Menggunakan agen Agent Development Kit

Selain petunjuk umum untuk menggunakan agen, halaman ini menjelaskan fitur yang khusus untuk AdkApp.

Sebelum memulai

Tutorial ini mengasumsikan bahwa Anda telah membaca dan mengikuti petunjuk di:

Untuk membuat kueri aplikasi ADK, Anda harus membuat instance aplikasi ADK baru atau mendapatkan instance yang ada terlebih dahulu.

Untuk mendapatkan aplikasi ADK yang sesuai dengan ID resource tertentu:

Vertex AI SDK untuk Python

Jalankan kode berikut:

from vertexai import agent_engines

adk_app = agent_engines.get(RESOURCE_ID)

Atau, Anda dapat memberikan nama resource lengkap agen:

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

Library permintaan Python

Jalankan kode berikut:

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

Operasi yang didukung

Operasi berikut didukung untuk AdkApp:

Untuk mencantumkan semua operasi yang didukung:

Vertex AI SDK untuk Python

Jalankan kode berikut:

adk_app.operation_schemas()

Library permintaan Python

Jalankan kode berikut:

import json

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

REST API

Diwakili dalam spec.class_methods dari respons terhadap permintaan curl.

Mengelola sesi

AdkApp menggunakan sesi terkelola berbasis cloud setelah Anda men-deploy agen ke Vertex AI Agent Engine. Bagian ini menjelaskan cara menggunakan sesi terkelola.

Membuat sesi

Untuk membuat sesi bagi pengguna:

Vertex AI SDK untuk Python 

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

Library permintaan Python

Jalankan kode berikut:

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"},}'

dengan USER_ID adalah ID yang ditentukan pengguna dengan batas karakter 128.

Mencantumkan sesi

Untuk mencantumkan sesi bagi pengguna:

Vertex AI SDK untuk Python 

adk_app.list_sessions(user_id="USER_ID")

permintaan

Jalankan kode berikut:

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"},}'

dengan USER_ID adalah ID yang ditentukan pengguna dengan batas karakter 128.

Mendapatkan sesi

Untuk mendapatkan sesi tertentu, Anda memerlukan ID pengguna dan ID sesi:

Vertex AI SDK untuk Python 

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

permintaan

Jalankan kode berikut:

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"},}'

Menghapus sesi

Untuk menghapus sesi, Anda memerlukan ID pengguna dan ID sesi:

Vertex AI SDK untuk Python 

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

permintaan

Jalankan kode berikut:

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"},}'

Menstreaming respons ke kueri

Untuk melakukan streaming respons dari agen dalam sesi:

Vertex AI SDK untuk Python 

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)

permintaan 

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?",
  }
}'

Langkah berikutnya