wallaroo.model_version

class ModelVersion(wallaroo.object.Object):

The Wallaroo ModelVersion object. Each ModelVersion is a specific version of a Model.

ModelVersion(client: 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.
client
def id(self) -> int:
def uid(self) -> str:
def name(*args, **kwargs):
def version(*args, **kwargs):
def models_pk_id(*args, **kwargs):
def sha(*args, **kwargs):
def status(*args, **kwargs):
def error_summary(*args, **kwargs):
def file_name(*args, **kwargs):
def image_path(*args, **kwargs):
def arch(*args, **kwargs):
def accel(*args, **kwargs):
def last_update_time(*args, **kwargs):
def tags(*args, **kwargs):
def workspace(*args, **kwargs):
def rehydrate_config(*args, **kwargs):
def configure( self, runtime: Optional[str] = None, tensor_fields: Optional[List[str]] = None, filter_threshold: Optional[float] = None, input_schema: Optional[pyarrow.lib.Schema] = None, output_schema: Optional[pyarrow.lib.Schema] = None, batch_config: Optional[str] = None, dynamic_batching_config: Optional[wallaroo.dynamic_batching_config.DynamicBatchingConfig] = None, continuous_batching_config: Optional[wallaroo.continuous_batching_config.ContinuousBatchingConfig] = None, openai_config: Optional[wallaroo.openai_config.OpenaiConfig] = None) -> ModelVersion:
def get_upload_logs( self, limit: Optional[int] = None) -> ModelUploadLogs:

Returns the user visible logs for the given model_upload() call for a custom python model. These will be messages related to parse and "pip install" of requirements.txt or to static validation of the model code.

Note: The default retention policy for model upload logs is 30 days.

Parameters
  • limit int Limits the number of lines of logs returned. Starts from the most recent logs.
Returns

ModelUploadLogs object.

def logs( self, limit: int = 100, valid: Optional[bool] = None, arrow: Optional[bool] = False) -> Tuple[Any, Optional[str]]:
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
Parameters
  • 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.
class ModelVersionList(typing.List[wallaroo.model_version.ModelVersion]):

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

class ModelUploadLogs(typing.List[str]):

This is a list of log messages associated with a model_upload() call.