I need to somehow carry the input file all the way through this flow to return it as an output along with the final rewritten brief output in the final step. The issue is, there are many loops of the Drive file analysis step that encounter errors and are skipped with my error shield, so there is a risk of list mismatch with any Drive file I attempt to pass through.
I would appreciate any input on how to solve this! I’m sure it’s something simple.
Hey @Peter_Czepiga! 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 @Peter_Czepiga, the issue you’re facing can be solved using a subflow. Since you’re working with multiple URLs and want to avoid list mismatch issues, subflows make this much easier.
You can keep the Drive Folder Reader in your main flow and pass its output into a subflow that contains your creative brief writer nodes. The subflow will process each URL one at a time, so you don’t need to handle lists or worry about errors breaking the sequence. This also makes the flow much easier to manage.
Also, because your input files can be either videos or images, I used a Join Paths node after the Analyze Video and Analyze Image nodes inside the subflow. That makes sure whichever node successfully processes the file, its result continues to the next step.
Let me know if that helps or if you have any questions.
I really appreciate the help @Rithen_Gumloop. I tested your flow, and I seem to always get a blank output now. The “Ask AI” node that reformats the Google Drive file into a download link is still working, but then the “Analyze Image” and “Analyze Video” nodes no longer recognize the file as an input. They simply return a blank output.
Hey @Peter_Czepiga, I think I figured out what was going wrong.
It looks like your flow was set up to return Drive links, but since I moved everything into a subflow, the files were being returned directly instead. That mismatch is probably what caused the error when you ran it.
Also removed the Ask AI node that was formatting the links. Now the files go straight into the Analyze Image and Analyze Video nodes, which should work more reliably.
Give it a spin and let me know if it works better now.
This worked perfectly, thank you @Rithen_Gumloop! I can now pass through the Drive file to the end of the flow. However, I have one small issue. The Drive file output that is passing through is not a readable Google Drive link. It is in this format (example): 1RaU2XBi_nSJc2b6YO1VF80aFaAzjupic/Statics + Headlines_Luka_Get a better breed of Style 2.png
It seems to be combining the folder ID with the file name. Do you know if it’s possible to return the actual openable Drive file link?
The reason your Analyze Image/Video nodes were breaking is that once you switched to passing file links, those nodes needed to be updated to accept URLs instead of the raw file objects they were originally getting.
This above workflow has those changes in place, so the links from the Drive Folder Reader will work all the way through. Give it a try and let me know if you need any more help.
