flytekitplugins.mmcloud.agent

Directory

Classes

flytekitplugins.mmcloud.agent.MMCloudAgent

This is the base class for all async agents. It defines the interface that all agents must implement. The agent service is responsible for invoking agents. The propeller will communicate with the agent service to create tasks, get the status of tasks, and delete tasks.

All the agents should be registered in the AgentRegistry. Agent Service will look up the agent based on the task type. Every task type can only have one agent.

def MMCloudAgent()

Methods

async_login()

def async_login()

Log in to Memory Machine Cloud OpCenter.

create()

def create(
    task_template: flytekit.models.task.TaskTemplate,
    inputs: typing.Optional[flytekit.models.literals.LiteralMap],
    kwargs,
) -> flytekitplugins.mmcloud.agent.MMCloudMetadata

Submit a Flyte task as MMCloud job to the OpCenter, and return the job UID for the task.

delete()

def delete(
    resource_meta: flytekitplugins.mmcloud.agent.MMCloudMetadata,
    kwargs,
)

Delete the task. This call should be idempotent.

get()

def get(
    resource_meta: flytekitplugins.mmcloud.agent.MMCloudMetadata,
    kwargs,
) -> flytekit.extend.backend.base_agent.Resource

Return the status of the task, and return the outputs on success.

Properties

flytekitplugins.mmcloud.agent.MMCloudMetadata

class MMCloudMetadata(
    job_id: str,
)

Methods

decode()

def decode(
    data: bytes,
) -> ResourceMeta

Decode the resource meta from bytes.

encode()

def encode()

Encode the resource meta to bytes.