ModelServe sklearnserve Serve

The serve action deploys scikit-learn ML models as services on Kubernetes. A Task is created by calling run() on the Function; task parameters are passed through that call.

Overview

The sklearnserve function kind supports deploying scikit-learn models as REST API services. The model must be saved in pickle format (.pkl).

Quick example

function = dh.new_function(
    name="my-sklearn-service",
    kind="sklearnserve",
    path=model.key
)

run = function.run(
    action="serve",
    replicas=1
)

Parameters

Function Parameters

Must be specified when creating the function.

Name	Type	Description
project	str	Project name. Required only when creating from the library; otherwise MUST NOT be set.
name	str	Name that identifies the object. Required.
kind	str	Function kind. Must be sklearnserve. Required.
uuid	str	Object ID in UUID4 format.
description	str	Description of the object.
labels	list[str]	List of labels.
embedded	bool	Whether the object should be embedded in the project.
path	str	Model path. Required.
model_name	str	Name of the model.
image	str	Docker image where to serve the model.

Model Path

The model path must consists of the model key or the s3 path partition where the model files are or a zip containing the model files.

Model Image

Model image must follow the pattern:

image_regex = r"^seldonio\\/mlserver?:.*-sklearn$"

Task Parameters

Can only be specified when calling function.run().

Name	Type	Description
action	str	Task action. Required. Must be serve
node_selector	list[dict]	Node selector.
volumes	list[dict]	List of volumes.
resources	dict	Resource limits/requests.
affinity	dict	Affinity configuration.
tolerations	list[dict]	Tolerations.
envs	list[dict]	Environment variables.
secrets	list[str]	List of secret names.
profile	str	Profile template.
replicas	int	Number of replicas.
service_type	str	Service type.
service_name	str	Service name.

Run Parameters

Can only be specified when calling function.run().

No specific parameters for run of this action.

Entity methods

Run methods

Once the run is created, you can access its attributes and methods through the run object.

invoke

Invoke served model. By default it exposes infer v2 endpoint.

Parameters:

Name	Type	Description	Default
model_name	str	Name of the model.	None
method	str	Method of the request.	'POST'
url	str	URL of the request.	None
**kwargs	dict	Keyword arguments to pass to the request.	{}

Returns:

Type	Description
Response	Response from the request.