flytekitplugins.openai.BatchEndpointAgent

class flytekitplugins.openai.BatchEndpointAgent[source]

Methods

async create(task_template, inputs=None, **kwargs)[source]

Return a resource meta that can be used to get the status of the task.

Parameters:
  • task_template (TaskTemplate)

  • inputs (LiteralMap | None)

Return type:

BatchEndpointMetadata

async delete(resource_meta, **kwargs)[source]

Delete the task. This call should be idempotent. It should raise an error if fails to delete the task.

Parameters:

resource_meta (BatchEndpointMetadata)

async get(resource_meta, **kwargs)[source]

Return the status of the task, and return the outputs in some cases. For example, bigquery job can’t write the structured dataset to the output location, so it returns the output literals to the propeller, and the propeller will write the structured dataset to the blob store.

Parameters:

resource_meta (BatchEndpointMetadata)

Return type:

Resource

Attributes

metadata_type
name = 'OpenAI Batch Endpoint Agent'
task_category

task category that the agent supports