Build and deploy an AI agent to Cloud Run using the Agent Development Kit (ADK)

Preview — The Python buildpack supports default entrypoint detection for the Agent Development Kit (ADK) framework google-adk

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

The Agent Development Kit (ADK) framework simplifies the creation, evaluation, and deployment of AI agents. ADK provides a modular, code-first approach to building agents that can reason, plan, and utilize tools.

This tutorial shows you how to build and deploy an AI agent to Cloud Run using ADK for Python. This agent retrieves the weather report for a city you specify.

For more information about hosting your ADK agent using the Google Cloud CLI, see Deploy to Cloud Run in ADK documentation.

Objectives

• Write the sample application to define the weather-agent.
• Deploy the agent to Cloud Run from source.
• Run your agent to query weather information.

Costs

In this document, you use the following billable components of Google Cloud:

• Artifact Registry
• Cloud Build
• Cloud Run
• Vertex AI

To generate a cost estimate based on your projected usage, use the pricing calculator.

New Google Cloud users might be eligible for a free trial.

Before you begin

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

1. Enable the Cloud Run Admin API, Vertex AI API, and Cloud Build APIs.

   Roles required to enable APIs

   To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

   Enable the APIs

2. Set up your Cloud Run development environment in your Google Cloud project.
3. Install ADK by following the instructions in the Agent Development Kit documentation.

4. If you are under a domain restriction organization policy restricting unauthenticated invocations for your project, you will need to access your deployed service as described under Testing private services.

Required roles

To get the permissions that you need to deploy an AI agent to Cloud Run, ask your administrator to grant you the following IAM roles:

• Cloud Run Source Developer (roles/run.sourceDeveloper) on the project
• Vertex AI User (roles/aiplatform.user) on the project
• Service Account User (roles/iam.serviceAccountUser) on the service identity
• Logs Viewer (roles/logging.viewer) on the project

For more information about granting roles, see Manage access to projects, folders, and organizations.

You might also be able to get the required permissions through custom roles or other predefined roles.

Write the sample application

To write an application in Python:

1. Create a new parent directory named parent_folder and change directory into it:

   mkdir parent_folder
   cd parent_folder
   

2. In the parent_folder directory, create a new subdirectory named multi_tool_agent and change directory into it:

   mkdir multi_tool_agent
   cd multi_tool_agent
   

3. Create an __init__.py file to import the agent:

   from . import agent
   

4. Create an agent.py file to define the agent for answering questions about the time and weather in a specified city:

   import datetime
   from zoneinfo import ZoneInfo
   from google.adk.agents import Agent
   
   def get_weather(city: str) -> dict:
       """Retrieves the current weather report for a specified city.
   
       Args:
           city (str): The name of the city for which to retrieve the weather report.
   
       Returns:
           dict: status and result or error msg.
       """
       if city.lower() == "new york":
           return {
               "status": "success",
               "report": (
                   "The weather in New York is sunny with a temperature of 25 degrees"
                   " Celsius (77 degrees Fahrenheit)."
               ),
           }
       else:
           return {
               "status": "error",
               "error_message": f"Weather information for '{city}' is not available.",
           }
   
   def get_current_time(city: str) -> dict:
       """Returns the current time in a specified city.
   
       Args:
           city (str): The name of the city for which to retrieve the current time.
   
       Returns:
           dict: status and result or error msg.
       """
   
       if city.lower() == "new york":
           tz_identifier = "America/New_York"
       else:
           return {
               "status": "error",
               "error_message": (
                   f"Sorry, I don't have timezone information for {city}."
               ),
           }
   
       tz = ZoneInfo(tz_identifier)
       now = datetime.datetime.now(tz)
       report = (
           f'The current time in {city} is {now.strftime("%Y-%m-%d %H:%M:%S %Z%z")}'
       )
       return {"status": "success", "report": report}
   
   root_agent = Agent(
       name="weather_time_agent",
       model="gemini-2.0-flash",
       description=(
           "Agent to answer questions about the time and weather in a city."
       ),
       instruction=(
           "You are a helpful agent who can answer user questions about the time and weather in a city."
       ),
       tools=[get_weather, get_current_time],
   )
   

5. Create a .env file and add the following variables:

   GOOGLE_GENAI_USE_VERTEXAI=TRUE
   GOOGLE_CLOUD_PROJECT=PROJECT_ID
   GOOGLE_CLOUD_LOCATION=REGION
   

   Replace the following:

   • PROJECT_ID: the Google Cloud project ID.
   • REGION: the region you plan to deploy your service in.

6. Navigate to the parent folder directory parent_folder, and create a requirements.txt file to add the google-adk dependency:

   google-adk
   

   Your source project includes the following structure:

   parent_folder/
   ├── requirements.txt
   └── multi_tool_agent/
       ├── __init__.py
       ├── agent.py
       └── .env
   

Your app is finished and ready to be deployed.

Deploy to Cloud Run from source

Deploy from source automatically builds a container image from source code and deploys it.

1. In your source code directory (parent_folder), deploy to Cloud Run using the following command:

   gcloud beta run deploy --source .

   1. When you are prompted for the service name, press Enter to accept the default name, for example weather-agent.

   2. If you are prompted to enable additional APIs on the project, for example, the Artifact Registry API, respond by pressing y.

   3. When you are prompted for region: select the region of your choice, for example europe-west1.

   4. If you are prompted to create a repository in the specified region, respond by pressing y.

   5. If you are prompted to allow public access: respond y. You might not see this prompt if there is a domain restriction organization policy that prevents it; for more details see the Before you begin section.

   Then wait a few moments until the deployment is complete. On success, the command line displays the service URL. Navigate to /list-apps from your service URL. For example, https://weather-agent-123456789101.us-central1.run.app/list-apps.

Run your agent

To query the ADK agent, run the following curl commands:

1. To get the list of apps, run the following command:

   curl -X GET SERVICE_URL/list-apps
   

   Replace SERVICE_URL with the URL of your deployed service.

2. To start a session, run the following command:

   curl -X POST SERVICE_URL/apps/multi_tool_agent/users/u_123/sessions/s_123 -H "Content-Type: application/json" -d '{"key1": "value1", "key2": 42}'
   

3. To query the agent, run the following command:

   curl -X POST SERVICE_URL/run \
   -H "Content-Type: application/json" \
   -d "{\"appName\": \"multi_tool_agent\",\"userId\": \"u_123\",\"sessionId\": \"s_123\",\"newMessage\": { \"role\": \"user\", \"parts\": [{ \"text\": \"What's the weather in New York today?\" }]}}"
   

The agent returns the weather information in the results of your query.

For more information and examples about the supported curl commands, see Use the API Server in ADK documentation.

Success: You deployed an AI agent using the Agent Development Kit to Cloud Run.

Clean up

To avoid additional charges to your Google Cloud account, delete all the resources you deployed with this tutorial.

Delete the project

If you created a new project for this tutorial, delete the project. If you used an existing project and need to keep it without the changes you added in this tutorial, delete resources that you created for the tutorial.

The easiest way to eliminate billing is to delete the project that you created for the tutorial.

To delete the project:

Caution: Deleting a project has the following effects:

• Everything in the project is deleted. If you used an existing project for the tasks in this document, when you delete it, you also delete any other work you've done in the project.
• Custom project IDs are lost. When you created this project, you might have created a custom project ID that you want to use in the future. To preserve the URLs that use the project ID, such as an appspot.com URL, delete selected resources inside the project instead of deleting the whole project.

If you plan to explore multiple architectures, tutorials, or quickstarts, reusing projects can help you avoid exceeding project quota limits.

1. In the Google Cloud console, go to the Manage resources page.

   Go to Manage resources

2. In the project list, select the project that you want to delete, and then click Delete.
3. In the dialog, type the project ID, and then click Shut down to delete the project.

Delete tutorial resources

1. Delete the Cloud Run service you deployed in this tutorial. Cloud Run services don't incur costs until they receive requests.

   To delete your Cloud Run service, run the following command:

   gcloud run services delete SERVICE-NAME

   Replace SERVICE-NAME with the name of your service.

   You can also delete Cloud Run services from the Google Cloud console.

2. Remove the gcloud default region configuration you added during tutorial setup:

    gcloud config unset run/region
   

3. Remove the project configuration:

    gcloud config unset project