class Model(wallaroo.object.Object):

Wraps a backend Model object.

Model( client: Optional[wallaroo.client.Client], data: Dict[str, Any], standalone=False)

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 as_standalone(name: str, version: str, file_name: str) -> wallaroo.model.Model:

Creates a Model intended for use in generating standalone configurations

def id(self) -> int:
def uid(self) -> str:
def name(*args, **kwargs):
def version(*args, **kwargs):
def sha(*args, **kwargs):
def file_name(*args, **kwargs):
def image_path(*args, **kwargs):
def last_update_time(*args, **kwargs):
def rehydrate_config(*args, **kwargs):
def config(self) -> wallaroo.model_config.ModelConfig:
def configure( self, runtime: Optional[str] = None, tensor_fields: List[str] = None, filter_threshold: float = None, input_schema: Optional[pyarrow.lib.Schema] = None, output_schema: Optional[pyarrow.lib.Schema] = None) -> wallaroo.model.Model:
def logs( self, limit: int = 100, valid: Optionalbool] = None) -> [wallaroo.logs.LogEntries:
def deploy( self, pipeline_name: str, deployment_config: Optional[wallaroo.deployment_config.DeploymentConfig] = None) -> wallaroo.pipeline.Pipeline:

Convenience function to quickly deploy a Model. It will configure the model, create a pipeline with a single model step, deploy it, and return the pipeline.

Typically, the configure() method is used to configure a model prior to deploying it. However, if a default configuration is sufficient, this function can be used to quickly deploy with said default configuration.

The filename this Model was generated from needs to have a recognizable file extension so that the runtime can be inferred. Currently, this is:

  • .onnx -> ONNX runtime
  • str deployment_name: Name of the deployment to create. Must be unique across all deployments. Deployment names must be ASCII alpha-numeric characters plus dash (-) only.