Notifications
Clear all
Topic starter
Hello!
I'm attempting to create a basic version of deep search but am encountering a 429 error. It appears the AI Agent node is making all requests concurrently.
Since the HTTP Request tool lacks batching or retry capabilities (unlike the HTTP Request node), I'm unsure how to proceed.
Thank you for your assistance!
Describe the problem/error/question
When utilizing the AI Agent node, it seems to initiate all HTTP requests simultaneously, leading to a 429 error.
What is the error message (if any)?
"There was an error: "Request failed with status code 429""
Please share your workflow
Information on your callin.io setup
- callin.ioVersion: 1.77.3
- platform: docker (self-hosted)
- nodeJsVersion: 20.18.2
- database: postgres
- executionMode: scaling
Posted : 10/02/2025 12:42 pm
It appears your topic is missing some crucial details. Could you please provide the following information, if relevant?
- callin.io version:
- Database (default: SQLite):
- callin.io EXECUTIONS_PROCESS setting (default: own, main):
- Running callin.io via (Docker, npm, callin.io cloud, desktop app):
- Operating system:
Please provide the requested information.
Posted : 10/02/2025 12:42 pm
Hi there,
Could you try inserting a wait node prior to sending it to the Agent?
Posted : 10/02/2025 4:48 pm
Topic starter
I've tested this, and it doesn't seem to have any effect. I also attempted using a loop over items, but it made no difference because the agent itself is invoking the HTTP sub-node multiple times (3-5 calls).
Posted : 10/02/2025 6:15 pm
Instead of utilizing the HTTP Tool Node, have you considered moving the HTTP Request to a separate workflow and employing it as a Custom tool?
Here is my primary agent workflow:
Here is my custom tool workflow:
Posted : 12/02/2025 6:06 am
Topic starter
Hi mcnaveen,
Thanks for getting back to me.
I've also attempted that approach, but regrettably, the workflow is initiating multiple times concurrently, leading to the same error.
Posted : 12/02/2025 8:33 am
It ought to function. Which API endpoint are you invoking?
RapidAPI?
Kindly share the rewritten markdown content.
Posted : 12/02/2025 8:45 am
Hello there! Your input would be greatly appreciated.
Posted : 12/02/2025 4:28 pm
Topic starter
Hey
Did you discover a workaround for this?
Posted : 17/02/2025 1:53 pm
You can leverage the AI Agent to format the desired output, and then utilize the standard HTTP request node subsequent to the agent within your workflow to configure any retry mechanisms or failure handling.
Have you explored this method?
Posted : 17/02/2025 1:56 pm
This thread was automatically closed 90 days following the last response. New replies are no longer permitted.
Posted : 18/05/2025 1:56 pm