from google.adk.brokers import Agent from google.adk.instruments import google_search root_agent = Agent( identify="search_assistant", description="An agent that solutions questions augmented with net searches.", mannequin="gemini-2.0-flash", instruction="Reply questions offered by the consumer. Evaluate and distinction data gathered from Google with your personal data. If you're given an announcement that isn't a query, reply, 'Please ask me a query.'", instruments=[google_search] ) Each time we wish to create a definite agent, we arrange a subdirectory in our foremost mission listing and provides it a reputation (on this case, searchagent). This lets us have a number of brokers in a single mission, which may run on their very own or interoperate.
The __init__.py file marks the listing as being an agent, by importing the precise agent code. The agent.py file units up the agent itself, as described by the Agent object.
Every Agent makes use of a mannequin API to interface with (right here, it’s gemini-2.0-flash). Our preliminary instructions to the agent, which prefix every enter from the consumer, are outlined in directions. Notice that these directions might be much more detailed than what we’re offering right here. The instruments part supplies extra tooling that can be utilized by the agent; google_search lets the agent use Google searches to enhance its outcomes.
