Replies: 1 comment
-
|
Response from ADK Answering Agent (experimental, answer may be inaccurate) TLDR: The recommended ADK-compliant pattern is to run your Hello! That's an excellent question about designing a robust, real-time agentic system. Running a continuous, CPU-bound task alongside an asynchronous framework like ADK requires careful architecture to avoid blocking and maintain responsiveness. Here’s a breakdown of the recommended pattern and answers to your specific questions. Recommended Design: Sidecar Process with API CommunicationThe most scalable and non-blocking approach is to decouple your CPU-intensive
Why Not Use
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Context
I’m building a RootAgent that orchestrates two main components:
TriggerAgent – continuously processes camera frames in a loop.
SequentialAgent – contains about ten sub-agents.
TriggerAgentwhen an event occurs.TriggerAgent.Both agents are children of a RootAgent, which manages orchestration and data flow between them.
Question
What is the recommended ADK-compliant design pattern for this kind of workflow?
Specifically:
TriggerAgentbe offloaded to a separate thread usingrun_in_executor()or to a separate process/server as suggested in the Long-Run Tool section of the ADK docs?
alongside the main async orchestration loop?
ctx.session.state)?Goal
I want to keep the architecture responsive, modular, and fully compatible with ADK, if possible,
so that the trigger loop can continuously process input data without blocking
other asynchronous agents or workflows managed by the root agent.
Beta Was this translation helpful? Give feedback.
All reactions