Esta página foi traduzida pela API Cloud Translation.

Desenvolva e implemente agentes no Vertex AI Agent Engine

Esta página demonstra como criar e implementar um agente que devolve a taxa de câmbio entre duas moedas numa data especificada, usando as seguintes estruturas de agentes:

Agent Development Kit (ADK)
LangGraph
LangChain
AG2
Pipeline de consultas do LlamaIndex (pré-visualização)

Antes de começar

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 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

Para receber as autorizações de que precisa para usar o Vertex AI Agent Engine, peça ao seu administrador que lhe conceda as seguintes funções de IAM no seu projeto:

Utilizador do Vertex AI (roles/aiplatform.user)
Administrador de armazenamento (roles/storage.admin)

Para mais informações sobre a atribuição de funções, consulte o artigo Faça a gestão do acesso a projetos, pastas e organizações.

Também pode conseguir as autorizações necessárias através de funções personalizadas ou outras funções predefinidas.

Instale e inicialize o SDK Vertex AI para Python

Execute o seguinte comando para instalar o SDK Vertex AI para Python e outros pacotes necessários:
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

Pré-visualização

Esta funcionalidade está sujeita aos "Termos das Ofertas de Pré-DG" na secção Termos Gerais de Serviço dos Termos Específicos do Serviço. As funcionalidades de pré-DG estão disponíveis "tal como estão" e podem ter apoio técnico limitado. Para mais informações, consulte as descrições das fases de lançamento.
```
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,llama_index]>=1.112
```
Autentique-se como utilizador
Colab
Execute o seguinte código:
```
from google.colab import auth

auth.authenticate_user(project_id="PROJECT_ID")
```
Cloud Shell
Não é necessária nenhuma ação.
Shell local
Execute o seguinte comando:
```
gcloud auth application-default login
```

Execute o seguinte código para importar o Vertex AI Agent Engine e inicializar o SDK:

import vertexai

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

Onde:

PROJECT_ID é o Google Cloud ID do projeto no qual desenvolve e implementa agentes
LOCATION é uma das regiões suportadas.

Desenvolva um agente

Primeiro, desenvolva uma ferramenta:

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()

Em seguida, instancie um 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 fim, teste o agente localmente:

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)

onde USER_ID é um ID definido pelo utilizador com um limite de 128 carateres.

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?"
)

Implemente um agente

Para implementar o agente:

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]"],
    },
)

Esta ação cria um recurso reasoningEngine no Vertex AI.

Use um agente

Teste o agente implementado enviando uma 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?"
)

Limpar

Para evitar incorrer em cobranças na sua Google Cloud conta pelos recursos usados nesta página, siga estes passos.

remote_agent.delete(force=True)

Desenvolva e implemente agentes no Vertex AI Agent Engine

Antes de começar

Instale e inicialize o SDK Vertex AI para Python

ADK

LangGraph

LangChain

AG2

LlamaIndex

Colab

Cloud Shell

Shell local

Desenvolva um agente

ADK

LangGraph

LangChain

AG2

LlamaIndex

ADK

LangGraph

LangChain

AG2

LlamaIndex

Implemente um agente

ADK

LangGraph

LangChain

AG2

LlamaIndex

Use um agente

ADK

LangGraph

LangChain

AG2

LlamaIndex

Limpar

O que se segue?