search

awslabs / multi-agent-orchestrator

Flexible and powerful framework for managing multiple AI agents and handling complex conversations
https://awslabs.github.io/multi-agent-orchestrator/
Apache License 2.0
1.75k stars 117 forks source link

Added model router example #60

Closed veeragoni closed 13 hours ago

veeragoni commented 1 month ago

Issue number:

Summary

An inherent capability of MAO is ability to route the request to different models based on the context using its classifier. In this demo, I have showed an example of how to route the route the request to different models based on cost vs. reliability vs. privacy.

Acknowledgment

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

Disclaimer: We value your time and bandwidth. As such, any pull requests created on non-triaged issues might not be successful.

cornelcroi commented 1 month ago

Thank you for submitting this PR. The concept of utilizing various agents for tasks based on their performance and cost-effectiveness is really good. However, we can enhance this approach by incorporating realistic business scenarios. I'd like to see a concrete business use case in each example. At present, it's unclear how the classifier would effectively route tasks using the descriptions provided in this PR.

veeragoni commented 13 hours ago

agreed. let me close this for now and add more industry specific use case