Create Seldon Core Model Deployment

Table of Contents

Configuration properties

Use this job to deploy a Seldon Core Model into the Fusion cluster.

For information to deploy available Fusion Seldon models, see the:

sentiment-general model trained on short sentences and text for intent prediction. For more information, see Sentiment analysis and prediction.
sentiment-reviews model trained on customer reviews and longer text. For more information, see Sentiment analysis and prediction.
pretrained scispacy model trained on biomedical text.
qna-coldstart-large model trained on a variety of corpuses and tasks. For more information, see Smart answers.
qna-coldstart-mulitlingual model trained on a variety of corpuses and tasks that supports 16 languages. For more information, see Smart answers.

Configuration properties

Deploys a Seldon Core Model into the Fusion cluster

id - stringrequired

The ID for this job. Used in the API to reference this job. Allowed characters: a-z, A-Z, dash (-) and underscore (_)

<= 63 characters

Match pattern: [a-zA-Z][_\-a-zA-Z0-9]*[a-zA-Z0-9]?

sparkConfig - array[object]

Provide additional key/value pairs to be injected into the training JSON map at runtime. Values will be inserted as-is, so use " to surround string values

object attributes:{key required : {
display name: Parameter Name
type: string
}value : {
display name: Parameter Value
type: string
}}

writeOptions - array[object]

Options used when writing output to Solr or other sources

object attributes:{key required : {
display name: Parameter Name
type: string
}value : {
display name: Parameter Value
type: string
}}

readOptions - array[object]

Options used when reading input from Solr or other sources.

object attributes:{key required : {
display name: Parameter Name
type: string
}value : {
display name: Parameter Value
type: string
}}

deployModelName - stringrequired

The model name of the Seldon Core deployment to deploy (must be a valid lowercased DNS subdomain with no underscores).

<= 30 characters

Match pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$

modelReplicas - integer

How many replicas of the model should be deployed by Seldon Core

Default: 1

modelDockerRepo - stringrequired

Defines the Docker repository where the model image is located.

modelDockerImage - stringrequired

Name of the model's docker image

modelDockerSecret - string

Defines the Kubernetes secret to be used with the Docker repository

columnNames - string

A list of column names that the model generates which the ML Service will return after inference.

Default: [output1, output2]

cloudPath - string

Path to cloud storage location that contains the saved parameters for this model. Supports S3, GCS, or Azure Blob Storage URIs

cloudSecret - string

Defines the Kubernetes secret that will be used to access cloud storage

type - stringrequired

Default: argo-deploy-model

Allowed values: argo-deploy-model