tempo.aio packageΒΆ
-
class
tempo.aio.
Model
(*args, **kwargs)ΒΆ Bases:
tempo.aio.mixin._AsyncMixin
,tempo.serve.model.Model
-
class
tempo.aio.
Pipeline
(*args, **kwargs)ΒΆ Bases:
tempo.aio.mixin._AsyncMixin
,tempo.serve.pipeline.Pipeline
-
tempo.aio.
deploy
(model: Any, options: Union[tempo.serve.metadata.KubernetesRuntimeOptions, tempo.serve.metadata.DockerOptions, tempo.serve.metadata.EnterpriseRuntimeOptions] = None) β tempo.serve.deploy.RemoteModelΒΆ
-
tempo.aio.
deploy_local
(model: Any, options: Union[tempo.serve.metadata.SeldonCoreOptions, tempo.serve.metadata.KFServingOptions, tempo.serve.metadata.SeldonEnterpriseOptions] = None) β tempo.serve.deploy.RemoteModelΒΆ
-
tempo.aio.
deploy_remote
(model: Any, options: Union[tempo.serve.metadata.SeldonCoreOptions, tempo.serve.metadata.KFServingOptions, tempo.serve.metadata.SeldonEnterpriseOptions] = None) β tempo.serve.deploy.RemoteModelΒΆ
-
tempo.aio.
model
(name: str, local_folder: str = None, uri: str = None, platform: tempo.serve.metadata.ModelFramework = <ModelFramework.Custom: 'custom'>, inputs: Optional[Union[Type, List, Dict[str, Type]]] = None, outputs: Optional[Union[Type, List, Dict[str, Type]]] = None, conda_env: str = None, protocol: tempo.serve.protocol.Protocol = V2Protocol(), runtime_options: Union[tempo.serve.metadata.KubernetesRuntimeOptions, tempo.serve.metadata.DockerOptions, tempo.serve.metadata.EnterpriseRuntimeOptions] = DockerOptions(runtime='tempo.seldon.SeldonDockerRuntime', state_options=StateOptions(state_type=<StateTypes.LOCAL: 'LOCAL'>, key_prefix='', host='', port=''), insights_options=InsightsOptions(worker_endpoint='', batch_size=1, parallelism=1, retries=3, window_time=0, mode_type=<InsightRequestModes.NONE: 'NONE'>, in_asyncio=False), ingress_options=IngressOptions(ingress='tempo.ingress.istio.IstioIngress', ssl=False, verify_ssl=True)), description: str = '')ΒΆ - Parameters
name β Name of the model. Needs to be Kubernetes compliant.
protocol β
tempo.serve.protocol.Protocol
. Defaults to KFserving V2.local_folder β Location of local artifacts.
uri β Location of remote artifacts.
inputs β The input types.
outputs β The output types.
conda_env β The conda environment name to use. If not specified will look for conda.yaml in local_folder or generate from current running environment.
runtime_options β The runtime options. Can be left empty and set when creating a runtime.
platform β The
tempo.serve.metadata.ModelFramework
description β Description of the model
- Returns
A decorated function or class as a Tempo Model.
-
tempo.aio.
pipeline
(name: str, protocol: tempo.serve.protocol.Protocol = V2Protocol(), local_folder: str = None, uri: str = None, models: tempo.serve.pipeline.PipelineModels = None, inputs: Optional[Union[Type, List, Dict[str, Type]]] = None, outputs: Optional[Union[Type, List, Dict[str, Type]]] = None, conda_env: str = None, runtime_options: Union[tempo.serve.metadata.KubernetesRuntimeOptions, tempo.serve.metadata.DockerOptions, tempo.serve.metadata.EnterpriseRuntimeOptions] = DockerOptions(runtime='tempo.seldon.SeldonDockerRuntime', state_options=StateOptions(state_type=<StateTypes.LOCAL: 'LOCAL'>, key_prefix='', host='', port=''), insights_options=InsightsOptions(worker_endpoint='', batch_size=1, parallelism=1, retries=3, window_time=0, mode_type=<InsightRequestModes.NONE: 'NONE'>, in_asyncio=False), ingress_options=IngressOptions(ingress='tempo.ingress.istio.IstioIngress', ssl=False, verify_ssl=True)), description: str = '')ΒΆ A decorator for a class or function to make it a Tempo Pipeline.
- Parameters
name β Name of the pipeline. Needs to be Kubernetes compliant.
protocol β
tempo.serve.protocol.Protocol
. Defaults to KFserving V2.local_folder β Location of local artifacts.
uri β Location of remote artifacts.
models β A list of models defined as PipelineModels.
inputs β The input types.
outputs β The output types.
conda_env β The conda environment name to use. If not specified will look for conda.yaml in local_folder or generate from current running environment.
runtime_options β The runtime options. Can be left empty and set when creating a runtime.
description β Description of the pipeline
- Returns
A decorated class or function.