Develop and deploy agents on Vertex AI Agent Engine

This page demonstrates how to create and deploy an agent that returns the exchange rate between two currencies on a specified date, using the following agent frameworks:

• Agent Development Kit (ADK)

• LangGraph

• LangChain

• AG2

• LlamaIndex Query Pipeline (preview)

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ドル 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 (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI and Cloud Storage 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

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 (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI and Cloud Storage 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

To get the permissions that you need to use Vertex AI Agent Engine, ask your administrator to grant you the following IAM roles on your project:

• Vertex AI User (roles/aiplatform.user)
• Storage Admin (roles/storage.admin)

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.

Install and initialize the Vertex AI SDK for Python

1. Run the following command to install the Vertex AI SDK for Python and other required packages:

   ADK

   pipinstall--upgrade--quietgoogle-cloud-aiplatform[agent_engines,adk]>=1.112

   LangGraph

   pipinstall--upgrade--quietgoogle-cloud-aiplatform[agent_engines,langchain]>=1.112

   LangChain

   pipinstall--upgrade--quietgoogle-cloud-aiplatform[agent_engines,langchain]>=1.112

   AG2

   pipinstall--upgrade--quietgoogle-cloud-aiplatform[agent_engines,ag2]>=1.112

   LlamaIndex

   pipinstall--upgrade--quietgoogle-cloud-aiplatform[agent_engines,llama_index]>=1.112

2. Authenticate as a user

   Colab

   Run the following code:

   fromgoogle.colabimport auth
   auth.authenticate_user(project_id="PROJECT_ID")
   

   Cloud Shell

   No action required.

   Local Shell

   Run the following command:

   gcloudauthapplication-defaultlogin

3. Run the following code to import Vertex AI Agent Engine and initialize the SDK:

   importvertexai
   client = vertexai .Client(
    project="PROJECT_ID", # Your project ID.
    location="LOCATION", # Your cloud region.
   )
   

   Where:

   • PROJECT_ID is the Google Cloud project ID under which you develop and deploy agents

   • LOCATION is one of the supported regions.

Develop an agent

First, develop a tool:

defget_exchange_rate(
 currency_from: str = "USD",
 currency_to: str = "EUR",
 currency_date: str = "latest",
):
"""Retrieves the exchange rate between two currencies on a specified date."""
 importrequests
 response = requests.get(
 f"https://api.frankfurter.app/{currency_date}",
 params={"from": currency_from, "to": currency_to},
 )
 return response.json()

Next, instantiate an agent:

fromgoogle.adk.agentsimport Agent
fromvertexaiimport agent_engines
agent = Agent(
 model="gemini-2.0-flash",
 name='currency_exchange_agent',
 tools=[get_exchange_rate],
)
app = agent_engines.AdkApp(agent=agent)

fromvertexaiimport agent_engines
agent = agent_engines.LanggraphAgent(
 model="gemini-2.0-flash",
 tools=[get_exchange_rate],
 model_kwargs={
 "temperature": 0.28,
 "max_output_tokens": 1000,
 "top_p": 0.95,
 },
)

fromvertexaiimport agent_engines
agent = agent_engines.LangchainAgent(
 model="gemini-2.0-flash",
 tools=[get_exchange_rate],
 model_kwargs={
 "temperature": 0.28,
 "max_output_tokens": 1000,
 "top_p": 0.95,
 },
)

fromvertexaiimport agent_engines
agent = agent_engines.AG2Agent(
 model="gemini-2.0-flash",
 runnable_name="Get Exchange Rate Agent",
 tools=[get_exchange_rate],
)

fromvertexai.previewimport reasoning_engines
defrunnable_with_tools_builder(model, runnable_kwargs=None, **kwargs):
 fromllama_index.core.query_pipelineimport QueryPipeline
 fromllama_index.core.toolsimport FunctionTool
 fromllama_index.core.agentimport ReActAgent
 llama_index_tools = []
 for tool in runnable_kwargs.get("tools"):
 llama_index_tools.append(FunctionTool.from_defaults(tool))
 agent = ReActAgent.from_tools(llama_index_tools, llm=model, verbose=True)
 return QueryPipeline(modules = {"agent": agent})
agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
 model="gemini-2.0-flash",
 runnable_kwargs={"tools": [get_exchange_rate]},
 runnable_builder=runnable_with_tools_builder,
)

Finally, test the agent locally:

async for event in app.async_stream_query(
 user_id="USER_ID",
 message="What is the exchange rate from US dollars to SEK today?",
):
 print(event)

agent.query(input={"messages": [
 ("user", "What is the exchange rate from US dollars to SEK today?"),
]})

agent.query(
 input="What is the exchange rate from US dollars to SEK today?"
)

agent.query(
 input="What is the exchange rate from US dollars to SEK today?"
)

agent.query(
 input="What is the exchange rate from US dollars to SEK today?"
)

Deploy an agent

To deploy the agent:

remote_agent = client.agent_engines.create(
 agent=app,
 config={
 "requirements": ["google-cloud-aiplatform[agent_engines,adk]"],
 }
)

remote_agent = client.agent_engines.create(
 agent,
 config={
 "requirements": ["google-cloud-aiplatform[agent_engines,langchain]"],
 },
)

remote_agent = client.agent_engines.create(
 agent,
 config={
 "requirements": ["google-cloud-aiplatform[agent_engines,langchain]"],
 },
)

fromvertexaiimport agent_engines
remote_agent = agent_engines.create (
 agent,
 config={
 "requirements": ["google-cloud-aiplatform[agent_engines,ag2]"],
 },
)

fromvertexaiimport agent_engines
remote_agent = agent_engines.create (
 agent,
 config={
 "requirements": ["google-cloud-aiplatform[agent_engines,llama_index]"],
 },
)

This creates a reasoningEngine resource in Vertex AI.

Use an agent

Test the deployed agent by sending a query:

async for event in remote_agent.async_stream_query(
 user_id="USER_ID",
 message="What is the exchange rate from US dollars to SEK today?",
):
 print(event)

remote_agent.query(input={"messages": [
 ("user", "What is the exchange rate from US dollars to SEK today?"),
]})

remote_agent.query(
 input="What is the exchange rate from US dollars to SEK today?"
)

remote_agent.query(
 input="What is the exchange rate from US dollars to SEK today?"
)

remote_agent.query(
 input="What is the exchange rate from US dollars to SEK today?"
)

Clean up

To avoid incurring charges to your Google Cloud account for the resources used on this page, follow these steps.

remote_agent.delete(force=True)

What's next

• Explore the notebooks.
• Set up the environment.
• Develop an agent.
• Deploy an agent.
• Use an agent.
• Manage an agent.
• Get support.