You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm not sure if this makes sense, so I'd like your take.
I've built some pipelines with "local" agents, using llama-index/workflows and my pipeline essentially acts an agent.
Now that Google's A2A protocol has been introduced and getting traction - if I wanted to use remote a2a agents within my pipeline I could always have an a2a client within my pipeline to interact with them...
But does it make sense to expose my pipeline through/as an A2A server and how that integration might be done automagically with all of my pipelines? Is that a feature may be implemented in the future?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello,
I'm not sure if this makes sense, so I'd like your take.
I've built some pipelines with "local" agents, using llama-index/workflows and my pipeline essentially acts an agent.
Now that Google's A2A protocol has been introduced and getting traction - if I wanted to use remote a2a agents within my pipeline I could always have an a2a client within my pipeline to interact with them...
But does it make sense to expose my pipeline through/as an A2A server and how that integration might be done automagically with all of my pipelines? Is that a feature may be implemented in the future?
Beta Was this translation helpful? Give feedback.
All reactions