airflow.providers.google.cloud.operators.vertex_ai.agent_engine¶

This module contains Google Vertex AI Agent Engine operators.

Classes¶

`CreateAgentEngineOperator`	Create a Vertex AI Agent Engine.
`GetAgentEngineOperator`	Get a Vertex AI Agent Engine.
`RunReasoningEngineQueryOperator`	Query a Vertex AI Reasoning Engine synchronously.
`RunQueryJobOperator`	Run a query job on a Vertex AI Agent Engine.
`UpdateAgentEngineOperator`	Update a Vertex AI Agent Engine.
`DeleteAgentEngineOperator`	Delete a Vertex AI Agent Engine.

Module Contents¶

class airflow.providers.google.cloud.operators.vertex_ai.agent_engine.CreateAgentEngineOperator(*, project_id, location, agent=None, config=None, gcp_conn_id='google_cloud_default', impersonation_chain=None, **kwargs)[source]¶

Bases: airflow.providers.google.cloud.operators.cloud_base.GoogleCloudBaseOperator

Create a Vertex AI Agent Engine.

Parameters:

project_id (str) – Required. The ID of the Google Cloud project that the service belongs to.
location (str) – Required. The ID of the Google Cloud location that the service belongs to.
agent (Any | None) – Optional. The agent object to deploy.
config (vertexai._genai.types.AgentEngineConfigOrDict | None) – Optional. Configuration for the Agent Engine.
gcp_conn_id (str) – The connection ID to use connecting to Google Cloud.
impersonation_chain (str | collections.abc.Sequence[str] | None) – Optional service account to impersonate using short-term credentials.

template_fields = ('project_id', 'location', 'agent', 'config', 'gcp_conn_id', 'impersonation_chain')[source]¶

project_id[source]¶

location[source]¶

agent = None[source]¶

config = None[source]¶

gcp_conn_id = 'google_cloud_default'[source]¶

impersonation_chain = None[source]¶

property hook: airflow.providers.google.cloud.hooks.vertex_ai.agent_engine.AgentEngineHook[source]¶

execute(context)[source]¶

Derive when creating an operator.

The main method to execute the task. Context is the same dictionary used as when rendering jinja templates.

Refer to get_template_context for more context.

class airflow.providers.google.cloud.operators.vertex_ai.agent_engine.GetAgentEngineOperator(*, project_id, location, agent_engine_id, config=None, gcp_conn_id='google_cloud_default', impersonation_chain=None, **kwargs)[source]¶

Bases: airflow.providers.google.cloud.operators.cloud_base.GoogleCloudBaseOperator

Get a Vertex AI Agent Engine.

Parameters:

project_id (str) – Required. The ID of the Google Cloud project that the service belongs to.
location (str) – Required. The ID of the Google Cloud location that the service belongs to.
agent_engine_id (str) – Required. The Agent Engine ID.
config (vertexai._genai.types.GetAgentEngineConfigOrDict | None) – Optional. Configuration for getting the Agent Engine.
gcp_conn_id (str) – The connection ID to use connecting to Google Cloud.
impersonation_chain (str | collections.abc.Sequence[str] | None) – Optional service account to impersonate using short-term credentials.

template_fields = ('project_id', 'location', 'agent_engine_id', 'config', 'gcp_conn_id', 'impersonation_chain')[source]¶

project_id[source]¶

location[source]¶

agent_engine_id[source]¶

config = None[source]¶

gcp_conn_id = 'google_cloud_default'[source]¶

impersonation_chain = None[source]¶

property hook: airflow.providers.google.cloud.hooks.vertex_ai.agent_engine.AgentEngineHook[source]¶

execute(context)[source]¶

Derive when creating an operator.

The main method to execute the task. Context is the same dictionary used as when rendering jinja templates.

Refer to get_template_context for more context.

class airflow.providers.google.cloud.operators.vertex_ai.agent_engine.RunReasoningEngineQueryOperator(*, project_id, location, reasoning_engine_id, input_data=None, class_method='query', retry=None, timeout=None, metadata=(), gcp_conn_id='google_cloud_default', impersonation_chain=None, **kwargs)[source]¶

Bases: airflow.providers.google.cloud.operators.cloud_base.GoogleCloudBaseOperator

Query a Vertex AI Reasoning Engine synchronously.

Parameters:

project_id (str) – Required (templated). The ID of the Google Cloud project that the service belongs to.
location (str) – Required (templated). The ID of the Google Cloud location that the service belongs to.
reasoning_engine_id (str) – Required (templated). The Reasoning Engine resource ID.
input_data (dict[str, Any] | None) – Optional (templated). Input for the Reasoning Engine class method in JSON object format. Defaults to None.
class_method (str) – Optional (templated). The Reasoning Engine class method to invoke. Defaults to query.
retry (google.api_core.retry.Retry | None) – Designation of what errors, if any, should be retried. Defaults to None.
timeout (float | None) – The timeout for this request. Defaults to None.
metadata (collections.abc.Sequence[tuple[str, str]]) – Strings which should be sent along with the request as metadata. Defaults to an empty tuple.
gcp_conn_id (str) – The connection ID to use connecting to Google Cloud (templated). Defaults to google_cloud_default.
impersonation_chain (str | collections.abc.Sequence[str] | None) – Optional service account to impersonate using short-term credentials (templated). Defaults to None.

template_fields = ('project_id', 'location', 'reasoning_engine_id', 'input_data', 'class_method', 'gcp_conn_id',...[source]¶

project_id[source]¶

location[source]¶

reasoning_engine_id[source]¶

input_data = None[source]¶

class_method = 'query'[source]¶

retry = None[source]¶

timeout = None[source]¶

metadata = ()[source]¶

gcp_conn_id = 'google_cloud_default'[source]¶

impersonation_chain = None[source]¶

property hook: airflow.providers.google.cloud.hooks.vertex_ai.agent_engine.AgentEngineHook[source]¶

execute(context)[source]¶

Derive when creating an operator.

The main method to execute the task. Context is the same dictionary used as when rendering jinja templates.

Refer to get_template_context for more context.

class airflow.providers.google.cloud.operators.vertex_ai.agent_engine.RunQueryJobOperator(*, project_id, location, agent_engine_id, config=None, check_config=None, wait_for_completion=True, poll_interval=30, timeout=None, gcp_conn_id='google_cloud_default', impersonation_chain=None, deferrable=conf.getboolean('operators', 'default_deferrable', fallback=False), **kwargs)[source]¶

Bases: airflow.providers.google.cloud.operators.cloud_base.GoogleCloudBaseOperator

Run a query job on a Vertex AI Agent Engine.

Parameters:

project_id (str) – Required. The ID of the Google Cloud project that the service belongs to.
location (str) – Required. The ID of the Google Cloud location that the service belongs to.
agent_engine_id (str) – Required. The Agent Engine ID.
config (vertexai._genai.types.RunQueryJobAgentEngineConfigOrDict | None) – Optional. Configuration for the query job (query, output_gcs_uri).
check_config (vertexai._genai.types.CheckQueryJobAgentEngineConfigOrDict | None) – Optional. Configuration for checking the query job.
wait_for_completion (bool) – Whether to wait until the query job completes.
poll_interval (float) – Time, in seconds, to wait between checks.
timeout (float | None) – Optional timeout, in seconds.
gcp_conn_id (str) – The connection ID to use connecting to Google Cloud.
impersonation_chain (str | collections.abc.Sequence[str] | None) – Optional service account to impersonate using short-term credentials.
deferrable (bool) – Run operator in the deferrable mode.

template_fields = ('project_id', 'location', 'agent_engine_id', 'config', 'check_config', 'gcp_conn_id',...[source]¶

project_id[source]¶

location[source]¶

agent_engine_id[source]¶

config = None[source]¶

check_config = None[source]¶

wait_for_completion = True[source]¶

poll_interval = 30[source]¶

timeout = None[source]¶

gcp_conn_id = 'google_cloud_default'[source]¶

impersonation_chain = None[source]¶

deferrable[source]¶

property hook: airflow.providers.google.cloud.hooks.vertex_ai.agent_engine.AgentEngineHook[source]¶

execute(context)[source]¶

Derive when creating an operator.

The main method to execute the task. Context is the same dictionary used as when rendering jinja templates.

Refer to get_template_context for more context.

execute_complete(context, event=None)[source]¶

class airflow.providers.google.cloud.operators.vertex_ai.agent_engine.UpdateAgentEngineOperator(*, project_id, location, agent_engine_id, config, agent=None, gcp_conn_id='google_cloud_default', impersonation_chain=None, **kwargs)[source]¶

Bases: airflow.providers.google.cloud.operators.cloud_base.GoogleCloudBaseOperator

Update a Vertex AI Agent Engine.

Parameters:

project_id (str) – Required. The ID of the Google Cloud project that the service belongs to.
location (str) – Required. The ID of the Google Cloud location that the service belongs to.
agent_engine_id (str) – Required. The Agent Engine ID.
agent (Any | None) – Optional. The updated agent object to deploy.
config (vertexai._genai.types.AgentEngineConfigOrDict) – Required. Configuration for the Agent Engine update.
gcp_conn_id (str) – The connection ID to use connecting to Google Cloud.
impersonation_chain (str | collections.abc.Sequence[str] | None) – Optional service account to impersonate using short-term credentials.

template_fields = ('project_id', 'location', 'agent_engine_id', 'agent', 'config', 'gcp_conn_id', 'impersonation_chain')[source]¶

project_id[source]¶

location[source]¶

agent_engine_id[source]¶

agent = None[source]¶

config[source]¶

gcp_conn_id = 'google_cloud_default'[source]¶

impersonation_chain = None[source]¶

property hook: airflow.providers.google.cloud.hooks.vertex_ai.agent_engine.AgentEngineHook[source]¶

execute(context)[source]¶

Derive when creating an operator.

The main method to execute the task. Context is the same dictionary used as when rendering jinja templates.

Refer to get_template_context for more context.

class airflow.providers.google.cloud.operators.vertex_ai.agent_engine.DeleteAgentEngineOperator(*, project_id, location, agent_engine_id, force=None, config=None, wait_for_completion=True, poll_interval=30, timeout=None, gcp_conn_id='google_cloud_default', impersonation_chain=None, **kwargs)[source]¶

Bases: airflow.providers.google.cloud.operators.cloud_base.GoogleCloudBaseOperator

Delete a Vertex AI Agent Engine.

Parameters:

project_id (str) – Required. The ID of the Google Cloud project that the service belongs to.
location (str) – Required. The ID of the Google Cloud location that the service belongs to.
agent_engine_id (str) – Required. The Agent Engine ID.
force (bool | None) – Optional. Whether to delete child resources.
config (vertexai._genai.types.DeleteAgentEngineConfigOrDict | None) – Optional. Additional deletion configuration.
wait_for_completion (bool) – Whether to wait until the delete operation completes.
poll_interval (float) – Time, in seconds, to wait between checks.
timeout (float | None) – Optional timeout, in seconds.
gcp_conn_id (str) – The connection ID to use connecting to Google Cloud.
impersonation_chain (str | collections.abc.Sequence[str] | None) – Optional service account to impersonate using short-term credentials.

template_fields = ('project_id', 'location', 'agent_engine_id', 'force', 'config', 'gcp_conn_id', 'impersonation_chain')[source]¶

project_id[source]¶

location[source]¶

agent_engine_id[source]¶

force = None[source]¶

config = None[source]¶

wait_for_completion = True[source]¶

poll_interval = 30[source]¶

timeout = None[source]¶

gcp_conn_id = 'google_cloud_default'[source]¶

impersonation_chain = None[source]¶

property hook: airflow.providers.google.cloud.hooks.vertex_ai.agent_engine.AgentEngineHook[source]¶

execute(context)[source]¶

Derive when creating an operator.

The main method to execute the task. Context is the same dictionary used as when rendering jinja templates.

Refer to get_template_context for more context.