wallaroo.pipeline_variant

class PipelineVariant(wallaroo.object.Object):

Base class for all backend GraphQL API objects.

This class serves as a framework for API objects to be constructed based on a partially-complete JSON response, and to fill in their remaining members dynamically if needed.

PipelineVariant(client: Optional[wallaroo.client.Client], data: Dict[str, Any])

Base constructor.

Each object requires:

  • a GraphQL client - in order to fill its missing members dynamically
  • an initial data blob - typically from unserialized JSON, contains at
  • least the data for required members (typically the object's primary key) and optionally other data members.
def id(self) -> int:
def create_time(*args, **kwargs):
def last_update_time(*args, **kwargs):
def name(*args, **kwargs):
def definition(*args, **kwargs):
def pipeline(*args, **kwargs):
def deployments(*args, **kwargs):
def model_configs(*args, **kwargs):
def deploy( self, deployment_name: str, model_configs: List[wallaroo.model_config.ModelConfig], config: Optional[wallaroo.deployment_config.DeploymentConfig] = None) -> wallaroo.deployment.Deployment:

Deploys this PipelineVariant.

Parameters
  • str deployment_name: Name of the new Deployment. Must be unique across all deployments.
  • List[ModelConfig] model_configs: List of the configured models to use. These must be the same ModelConfigs used when creating the Pipeline.
  • Optional[DeploymentConfig] config: Deployment configuration to use.
Returns

A Deployment object for the resulting deployment.

class PipelineVariants(typing.List[wallaroo.pipeline_variant.PipelineVariant]):

Wraps a list of pipelines for display in a display-aware environment like Jupyter.

Inherited Members
builtins.list
list
clear
copy
append
insert
extend
pop
remove
index
count
reverse
sort