| Name | Type | Description |
|---|---|---|
project_endpoint* | str | Azure AI Foundry project endpoint URL. |
evaluator_name* | str | Builtin evaluator name
(e.g., |
deployment_name* | str | Model deployment for the LLM judge. |
display_name | str | None | Default: None |
credential | Any | None | Default: None |
poll_interval | float | Default: 5.0 |
max_wait | float | Default: 300.0 |
Wrapper around a single Foundry agent evaluator.
Manages the lifecycle of creating an eval definition and running evaluations against it. Each instance corresponds to one evaluator type (e.g., TaskCompletion).
Human-readable name for the evaluator.
Azure credential. Defaults to DefaultAzureCredential.
Seconds between status checks.
Maximum seconds to wait for eval completion.
