Replies: 4 comments
|
Were you able to figure this out? |
0 replies
|
Not yet 😓 A native feature or guide for it would be great. I found this tutorial on the OpenAI cookbook. I will give it a shot next time I work on this and report back if it works. Otherwise, I'm still open to suggestions |
0 replies
|
use a custom agent and add the parallel agent in the custom agent. in the run async method you can define a python script to run for N times. |
0 replies
|
Or preferable define the N condition in a python function and add it to a custom agent. No parallel agent explicitly required. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Does anyone know what is the recommended strategy to run N parallel web searches without knowing N in advance ? I want to maintain the standard Google ADK agent structure (root_agent) so I can use it in the Web UI. I need the parallelism because latency is critical.
Example: the user gives a list of N names. The agent (or deterministic workflow) runs N parallel web searches, one per person.
All reactions