EvaluatorVersion interface
Evaluator Definition
Properties
| categories | The categories of the evaluator |
| created_at | Creation date/time of the evaluator |
| created_by | Creator of the evaluator |
| definition | Definition of the evaluator |
| description | The asset description text. |
| display_name | Display Name for evaluator. It helps to find the evaluator easily in AI Foundry. It does not need to be unique. |
| evaluator_type | The type of the evaluator |
| generation_artifacts | Provenance artifacts from the generation pipeline. Read-only; present only on evaluator versions created via an EvaluatorGenerationJob. Each artifact resolves to a versioned Foundry Dataset. |
| generation_job_id | Read-only provenance link back to the EvaluatorGenerationJob that produced this version. Present only on evaluator versions created via the generation pipeline; absent for manually-created versions and unaffected by subsequent |
| id | Asset ID, a unique identifier for the asset |
| metadata | Metadata about the evaluator |
| modified_at | Last modified date/time of the evaluator |
| name | The name of the resource |
| supported_evaluation_levels | Evaluation levels this evaluator supports (e.g., |
| tags | Tag dictionary. Tags can be added, removed, and updated. |
| version | The version of the resource |
| warnings | Categories of warnings surfaced on this generated evaluator version. Present only on versions created via an EvaluatorGenerationJob when the paired job produced non-empty warnings. Absent (treat as no warnings) when the version is not from generation, when the paired job was clean, or when a subsequent |
Property Details
categories
created_at
Creation date/time of the evaluator
created_at?: stringProperty Value
string
created_by
Creator of the evaluator
created_by?: stringProperty Value
string
definition
Definition of the evaluator
definition: EvaluatorDefinitionUnionProperty Value
description
The asset description text.
description?: stringProperty Value
string
display_name
Display Name for evaluator. It helps to find the evaluator easily in AI Foundry. It does not need to be unique.
display_name?: stringProperty Value
string
evaluator_type
generation_artifacts
Provenance artifacts from the generation pipeline. Read-only; present only on evaluator versions created via an EvaluatorGenerationJob. Each artifact resolves to a versioned Foundry Dataset.
generation_artifacts?: EvaluatorGenerationArtifactsProperty Value
generation_job_id
Read-only provenance link back to the EvaluatorGenerationJob that produced this version. Present only on evaluator versions created via the generation pipeline; absent for manually-created versions and unaffected by subsequent PATCH calls.
generation_job_id?: stringProperty Value
string
id
Asset ID, a unique identifier for the asset
id?: stringProperty Value
string
metadata
Metadata about the evaluator
metadata?: Record<string, string>Property Value
Record<string, string>
modified_at
Last modified date/time of the evaluator
modified_at?: stringProperty Value
string
name
The name of the resource
name: stringProperty Value
string
supported_evaluation_levels
Evaluation levels this evaluator supports (e.g., turn, conversation). When omitted on create, the service defaults to ["turn"]. On update, omitting this field leaves it unchanged; an empty list is rejected. Custom code-based evaluators support only turn; custom prompt-based evaluators support exactly one level (turn or conversation).
supported_evaluation_levels?: EvaluationLevel[]Property Value
tags
Tag dictionary. Tags can be added, removed, and updated.
tags?: Record<string, string>Property Value
Record<string, string>
version
The version of the resource
version?: stringProperty Value
string
warnings
Categories of warnings surfaced on this generated evaluator version. Present only on versions created via an EvaluatorGenerationJob when the paired job produced non-empty warnings. Absent (treat as no warnings) when the version is not from generation, when the paired job was clean, or when a subsequent PATCH to definition cleared the paired job's advisories. Follow generation_job_id to fetch the detailed warning payloads.
warnings?: "input_quality"[]Property Value
"input_quality"[]