Wei (Jack) Sun
1c64a41b53
Introduces two major capabilities: - Workflow runtime: graph-based execution engine for composing deterministic execution flows for agentic apps, with support for routing, fan-out/fan-in, loops, retry, state management, dynamic nodes, human-in-the-loop, and nested workflows - Task API: structured agent-to-agent delegation with multi-turn task mode, single-turn controlled output, mixed delegation patterns, human-in-the-loop, and task agents as workflow nodes Co-Authored-By: Bo Yang <ybo@google.com> Co-Authored-By: George Weale <gweale@google.com> Co-Authored-By: Sean Zhou <seanzhougoogle@google.com> Co-Authored-By: Shangjie Chen <deanchen@google.com> Co-Authored-By: Swapnil Agarwal <swapnilag@google.com> Co-Authored-By: Wei Sun <weisun@google.com> Co-Authored-By: Xuan Yang <xygoogle@google.com> Co-Authored-By: Yifan Wang <wanyif@google.com> Change-Id: I35932c50cfe29ff68559e3781713dbb5eb7b3382
ADK Workflow Sequence Sample
Overview
This sample demonstrates how to create a simple sequential workflow with ADK Workflows.
It connects two LLM agents in a chain. The first agent (generate_fruit_agent) is instructed to return the name of a random fruit. The output of this agent becomes the input for the second agent (generate_benefit_agent), which then tells a health benefit about that specific fruit.
In a sequence, the execution flows unconditionally from one node to the next in the order they are defined.
Sample Inputs
This sample does not require any input to run.
Graph
[ START ]
|
v
[generate_fruit_agent]
|
v
[generate_benefit_agent]
How To
-
Define the agents or functions that will make up the steps in your sequence.
generate_fruit_agent = Agent(...) generate_benefit_agent = Agent(...) -
Pass a tuple of three or more elements to
edgesto define an unconditional sequence starting from the first element and passing through each subsequent node in order.Workflow( name="root_agent", edges=[("START", generate_fruit_agent, generate_benefit_agent)], )