Annex 2. AI Agent Code
#######################

In the *AI Agents for OSM* functionality, AI Agents are built using the same approach as the configuration file used to run them. There is an orchestrator and a set of interfaces that implement each section of the configuration file.

.. code-block:: yaml

    config:
      executions:
        - active: True
          model:
            endpoint: "http://192.168.137.46:8501/v1/models/CPU-forecast-model:predict"
          monitoring:
            endpoint: "http://192.168.137.34:4000"
          threshold:
            function_name: evaluator
            logic: "evaluator = lambda x: True if x['predictions'][0][0] >= 0.8 else False"

AI Agent Orchestrator
*********************

.. autoclass:: aiagent.agent.AIAgent
    :members:


Interfaces
*************


Model Interface
--------------------


.. autoclass:: aiagent.interfaces.model_interface.ModelInterface
    :members:


Monitoring Interface
---------------------


.. autoclass:: aiagent.interfaces.monitoring_interface.MonitoringInterface
    :members:


Threshold Interface
--------------------


.. autoclass:: aiagent.interfaces.threshold_interface.ThresholdInterface
    :members: