Whatsup. I’m building a flow that extracts this months data from PDFs, reads previous months data in a google sheet, sends both to an ask AI to process, then updates a google sheet with this months data. In loop mode
Gummie has sent me on a wild goose chase with both JSON and CSV format. I keep getting errors. First my ask AI is saying it is getting 2 inputs from one node (The pdfs) when it should be getting 24 inputs, which doesn’t match the 24 inputs from the sheets reader node.
The other issue is that the sheets updater is recieving inputs in a list of list format, but needs the search key (to find the row its filling in) also in list of list format (which is impossible because it should just be a list) e.g. Kloba AI_Update, Dilla AI_Update.
extract to table isn’t really good enough for my usecase
Hey @TalF! If you’re reporting an issue with a flow or an error in a run, please include the run link and make sure it’s shareable so we can take a look.
Find your run link on the history page. Format: https://www.gumloop.com/pipeline?run_id={{your_run_id}}&workbook_id={{workbook_id}}
Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
Provide details about the issue—more context helps us troubleshoot faster.
Hey @TalF – The best approach here would be to create a subflow to restructure your workflow. I’d recommend building the suflow that works for a single input (like a single file). Once you’ve got the subflow working with just one file, you can loop it over your list of files.
By working backwards from a single input, you’ll avoid those list of lists and list size errors completely.