Desarrollar y desplegar agentes en Vertex AI Agent Engine
En esta página se muestra cómo crear e implementar un agente que devuelva el tipo de cambio entre dos monedas en una fecha específica. Para ello, se utilizan los siguientes frameworks de agentes:
Antes de empezar
- 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
(
roles/resourcemanager.projectCreator
), which contains theresourcemanager.projects.create
permission. Learn how to grant roles.
-
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 theserviceusage.services.enable
permission. Learn how to grant roles. -
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 theresourcemanager.projects.create
permission. Learn how to grant roles.
-
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 theserviceusage.services.enable
permission. Learn how to grant roles. -
Usuario de Vertex AI (
roles/aiplatform.user
) -
Administrador de almacenamiento (
roles/storage.admin
) Ejecuta el siguiente comando para instalar el SDK de Vertex AI para Python y otros paquetes necesarios:
ADK
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,adk]>=1.112
LangGraph
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,langchain]>=1.112
LangChain
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,langchain]>=1.112
AG2
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,ag2]>=1.112
LlamaIndex
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,llama_index]>=1.112
Autenticarse como usuario
Colab
Ejecuta el siguiente código:
from google.colab import auth auth.authenticate_user(project_id="PROJECT_ID")
Cloud Shell
No tienes que hacer nada.
Shell local
Ejecuta el siguiente comando:
gcloud auth application-default login
Ejecuta el siguiente código para importar Vertex AI Agent Engine e inicializar el SDK:
import vertexai client = vertexai.Client( project="PROJECT_ID", # Your project ID. location="LOCATION", # Your cloud region. )
Donde:
PROJECT_ID
es el Google Cloud ID de proyecto en el que desarrollas y despliegas agentes.LOCATION
es una de las regiones admitidas.
Para obtener los permisos que necesitas para usar Vertex AI Agent Engine, pide a tu administrador que te conceda los siguientes roles de gestión de identidades y accesos en tu proyecto:
Para obtener más información sobre cómo conceder roles, consulta el artículo Gestionar el acceso a proyectos, carpetas y organizaciones.
También puedes conseguir los permisos necesarios a través de roles personalizados u otros roles predefinidos.
Instalar e inicializar el SDK de Vertex AI para Python
Desarrollar un agente
Primero, desarrolla una herramienta:
def get_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."""
import requests
response = requests.get(
f"https://api.frankfurter.app/{currency_date}",
params={"from": currency_from, "to": currency_to},
)
return response.json()
A continuación, crea una instancia de un agente:
ADK
from google.adk.agents import Agent
from vertexai import agent_engines
agent = Agent(
model="gemini-2.0-flash",
name='currency_exchange_agent',
tools=[get_exchange_rate],
)
app = agent_engines.AdkApp(agent=agent)
LangGraph
from vertexai import 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,
},
)
LangChain
from vertexai import 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,
},
)
AG2
from vertexai import agent_engines
agent = agent_engines.AG2Agent(
model="gemini-2.0-flash",
runnable_name="Get Exchange Rate Agent",
tools=[get_exchange_rate],
)
LlamaIndex
from vertexai.preview import reasoning_engines
def runnable_with_tools_builder(model, runnable_kwargs=None, **kwargs):
from llama_index.core.query_pipeline import QueryPipeline
from llama_index.core.tools import FunctionTool
from llama_index.core.agent import 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,
)
Por último, prueba el agente de forma local:
ADK
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)
donde USER_ID es un ID definido por el usuario con un límite de 128 caracteres.
LangGraph
agent.query(input={"messages": [
("user", "What is the exchange rate from US dollars to SEK today?"),
]})
LangChain
agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
AG2
agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
LlamaIndex
agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
Desplegar un agente
Para desplegar el agente, sigue estos pasos:
ADK
remote_agent = client.agent_engines.create(
agent=app,
config={
"requirements": ["google-cloud-aiplatform[agent_engines,adk]"],
}
)
LangGraph
remote_agent = client.agent_engines.create(
agent,
config={
"requirements": ["google-cloud-aiplatform[agent_engines,langchain]"],
},
)
LangChain
remote_agent = client.agent_engines.create(
agent,
config={
"requirements": ["google-cloud-aiplatform[agent_engines,langchain]"],
},
)
AG2
from vertexai import agent_engines
remote_agent = agent_engines.create(
agent,
config={
"requirements": ["google-cloud-aiplatform[agent_engines,ag2]"],
},
)
LlamaIndex
from vertexai import agent_engines
remote_agent = agent_engines.create(
agent,
config={
"requirements": ["google-cloud-aiplatform[agent_engines,llama_index]"],
},
)
De esta forma, se crea un recurso reasoningEngine
en Vertex AI.
Usar un agente
Prueba el agente implementado enviando una consulta:
ADK
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)
LangGraph
remote_agent.query(input={"messages": [
("user", "What is the exchange rate from US dollars to SEK today?"),
]})
LangChain
remote_agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
AG2
remote_agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
LlamaIndex
remote_agent.query(
input="What is the exchange rate from US dollars to SEK today?"
)
Limpieza
Para evitar que se apliquen cargos en tu cuenta de Google Cloud por los recursos utilizados en esta página, sigue estos pasos.
remote_agent.delete(force=True)