Azure CreateEvaluation
CertifiedCreate an evaluation run in Azure AI Foundry
Azure CreateEvaluation
Create an evaluation run in Azure AI Foundry
Submits a new evaluation job using a dataset and a set of evaluators. Requires Entra ID authentication (DefaultAzureCredential).
type: io.kestra.plugin.azure.aifoundry.CreateEvaluationExamples
Create a new evaluation run in Azure AI Foundry
id: azure_ai_create_evaluation
namespace: company.team
tasks:
- id: create_eval
type: io.kestra.plugin.azure.aifoundry.CreateEvaluation
endpoint: "{{ secret('AZURE_AI_FOUNDRY_ENDPOINT') }}"
tenantId: "{{ secret('AZURE_TENANT_ID') }}"
clientId: "{{ secret('AZURE_CLIENT_ID') }}"
clientSecret: "{{ secret('AZURE_CLIENT_SECRET') }}"
datasetId: "azureml:my-dataset:1"
displayName: "Nightly Groundedness Eval"
evaluators:
groundedness: "azureml://registries/azureml/models/Groundedness-Evaluator/versions/1"
Properties
datasetId *string
Dataset ID
The Azure AI dataset ID to evaluate (e.g. azureml: my-dataset: 1).
endpoint *string
Azure AI Foundry endpoint
The Azure AI Foundry project or model endpoint URL.
evaluators *object
Evaluators
A map of evaluator keys to their Azure ML evaluator IDs.
apiKey string
Azure AI Foundry API key
API key for API-key authentication. When omitted, DefaultAzureCredential (Entra ID) is used instead.
assets
Assets this task consumes as inputs or produces as outputs, for lineage tracking and the asset graph (Enterprise Edition). A flow declaring this property on a task is rejected in the open-source edition.
io.kestra.core.models.assets.AssetsDeclaration
IGNOREFAILWARNAsset failure behavior
Behavior applied to the task state when a declared asset fails to render, emit, or be persisted (e.g. a lock conflict): FAIL escalates it to FAILED, WARN (default) warns it if it would otherwise succeed, IGNORE leaves the state untouched.
Whether to auto-register assets referenced dynamically at runtime that are not statically declared in inputs or outputs.
The assets consumed as inputs.
io.kestra.core.models.assets.AssetIdentifier
1The assets produced as outputs.
io.kestra.plugin.ee.assets.Dataset
1150{}1150io.kestra.plugin.ee.assets.File
1150{}1150io.kestra.plugin.ee.assets.Table
1150{}1150io.kestra.plugin.ee.assets.VM
1150{}1150io.kestra.core.models.assets.External
1150{}1150io.kestra.core.models.assets.Custom
11501Custom asset type
{}1150clientId string
Azure client ID
Client ID of the Azure app registration used with tenantId and clientSecret.
clientSecret string
Azure client secret
Client secret of the Azure app registration used with tenantId and clientId.
displayName string
Display Name
Human-readable label for this evaluation run.
tenantId string
Azure tenant ID
Azure Entra tenant ID used with clientId and clientSecret for service principal authentication.
Outputs
displayName string
The display name of the evaluation
name string
The assigned evaluation name / ID
status string
The initial status of the evaluation
