thath will turn it into CSV or PDF again?
Could you ctl a, ctl c the workflow, click the ‘</>’ button on the forums when drafting a reply and paste the workflow into the field that appears? Will help with context.
Some other ideas tho could be the use of GPT to search and provide page numbers. Or something like pdfco.
This is the current workflow, the code node before convert to CSV is something i tryed to make but its not working properly.
About PDF.co i tried to connect it but it keeps erroring me that some kind of signature is not right. Two error i run into are
and
i changed the key a few times tried everything chatgpt and deepseek offerd and it still errord. This is the workflow i used:
So if i can connect PDFco it would be much better then code nodes.
Where are those errors occurring? On which nodes?
I dont quite follow the need for all the merges. You can access earlier data via $(‘Node Name’) instead of $json which is just an “alias” for the last node. No need to merge to access previous node information.
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.