-
-
Notifications
You must be signed in to change notification settings - Fork 477
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[BUG] Multi-Agent Swarm for Logistics #515
Comments
I updated the OpenAI API in the logistics example to use gpt-4o-mini and accept an image URL as input instead of relying on the deprecated VisionAPI or local image uploads. With this change, the logistics example now works as expected. However, there is a caveat: some agents in the flow occasionally fail to process the image URL, despite the overall setup being consistent. A potential solution is to increase the max_loops value for each agent to allow additional attempts at processing the input, which may improve reliability and reduce the occurrence of these random failures. |
In colab, without an image file uploaded.
Upvote & Fund
The text was updated successfully, but these errors were encountered: