In addition to the general instructions for using an agent,
this page describes features that are specific to AdkApp
.
Before you begin
This tutorial assumes that you have read and followed the instructions in:
- Develop an Agent Development Kit agent: to develop
agent
as an instance ofAdkApp
. - User authentication to authenticate as a user for querying the agent.
To query an ADK application, you need to first create a new ADK application instance or get an existing instance.
To get the ADK application corresponding to a specific resource ID:
Vertex AI SDK for Python
Run the following code:
from vertexai import agent_engines
adk_app = agent_engines.get(RESOURCE_ID)
Alternatively, you can provide the full resource name of the agent:
adk_app = agent_engines.get("projects/PROJECT_ID/locations/LOCATION/reasoningEngines/RESOURCE_ID")
Python requests library
Run the following code:
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
Supported operations
The following operations are supported for AdkApp
:
stream_query
: for streaming a response to a query.create_session
: for creating a new session.list_sessions
: for listing the sessions available.get_session
: for retrieving a specific session.delete_session
: for deleting a specific session.
To list all supported operations:
Vertex AI SDK for Python
Run the following code:
adk_app.operation_schemas()
Python requests library
Run the following code:
import json
json.loads(response.content).get("spec").get("classMethods")
REST API
Represented in spec.class_methods
from the response to the curl request.
Manage sessions
AdkApp
uses cloud-based managed sessions after you deploy the agent to Vertex AI Agent Engine. This section describes how to use managed sessions.
Create a session
To create a session for a user:
Vertex AI SDK for Python
session = adk_app.create_session(user_id="USER_ID")
Python requests library
Run the following code:
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"},}'
where USER_ID is a user-defined ID with a character limit of 128.
List sessions
To list the sessions for a user:
Vertex AI SDK for Python
adk_app.list_sessions(user_id="USER_ID")
requests
Run the following code:
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"},}'
where USER_ID is a user-defined ID with a character limit of 128.
Get a session
To get a specific session, you need both the user ID and the session ID:
Vertex AI SDK for Python
session = adk_app.get_session(user_id="USER_ID", session_id="SESSION_ID")
requests
Run the following code:
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"},}'
Delete a session
To delete a session, you need both the user ID and the session ID:
Vertex AI SDK for Python
adk_app.delete_session(user_id="USER_ID", session_id="SESSION_ID")
requests
Run the following code:
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"},}'
Stream a response to a query
To stream responses from an agent in a session:
Vertex AI SDK for 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)
requests
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?",
}
}'