otcextensions.sdk.modelartsv1.v1.model

The AS Configuration Class

The Config class inherits from Resource.

class otcextensions.sdk.modelartsv1.v1.model.Model(_synchronized=False, connection=None, **attrs)

The base resource

Parameters:
  • _synchronized (bool) – This is not intended to be used directly. See new() and existing().

  • connection (openstack.connection.Connection) – Reference to the Connection being used. Defaults to None to allow Resource objects to be used without an active Connection, such as in unit tests. Use of self._connection in Resource code should protect itself with a check for None.

base_path: str = '/models'

The base part of the URI for this resource.

resources_key: ty.Optional[str] = 'models'

Plural form of key for resource.

allow_create = True

Allow create operation for this resource.

allow_list = True

Allow list operation for this resource.

allow_delete = True

Allow delete operation for this resource.

allow_fetch = True

Allow get operation for this resource.

ai_project

AI project.

apis

All input and output apis parameter information of a model, which is obtained from the model preview.

config

Model configurations.

created_at

Time when a model is created, in milliseconds calculated from 1970.

dependencies

Package required for inference code and model.

description

Model description.

execution_code

OBS path for storing the execution code. The name of the execution code file is fixed to customize_service.py.

health

Model health check interface information.

initial_config

Character string converted from the final model configuration file.

image_address

image path generated after model packaging.

input_params

Collection of input parameters of a model.

install_type

Supported service type for deployment.

is_publishable

Whether a model can be published to the marketplace.

is_subscribed

Whether a model is subscribed from the marketplace.

is_tunable

Whether a model can be tuned.

labels_map

Model label map.

model_algorithm

Model algorithm type. The value can be predict_analysis, object_detection, or image_classification.

model_docs

List of model description documents.

model_id

Model ID.

model_labels

Model label array.

model_metrics

Model precision, which is read from the configuration file.

model_name

Model name.

model_size

Model size, in bytes.

model_source

Model source.

model_status

Model status.

model_type

Model type. The value can be TensorFlow, MXNet, Spark_MLlib, Scikit_Learn, XGBoost, Image, or PyTorch.

model_version

Model version.

name: ty.Union[Body, URI]

Model name.

output_params

Collection of output parameters of a model.

owner_id

User to which a model belongs.

project_id

Project to which a model belongs.

runtime

Model runtime environment.

schema_doc

Download address of the model schema file.

source_job_id

ID of the source training job.

source_job_version

Version of the source training job.

source_location

OBS path where the model is located or the SWR image location.

source_type

Model source type. If a model is deployed through ExeML, the value is auto. If a model is deployed through a training job or an OBS model file, this parameter is left blank.

specification

Minimum model deployment specifications.

template

Template configuration items.

status

Model status.

tenant_id

Tenant to which a model belongs.

version

Model version.

workspace_id

ID of the workspace to which a service belongs.