# FoundryEvaluator

> **Class** in `langchain_azure_ai`

📖 [View in docs](https://reference.langchain.com/python/langchain-azure-ai/evaluation/foundry/FoundryEvaluator)

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).

## Signature

```python
FoundryEvaluator(
    self,
    *,
    project_endpoint: str,
    evaluator_name: str,
    deployment_name: str,
    display_name: str | None = None,
    credential: Any | None = None,
    poll_interval: float = 5.0,
    max_wait: float = 300.0,
)
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `project_endpoint` | `str` | Yes | Azure AI Foundry project endpoint URL. |
| `evaluator_name` | `str` | Yes | Builtin evaluator name (e.g., ``"builtin.task_completion"``). |
| `deployment_name` | `str` | Yes | Model deployment for the LLM judge. |
| `display_name` | `str \| None` | No | Human-readable name for the evaluator. (default: `None`) |
| `credential` | `Any \| None` | No | Azure credential. Defaults to ``DefaultAzureCredential``. (default: `None`) |
| `poll_interval` | `float` | No | Seconds between status checks. (default: `5.0`) |
| `max_wait` | `float` | No | Maximum seconds to wait for eval completion. (default: `300.0`) |

## Constructors

```python
__init__(
    self,
    *,
    project_endpoint: str,
    evaluator_name: str,
    deployment_name: str,
    display_name: str | None = None,
    credential: Any | None = None,
    poll_interval: float = 5.0,
    max_wait: float = 300.0,
) -> None
```

| Name | Type |
|------|------|
| `project_endpoint` | `str` |
| `evaluator_name` | `str` |
| `deployment_name` | `str` |
| `display_name` | `str \| None` |
| `credential` | `Any \| None` |
| `poll_interval` | `float` |
| `max_wait` | `float` |


## Methods

- [`close()`](https://reference.langchain.com/python/langchain-azure-ai/evaluation/foundry/FoundryEvaluator/close)
- [`evaluate()`](https://reference.langchain.com/python/langchain-azure-ai/evaluation/foundry/FoundryEvaluator/evaluate)

---

[View source on GitHub](https://github.com/langchain-ai/langchain-azure/blob/7a6a664d617264df8dcb12fcfb1bacc09f21d504/libs/azure-ai/langchain_azure_ai/evaluation/foundry.py#L62)