此页面由 Cloud Translation API 翻译。

使用 Agent Development Kit 代理

除了使用代理的一般说明之外，本页还介绍了特定于 AdkApp 的功能。

准备工作

本教程假定您已阅读并遵循以下说明：

开发智能体开发套件代理：将 agent 作为 AdkApp 的实例进行开发。
用户身份验证，以用户身份进行身份验证，以便查询代理。

如需查询 ADK 应用，您需要先创建新的 ADK 应用实例或获取现有实例。

如需获取与特定资源 ID 对应的 ADK 应用，请执行以下操作：

Python 版 Vertex AI SDK

运行以下代码：

from vertexai import agent_engines

adk_app = agent_engines.get(RESOURCE_ID)

或者，您也可以提供代理的完整资源名称：

adk_app = agent_engines.get("projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID")

Python requests 库

运行以下代码：

from google import auth as google_auth
from google.auth.transport import requests as google_requests
import requests

def get_identity_token():
    credentials, _ = google_auth.default()
    auth_request = google_requests.Request()
    credentials.refresh(auth_request)
    return credentials.token

response = requests.get(
f"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID",
    headers={
        "Content-Type": "application/json; charset=utf-8",
        "Authorization": f"Bearer {get_identity_token()}",
    },
)

REST API

curl \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID

支持的操作

AdkApp 支持以下操作：

stream_query：用于对查询的响应进行流式传输。
create_session：用于创建新会话。
list_sessions：用于列出可用的会话。
get_session：用于检索特定会话。
delete_session：用于删除特定会话。

如需列出所有受支持的操作，请使用以下命令：

Python 版 Vertex AI SDK

运行以下代码：

adk_app.operation_schemas()

Python requests 库

运行以下代码：

import json

json.loads(response.content).get("spec").get("classMethods")

REST API

在 curl 请求响应中以 spec.class_methods 表示。

管理会话

将智能体部署到 Vertex AI Agent Engine 后，AdkApp 会使用基于云的托管式会话。本部分介绍了如何使用受管理的会话。

创建会话

如需为用户创建会话，请执行以下操作：

Python 版 Vertex AI SDK

session = adk_app.create_session(user_id="USER_ID")

Python requests 库

运行以下代码：

from google import auth as google_auth
from google.auth.transport import requests as google_requests
import requests
import json

def get_identity_token():
  credentials, _ = google_auth.default()
  auth_request = google_requests.Request()
  credentials.refresh(auth_request)
  return credentials.token

response = requests.post(
  f"https://{adk_app.api_client.api_endpoint}/v1/{adk_app.resource_name}:query",
  headers={
    "Content-Type": "application/json; charset=utf-8",
    "Authorization": f"Bearer {get_identity_token()}",
  },
  data=json.dumps({
    "class_method": "create_session",
    "input": {"user_id": "USER_ID"},
  }),
)
print(response.content)

REST API

curl \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID:query -d '{"class_method": "create_session", "input": {"user_id": "USER_ID"},}'

其中 USER_ID 是用户定义的 ID，字符数限制为 128。

列出会话

如需列出用户的会话，请执行以下操作：

Python 版 Vertex AI SDK

adk_app.list_sessions(user_id="USER_ID")

请求

运行以下代码：

from google import auth as google_auth
from google.auth.transport import requests as google_requests
import requests
import json

def get_identity_token():
  credentials, _ = google_auth.default()
  auth_request = google_requests.Request()
  credentials.refresh(auth_request)
  return credentials.token

response = requests.post(
  f"https://{adk_app.api_client.api_endpoint}/v1/{adk_app.resource_name}:query",
  headers={
    "Content-Type": "application/json; charset=utf-8",
    "Authorization": f"Bearer {get_identity_token()}",
  },
  data=json.dumps({
    "class_method": "list_sessions",
    "input": {"user_id": "USER_ID"},
  }),
)
print(response.content)

REST

curl \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID:query -d '{"class_method": "list_sessions", "input": {"user_id": "USER_ID"},}'

其中 USER_ID 是用户定义的 ID，字符数限制为 128。

获取会话

如需获取特定会话，您需要同时提供用户 ID 和会话 ID：

Python 版 Vertex AI SDK

session = adk_app.get_session(user_id="USER_ID", session_id="SESSION_ID")

请求

运行以下代码：

from google import auth as google_auth
from google.auth.transport import requests as google_requests
import requests
import json

def get_identity_token():
  credentials, _ = google_auth.default()
  auth_request = google_requests.Request()
  credentials.refresh(auth_request)
  return credentials.token

response = requests.post(
  f"https://{adk_app.api_client.api_endpoint}/v1/{adk_app.resource_name}:query",
  headers={
    "Content-Type": "application/json; charset=utf-8",
    "Authorization": f"Bearer {get_identity_token()}",
  },
  data=json.dumps({
    "class_method": "get_session",
    "input": {"user_id": "USER_ID", "session_id": "SESSION_ID"},
  }),
)
print(response.content)

REST

curl \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID:query -d '{"class_method": "get_session", "input": {"user_id": "USER_ID", "session_id": "SESSION_ID"},}'

删除时段

如需删除会话，您需要同时提供用户 ID 和会话 ID：

Python 版 Vertex AI SDK

adk_app.delete_session(user_id="USER_ID", session_id="SESSION_ID")

请求

运行以下代码：

from google import auth as google_auth
from google.auth.transport import requests as google_requests
import requests
import json

def get_identity_token():
  credentials, _ = google_auth.default()
  auth_request = google_requests.Request()
  credentials.refresh(auth_request)
  return credentials.token

response = requests.post(
  f"https://{adk_app.api_client.api_endpoint}/v1/{adk_app.resource_name}:query",
  headers={
    "Content-Type": "application/json; charset=utf-8",
    "Authorization": f"Bearer {get_identity_token()}",
  },
  data=json.dumps({
    "class_method": "delete_session",
    "input": {"user_id": "USER_ID", "session_id": "SESSION_ID"},
  }),
)
print(response.content)

REST

curl \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID:query -d '{"class_method": "delete_session", "input": {"user_id": "USER_ID", "session_id": "SESSION_ID"},}'

对查询的响应进行流式传输

如需在会话中流式传输客服人员的回答，请执行以下操作：

Python 版 Vertex AI SDK

for event in adk_app.stream_query(
    user_id="USER_ID",
    session_id="SESSION_ID",  # Optional
    message="What is the exchange rate from US dollars to SEK today?",
):
  print(event)

请求

from google import auth as google_auth
from google.auth.transport import requests as google_requests
import requests

def get_identity_token():
    credentials, _ = google_auth.default()
    auth_request = google_requests.Request()
    credentials.refresh(auth_request)
    return credentials.token

requests.post(
    f"https://{adk_app.api_client.api_endpoint}/v1/{adk_app.resource_name}:streamQuery",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {get_identity_token()}",
    },
    data=json.dumps({
        "class_method": "stream_query",
        "input": {
            "user_id": "USER_ID",
            "session_id": "SESSION_ID",
            "message": "What is the exchange rate from US dollars to SEK today?",
        },
    }),
    stream=True,
)

REST

curl \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID:streamQuery?alt=sse -d '{
  "class_method": "stream_query",
  "input": {
    "user_id": "USER_ID",
    "session_id": "SESSION_ID",
    "message": "What is the exchange rate from US dollars to SEK today?",
  }
}'

使用 Agent Development Kit 代理 使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。

准备工作

Python 版 Vertex AI SDK

Python requests 库

REST API

支持的操作

Python 版 Vertex AI SDK

Python requests 库

REST API

管理会话

创建会话

Python 版 Vertex AI SDK

Python requests 库

REST API

列出会话

Python 版 Vertex AI SDK

请求

REST

获取会话

Python 版 Vertex AI SDK

请求

REST

删除时段

Python 版 Vertex AI SDK

请求

REST

对查询的响应进行流式传输

Python 版 Vertex AI SDK

请求

REST

后续步骤

使用 Agent Development Kit 代理