1. 简介
概览
此 Codelab 演示了如何使用智能体开发套件 (ADK) 构建可扩缩的异步智能体系统。您将创建一个 Cloud Run 工作器池，用于托管 ADK 快速入门天气代理，该代理会处理来自 PubSub 拉取订阅的任务。
学习内容
- 如何使用智能体开发套件 (ADK) 创建单轮对话智能体。
- 如何部署从 PubSub 订阅中拉取数据的工作器池。
2. 准备工作
启用 API
在开始使用此 Codelab 之前，请运行以下命令来启用以下 API：
gcloud services enable \
run.googleapis.com \
cloudbuild.googleapis.com \
artifactregistry.googleapis.com \
pubsub.googleapis.com \
aiplatform.googleapis.com
3. 设置和要求
如需设置所需资源，请按以下步骤操作：
- 为此 Codelab 设置环境变量：
export PROJECT_ID=<YOUR_PROJECT_ID>
export REGION=europe-west1
# AR repo
export AR_REPO="codelab-agent-wp"
# Application Names
export WORKER_APP_NAME="multi-tool-agent-worker"
# Pub/Sub Resources
export MY_TOPIC="pull-pubsub-topic-agent"
export MY_SUBSCRIPTION="agent-wp-sub"
# Service Accounts
export WORKER_SA_NAME="agent-worker-sa"
export WORKER_SA_ADDRESS="${WORKER_SA_NAME}@${PROJECT_ID}.iam.gserviceaccount.com"
Create Service Accounts
出于安全考虑，我们将为工作器创建一个专用服务账号，以确保它仅具有所需的权限。
为工作器创建服务账号：
gcloud iam service-accounts create ${WORKER_SA_NAME} \
--display-name="Service Account for ADK Agent Worker"
向服务账号授予必要的角色。它需要从 Pub/Sub 中提取消息，并调用 ADK 使用的 Vertex AI 模型。
# Role for subscribing to Pub/Sub
gcloud projects add-iam-policy-binding ${PROJECT_ID} \
--member="serviceAccount:${WORKER_SA_ADDRESS}" \
--role="roles/pubsub.admin"
# Role for invoking Vertex AI
gcloud projects add-iam-policy-binding ${PROJECT_ID} \
--member="serviceAccount:${WORKER_SA_ADDRESS}" \
--role="roles/aiplatform.user"
创建 Pub/Sub 资源
创建将充当任务队列的 Pub/Sub 主题。
gcloud pubsub topics create $MY_TOPIC
为工作器创建一个 Pub/Sub 订阅，以便从中拉取消息。
gcloud pubsub subscriptions create $MY_SUBSCRIPTION --topic=$MY_TOPIC
4. 创建 Cloud Run 工作器池
为您的项目创建一个名为 agents-wp 的目录。
mkdir agents-wp && cd agents-wp
创建 Dockerfile
touch Dockerfile
并将以下内容添加到您的 Dockerfile 中
FROM python:3.11-slim
WORKDIR /app
# Create a non-root user
RUN adduser --disabled-password --gecos "" myuser
# Switch to the non-root user
USER myuser
# Set up environment variables
ENV PATH="/home/myuser/.local/bin:$PATH"
# Copy agent files
COPY --chown=myuser:myuser multi_tool_agent/ /app/multi_tool_agent/
# Install dependencies from requirements.txt
RUN pip install -r /app/multi_tool_agent/requirements.txt
# Set the entrypoint to run the agent as a worker
CMD ["python3", "/app/multi_tool_agent/main.py"]
在其中创建一个名为 multi_tool_agent 的子目录。请注意文件夹名称 multi_tool_agent 中的下划线。此文件夹必须与您稍后将部署的 ADK 代理的名称一致。
mkdir multi_tool_agent && cd multi_tool_agent
创建 __init__.py 文件
touch __init__.py
并将以下内容添加到 __init__.py 文件中
from . import agent
创建 agent.py 文件
touch agent.py
并将以下内容添加到 agent.py 文件中
import datetime
from zoneinfo import ZoneInfo
from google.adk.agents.llm_agent 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.
"""
print(f"--- Entering get_weather function for city: {city} ---")
if city.lower() == "new york":
result = {
"status": "success",
"report": (
"The weather in New York is sunny with a temperature of 25 degrees"
" Celsius (77 degrees Fahrenheit)."
),
}
else:
result = {
"status": "error",
"error_message": f"Weather information for '{city}' is not available.",
}
print(f"--- Exiting get_weather function with result: {result} ---")
return result
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.
"""
print(f"--- Entering get_current_time function for city: {city} ---")
if city.lower() == "new york":
tz_identifier = "America/New_York"
else:
result = {
"status": "error",
"error_message": (
f"Sorry, I don't have timezone information for {city}."
),
}
print(f"--- Exiting get_current_time function with result: {result} ---")
return result
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")}'
)
result = {"status": "success", "report": report}
print(f"--- Exiting get_current_time function with result: {result} ---")
return result
print("--- Creating root_agent ---")
root_agent = Agent(
name="weather_time_agent",
model="gemini-2.5-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],
)
print("--- root_agent created ---")
创建 main.py 文件
touch main.py
并将以下内容添加到 main.py 文件中
import asyncio
import os
from google.adk.runners import InMemoryRunner, Runner
from google.genai import types
from google.cloud import pubsub_v1
from agent import root_agent
# --- Runner-based Invocation with Proper Async Handling ---
APP_NAME = "multi_tool_agent_worker"
USER_ID = "pubsub_user"
async def process_message(runner: Runner, message_data: bytes):
"""Processes a single message using the agent runner."""
print(f"Processing message: {message_data}")
try:
prompt = message_data.decode("utf-8")
session = await runner.session_service.create_session(
app_name=APP_NAME,
user_id=USER_ID
)
final_response_text = ""
async for event in runner.run_async(
user_id=USER_ID,
session_id=session.id,
new_message=types.Content(
role="user", parts=[types.Part.from_text(text=prompt)]
),
):
if event.content and event.content.parts:
if event.author != "user":
# Filter out thought parts to get only the final response text
final_response_text += "".join(
part.text or "" for part in event.content.parts if not part.thought
)
print(f"Agent response: {final_response_text}")
except Exception as e:
print(f"Error processing message: {e}")
async def async_worker(queue: asyncio.Queue, runner: Runner):
"""Continuously gets messages from the queue and processes them."""
while True:
message = await queue.get()
if message is None: # Sentinel for stopping
break
await process_message(runner, message.data)
message.ack()
queue.task_done()
async def main():
"""Sets up the Pub/Sub subscriber and the async worker."""
project_id = os.environ.get("GOOGLE_CLOUD_PROJECT")
subscription_id = os.environ.get("SUBSCRIPTION_ID")
if not project_id or not subscription_id:
print("GOOGLE_CLOUD_PROJECT and SUBSCRIPTION_ID environment variables must be set.")
return
runner = InMemoryRunner(agent=root_agent, app_name=APP_NAME)
message_queue = asyncio.Queue()
subscriber = pubsub_v1.SubscriberClient()
subscription_path = subscriber.subscription_path(project_id, subscription_id)
loop = asyncio.get_running_loop()
callback = lambda message: loop.call_soon_threadsafe(
message_queue.put_nowait, message
)
print(f"Listening for messages on {subscription_path}...\n")
streaming_pull_future = subscriber.subscribe(subscription_path, callback=callback)
worker_task = asyncio.create_task(async_worker(message_queue, runner))
try:
# This will block until the subscription is cancelled or an error occurs.
await loop.run_in_executor(None, streaming_pull_future.result)
except KeyboardInterrupt:
print("Shutting down...")
finally:
streaming_pull_future.cancel()
await message_queue.put(None) # Stop the worker
await worker_task # Wait for the worker to finish
await runner.close()
subscriber.close()
if __name__ == "__main__":
try:
asyncio.run(main())
except KeyboardInterrupt:
print("Exiting.")
创建 requirements.txt 文件
touch requirements.txt
并将以下内容添加到 requirements.txt 文件中
google-adk
google-cloud-pubsub
google-cloud-aiplatform
您应该会看到如下所示的文件夹结构
agents-wp
- multi_tool_agent
- __init__.py
- agent.py
- main.py
- requirements.txt
- Dockerfile
5. 构建和部署
创建 Artifact Registry 制品库
您需要一个位置来存储容器映像。
gcloud artifacts repositories create codelab-agent-wp \
--repository-format=docker \
--location=${REGION} \
--description="Repo for Cloud Run source deployments"
构建容器映像
导航到根 agents-wp 目录（您的 Dockerfile 位于该目录下）
cd ..
并运行以下 build 命令。
gcloud builds submit . --tag \
${REGION}-docker.pkg.dev/${PROJECT_ID}/${AR_REPO}/${WORKER_APP_NAME}:latest
部署到 Cloud Run
部署代理工作器映像。
gcloud beta run worker-pools deploy ${WORKER_APP_NAME} \
--image=${REGION}-docker.pkg.dev/${PROJECT_ID}/${AR_REPO}/${WORKER_APP_NAME}:latest \
--service-account=${WORKER_SA_ADDRESS} \
--region=${REGION} \
--set-env-vars="SUBSCRIPTION_ID=${MY_SUBSCRIPTION}" \
--set-env-vars="PYTHONUNBUFFERED=1" \
--set-env-vars="GOOGLE_GENAI_USE_VERTEXAI=1" \
--set-env-vars="GOOGLE_CLOUD_PROJECT=${PROJECT_ID}" \
--set-env-vars="GOOGLE_CLOUD_LOCATION=${REGION}"
6. 测试代理
您可以直接向 Pub/Sub 主题发布消息来测试工作器。
gcloud pubsub topics publish ${MY_TOPIC} --message="What is the weather in New York?"
您可以运行此命令，在 Google Cloud 控制台中查看多工具代理工作器服务的日志。
gcloud logging read 'resource.type="cloud_run_worker_pool" AND resource.labels.worker_pool_name="'$WORKER_APP_NAME'" AND resource.labels.location="'$REGION'"' --limit 10 --format="value(textPayload)"
您应该会看到输出，表明消息已收到并已处理，然后是代理的回答。
Agent response: The weather in New York is sunny with a temperature of 25 degrees Celsius (77 degrees Fahrenheit).
7. 恭喜！
恭喜您完成此 Codelab！
建议您查看有关工作器池和宿主代理的 Cloud Run 文档。
所学内容
- 如何使用智能体开发套件 (ADK) 创建单轮对话智能体。
- 如何部署从 PubSub 订阅中拉取数据的工作器池。
8. 清理
为避免产生任何费用，请删除您创建的资源。
删除 Cloud Run 工作器池
gcloud beta run worker-pools delete ${WORKER_APP_NAME} --region=${REGION}
删除 Pub/Sub 资源
gcloud pubsub subscriptions delete ${MY_SUBSCRIPTION}
gcloud pubsub topics delete ${MY_TOPIC}
删除 Artifact Registry 制品库
gcloud artifacts repositories delete ${AR_REPO} --location=$REGION
删除服务账号
gcloud iam service-accounts delete ${WORKER_SA_ADDRESS}
如需删除整个项目，请前往管理资源，选择您在第 2 步中创建的项目，然后选择“删除”。如果您删除项目，则需要在 Cloud SDK 中更改项目。您可以运行 gcloud projects list 查看所有可用项目的列表。