tempo package

class tempo.Model(name: str, protocol: tempo.serve.protocol.Protocol = V2Protocol(), local_folder: str = None, uri: str = None, platform: tempo.serve.metadata.ModelFramework = None, inputs: Optional[Union[Type, List, Dict[str, Type]]] = None, outputs: Optional[Union[Type, List, Dict[str, Type]]] = None, model_func: Callable[[...], Any] = 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 = '')

Bases: tempo.serve.base.BaseModel

__init__(name: str, protocol: tempo.serve.protocol.Protocol = V2Protocol(), local_folder: str = None, uri: str = None, platform: tempo.serve.metadata.ModelFramework = None, inputs: Optional[Union[Type, List, Dict[str, Type]]] = None, outputs: Optional[Union[Type, List, Dict[str, Type]]] = None, model_func: Callable[[...], Any] = 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 = '')

Parameters

• name – Name of the pipeline. Needs to be Kubernetes compliant.

• protocol – tempo.serve.protocol.Protocol. Defaults to KFserving V2.

• local_folder – Location of local artifacts.

• uri – Location of remote artifacts.

• platform – The tempo.serve.metadata.ModelFramework

• inputs – The input types.

• outputs – The output types.

• conda_env – 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 – The runtime options. Can be left empty and set when creating a runtime.

• description – The description of the model

class tempo.ModelFramework(value)

Bases: enum.Enum

An enumeration.

Alibi = 'alibi'

Custom = 'custom'

MLFlow = 'mlflow'

ONNX = 'ONNX'

PyTorch = 'pytorch'

SKLearn = 'sklearn'

TempoPipeline = 'tempo'

TensorRT = 'tensorrt'

Tensorflow = 'tensorflow'

XGBoost = 'xgboost'

class tempo.Pipeline(name: str, pipeline_func: Callable[[Any], Any] = None, protocol: Optional[tempo.serve.protocol.Protocol] = None, models: tempo.serve.pipeline.PipelineModels = None, local_folder: str = None, uri: str = 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 = '')

Bases: tempo.serve.base.BaseModel

deploy(runtime: tempo.serve.base.Runtime)

deploy_models(runtime: tempo.serve.base.Runtime)

save(save_env=True)

set_remote(val: bool)

set_runtime_options_override(runtime_options: Union[tempo.serve.metadata.KubernetesRuntimeOptions, tempo.serve.metadata.DockerOptions, tempo.serve.metadata.EnterpriseRuntimeOptions])

to_k8s_yaml(runtime: tempo.serve.base.Runtime) → str

Get k8s yaml

undeploy(runtime: tempo.serve.base.Runtime)

Undeploy all models and pipeline.

undeploy_models(runtime: tempo.serve.base.Runtime)

wait_ready(runtime: tempo.serve.base.Runtime, timeout_secs: int = None) → bool

class tempo.PipelineModels

Bases: types.SimpleNamespace

ModelExportKlass

alias of tempo.serve.model.Model

items()

keys()

remote_copy()

values()

tempo.deploy_local(model: Any, options: Union[tempo.serve.metadata.SeldonCoreOptions, tempo.serve.metadata.KFServingOptions, tempo.serve.metadata.SeldonEnterpriseOptions] = None) → tempo.serve.deploy.RemoteModel

tempo.deploy_remote(model: Any, options: Union[tempo.serve.metadata.SeldonCoreOptions, tempo.serve.metadata.KFServingOptions, tempo.serve.metadata.SeldonEnterpriseOptions] = None) → tempo.serve.deploy.RemoteModel

tempo.manifest(model: Any, options: Union[tempo.serve.metadata.SeldonCoreOptions, tempo.serve.metadata.KFServingOptions, tempo.serve.metadata.SeldonEnterpriseOptions] = None) → str

tempo.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 = '')

Parameters

• name – Name of the model. Needs to be Kubernetes compliant.

• protocol – tempo.serve.protocol.Protocol. Defaults to KFserving V2.

• local_folder – Location of local artifacts.

• uri – Location of remote artifacts.

• inputs – The input types.

• outputs – The output types.

• conda_env – 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 – The runtime options. Can be left empty and set when creating a runtime.

• platform – The tempo.serve.metadata.ModelFramework

• description – Description of the model

Returns

A decorated function or class as a Tempo Model.

tempo.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 = '')

A decorator for a class or function to make it a Tempo Pipeline.

Parameters

• name – Name of the pipeline. Needs to be Kubernetes compliant.

• protocol – tempo.serve.protocol.Protocol. Defaults to KFserving V2.

• local_folder – Location of local artifacts.

• uri – Location of remote artifacts.

• models – A list of models defined as PipelineModels.

• inputs – The input types.

• outputs – The output types.

• conda_env – 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 – The runtime options. Can be left empty and set when creating a runtime.

• description – Description of the pipeline

Returns

A decorated class or function.

tempo.predictmethod(f)

tempo.save(tempo_artifact: Any, save_env=True)

tempo.upload(tempo_artifact: Any)

Upload local to remote using rclone

Subpackages

• tempo.aio package
  • Submodules
    • tempo.aio.deploy module
    • tempo.aio.mixin module
    • tempo.aio.model module
    • tempo.aio.pipeline module
    • tempo.aio.utils module
• tempo.docker package
  • Submodules
    • tempo.docker.constants module
    • tempo.docker.utils module
• tempo.examples package
  • Submodules
    • tempo.examples.minio module
• tempo.ingress package
  • Submodules
    • tempo.ingress.istio module
• tempo.insights package
  • Submodules
    • tempo.insights.cloudevents module
    • tempo.insights.manager module
    • tempo.insights.worker module
    • tempo.insights.wrapper module
• tempo.k8s package
  • Submodules
    • tempo.k8s.constants module
    • tempo.k8s.utils module
• tempo.metaflow package
  • Submodules
    • tempo.metaflow.utils module
• tempo.protocols package
  • Submodules
    • tempo.protocols.seldon module
    • tempo.protocols.tensorflow module
    • tempo.protocols.v2 module
• tempo.seldon package
  • Submodules
    • tempo.seldon.constants module
    • tempo.seldon.deploy module
    • tempo.seldon.docker module
    • tempo.seldon.endpoint module
    • tempo.seldon.k8s module
    • tempo.seldon.specs module
• tempo.serve package
  • Subpackages
    • tempo.serve.loader package
      • Submodules
        • tempo.serve.loader.artifact module
        • tempo.serve.loader.env module
        • tempo.serve.loader.upload module
  • Submodules
    • tempo.serve.args module
    • tempo.serve.base module
    • tempo.serve.constants module
    • tempo.serve.deploy module
    • tempo.serve.ingress module
    • tempo.serve.metadata module
    • tempo.serve.model module
    • tempo.serve.pipeline module
    • tempo.serve.protocol module
    • tempo.serve.stub module
    • tempo.serve.types module
    • tempo.serve.typing module
    • tempo.serve.utils module
• tempo.state package
  • Submodules
    • tempo.state.state module

Submodules

• tempo.conf module
• tempo.errors module
• tempo.magic module
• tempo.mlserver module
• tempo.utils module
• tempo.version module