在 Agent Runtime 開發及部署代理

Agent Runtime 可讓您代管使用各種架構開發的代理。本文說明如何使用 LangGraph、LangChain、AG2 或 LlamaIndex 建立、部署及測試代理程式。

本快速入門導覽課程會逐步引導您完成下列步驟：

設定您的 Google Cloud 專案。
安裝 Python 專用的 Agent Platform SDK 和所選架構。
開發貨幣兌換代理程式。
將代理部署至 Agent Runtime。
測試已部署的代理。

如要瞭解如何使用 Agent Development Kit (ADK) 快速入門，請參閱「使用 Agent Development Kit 在 Agent Platform 上開發及部署代理」。

事前準備

登入 Google Cloud 帳戶。如果您是 Google Cloud新手，歡迎建立帳戶，親自評估產品在實際工作環境中的成效。新客戶還能獲得價值 $300 美元的免費抵免額，可用於執行、測試及部署工作負載。

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.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Agent Platform 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 role (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 Agent Platform 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

如要取得使用 Agent Runtime 所需的權限，請要求管理員在專案中授予您下列 IAM 角色：

Agent Platform User (roles/aiplatform.user)
儲存空間管理員 (roles/storage.admin)

如要進一步瞭解如何授予角色，請參閱「管理專案、資料夾和組織的存取權」。

您或許也能透過自訂角色或其他預先定義的角色，取得必要權限。

安裝並初始化 Python 專用的 Agent Platform SDK

執行下列指令，安裝 Agent Platform SDK for Python 和其他必要套件：
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

預覽

這項功能適用《服務專屬條款》中「一般服務條款」一節的《正式發布前產品條款》。正式發布前功能是依「原樣」提供，支援服務可能受限。詳情請參閱推出階段說明。
```
pip install --upgrade --quiet google-cloud-aiplatform[agent_engines,llama_index]>=1.112
```
以使用者身分進行驗證
Colab
請執行下列程式碼：
```
from google.colab import auth

auth.authenticate_user(project_id="PROJECT_ID")
```
Cloud Shell
您無需採取任何動作。
本機殼層
執行下列指令：
```
gcloud auth application-default login
```
執行下列程式碼，匯入 Agent Platform 並初始化 SDK：
1. (選用) 測試您開發的代理程式前，請先匯入 Agent Platform 並初始化 SDK，如下所示：
  Google Cloud 專案
  import vertexai vertexai.init( project="PROJECT_ID", # Your project ID. location="LOCATION", # Your cloud region. )
  其中：
  - PROJECT_ID 是您 Google Cloud 開發及部署代理程式時所用的專案 ID
  - LOCATION 是支援的區域之一。
2. 部署代理程式前，您需要匯入 Agent Platform 並初始化 SDK，如下所示：
  Google Cloud 專案
  import vertexai client = vertexai.Client( project="PROJECT_ID", # Your project ID. location="LOCATION", # Your cloud region. )
  其中：
  - PROJECT_ID 是您 Google Cloud 開發及部署代理程式時所用的專案 ID
  - LOCATION 是支援的區域之一。

開發代理

為代理開發貨幣匯率工具：

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()

例項化代理程式：

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,
)

在本機測試代理：

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?"
)

部署代理程式

在 Agent Platform 中建立 reasoningEngine 資源，即可部署代理程式：

LangGraph

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

LangChain

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

AG2

remote_agent = client.agent_engines.create(
    agent,
    config={
        "requirements": ["google-cloud-aiplatform[agent_engines,ag2]"],
        "identity_type": types.IdentityType.AGENT_IDENTITY,
    },
)

LlamaIndex

remote_agent = client.agent_engines.create(
    agent,
    config={
        "requirements": ["google-cloud-aiplatform[agent_engines,llama_index]"],
        "identity_type": types.IdentityType.AGENT_IDENTITY,
    },
)

使用代理

傳送查詢內容，測試已部署的代理：

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?"
)

清除所用資源

為了避免系統向您的 Google Cloud 帳戶收取本頁面所用資源的費用，請按照下列步驟操作。

remote_agent.delete(force=True)

後續步驟

指南

在 Agent Runtime 開發及部署代理

事前準備

安裝並初始化 Python 專用的 Agent Platform SDK

LangGraph

LangChain

AG2

LlamaIndex

Colab

Cloud Shell

本機殼層

Google Cloud 專案

Google Cloud 專案

開發代理

LangGraph

LangChain

AG2

LlamaIndex

LangGraph

LangChain

AG2

LlamaIndex

部署代理程式

LangGraph

LangChain

AG2

LlamaIndex

使用代理

LangGraph

LangChain

AG2

LlamaIndex

清除所用資源

後續步驟

Agent Platform Runtime 設定

部署代理程式

管理已部署的代理程式

使用代理

取得支援