airflow.providers.common.ai.example_dags.example_agent¶
Example DAGs demonstrating AgentOperator, @task.agent, and toolsets.
Attributes¶
Classes¶
Structured analysis output for the agent example. |
Functions¶
AgentOperator with HITL review — a human approves output via hitl-review plugin UI. |
|
Resume a conversation across runs via |
Module Contents¶
- class airflow.providers.common.ai.example_dags.example_agent.Analysis(/, **data)[source]¶
Bases:
pydantic.BaseModelStructured analysis output for the agent example.
- airflow.providers.common.ai.example_dags.example_agent.example_agent_operator_hitl_review()[source]¶
AgentOperator with HITL review — a human approves output via hitl-review plugin UI.
- airflow.providers.common.ai.example_dags.example_agent.example_agent_session()[source]¶
Resume a conversation across runs via
message_history.The agent step seeds itself with the prior transcript and re-emits the updated transcript to XCom (key
message_history). Loading and storing that transcript under a session key is the DAG’s job – here, a JSON file in object storage keyed bysession_id. Swap the path fors3:///gs://in a deployment.