I have a flow that is using a lot of tokens, and I’m hitting the tpm rate limit with my OpenAI API credentials. I’m wondering if there’s a way I can put in a one or two minute delay between some of my heavier AI nodes in the flow? I couldn’t find this in the docs or the forum.
Right now the flow just fails because of the rate limiting, and I’d rather it pause, and then continue than fail outright.
Hey @JS14! 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.
You could try using a Run Code node with Python.
I just tried adding such node between a webscraper node and an Ask AI node, using the simple code below that waits fordelayseconds before passingcontentto the next node :
def function(delay, content):
import time
time.sleep(int(delay))
return content
There’s no built-in delay node at the moment, but you can work around it by building a custom node. I’ve shared one with you called “Delay and Pass Through”, you should be able to find it in your node library by searching that name.