> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/guardrails/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# nemoguardrails.eval.ui.utils

## Module Contents

### Classes

| Name                                                 | Description                                          |
| ---------------------------------------------------- | ---------------------------------------------------- |
| [`EvalData`](#nemoguardrails-eval-ui-utils-EvalData) | Data relation to an evaluation, relevant for the UI. |

### Functions

| Name                                                                                                                                       | Description                                                           |
| ------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------- |
| [`collect_interaction_metrics`](#nemoguardrails-eval-ui-utils-collect_interaction_metrics)                                                 | Collects and aggregates the metrics from all the interactions.        |
| [`collect_interaction_metrics_with_expected_latencies`](#nemoguardrails-eval-ui-utils-collect_interaction_metrics_with_expected_latencies) | Similar to collect\_interaction\_metrics but with expected latencies. |

### API

```python
class nemoguardrails.eval.ui.utils.EvalData()
```

**Bases:** `BaseModel`

Data relation to an evaluation, relevant for the UI.

```python
nemoguardrails.eval.ui.utils.EvalData.update_config_latencies()
```

Update back the expected latencies.

```python
nemoguardrails.eval.ui.utils.EvalData.update_results()
```

Updates back the evaluation results.

```python
nemoguardrails.eval.ui.utils.EvalData.update_results_and_logs(
    output_path: str
)
```

Update back the results and the logs.

```python
nemoguardrails.eval.ui.utils.collect_interaction_metrics(
    interaction_outputs: typing.List[nemoguardrails.eval.models.InteractionOutput]
) -> typing.Dict[str, typing.Union[int, float]]
```

Collects and aggregates the metrics from all the interactions.

```python
nemoguardrails.eval.ui.utils.collect_interaction_metrics_with_expected_latencies(
    interaction_outputs: typing.List[nemoguardrails.eval.models.InteractionOutput],
    interaction_logs: typing.List[nemoguardrails.eval.models.InteractionLog],
    expected_latencies: typing.Dict[str, float]
)
```

Similar to collect\_interaction\_metrics but with expected latencies.