AIFeatureExtractor

Represents information about the feature extractor that’s used to extract the input data required for making predictions.This object is available in API version 55.0 and later.

Supported Calls

create(), delete(), describeSObjects(), query(), retrieve(), update(), upsert()

Special Access Rules

The AIFeatureExtractor object is available when the admin settings for AI Accelerator and for the product related to the use case are enabled. The Salesforce org must have the CRM Plus license and the product’s CRM license.

Fields

AiUsecaseModelId

Type: reference
Properties: Create, Filter, Group, Nillable, Sort, Update
Description: The use case model that’s related to the feature extractor.

This field is a relationship field.
Relationship Name: AiUsecaseModel
Relationship Type: Lookup
Refers To: AIUsecaseModel

BatchInputSourceIdentifier

Type: string
Properties: Create, Filter, Group, Nillable, Sort, Update
Description: The identifier of the input source containing batch job-computed features that a model can use to generate predictions. Available in API version 57.0 and later.

BatchInputSourceInformation

Type: string
Properties: Filter, Group, Nillable, Sort
Description: The information about the batch input source, including query parameters, objects, field mappings, and filter criteria.

BatchInputSourceType

Type: picklist
Properties: Create, Defaulted on create, Filter, Group, Restricted picklist, Sort, Update
Description: The input source of the features computed in batch jobs.
Default value: CRMA
Possible values:
- CRMA
- Data Cloud

ClassName

Type: string
Properties: Create, Filter, Group, Nillable, Sort, Update
Description: The ID of the Apex class created for the feature extractor.

DeveloperName

Type: string
Properties: Create, Filter, Group, Sort, Update
Description: The developer name of the feature extractor.

FeatureInputType

Type: picklist
Properties: Create, Defaulted on create, Filter, Group, Restricted picklist, Sort, Update
Description: Required. The type of feature input that’s used in generating predictions. Available in API version 57.0 and later.
Default value: Realtime_Input
Possible values:
- Batch_And_Realtime_Input
- Batch_Input
- Realtime_Input
- Sample_Input

InputContext

Type: textarea
Properties: Create, Nillable, Update
Description: The features that serve as the context for the feature extractor in the JSON or CSV file. Available in API version 57.0 and later.

Language

Type: picklist
Properties: Create, Defaulted on create, Filter, Group, Nillable, Restricted picklist, Sort, Update
Description: The languages that are supported by the feature extractor.
Possible values:
- da—Danish
- de—German
- en_US—English
- es—Spanish
- es_MX—Spanish (Mexico)
- fi—Finnish
- fr—French
- it—Italian
- ja—Japanese
- ko—Korean
- nl_NL—Dutch
- no—Norwegian
- pt_BR—Portuguese (Brazil)
- ru—Russian
- sv—Swedish
- th—Thai
- zh_CN—Chinese (Simplified)
- zh_TW—Chinese (Traditional)

MasterLabel

Type: string
Properties: Create, Filter, Group, Sort, Update
Description: The label of the feature extractor.

NamespacePrefix

Type: string
Properties: Filter, Group, Nillable, Sort
Description: Namespace prefix associated with this object. Each Developer Edition org that creates a managed package has a unique namespace prefix.

Type

Type: picklist
Properties: Create, Defaulted on create, Filter, Group, Nillable, Restricted picklist, Sort, Update
Description: Required. Specifies the type of the feature extractor.
Default value: APEX
Possible values:
- APEX
- HYBRID
- JAVA

Usage

Use this object to configure feature extractors for your use case model when it requires features that are calculated or aggregated on run-time. A use case model can have multiple feature extractors.