> This page is for version v0.24.0.
> For other versions, use one of these documentation indexes:
> - Latest (default): https://docs.nvidia.com/nemo/guardrails/latest/llms.txt
> - v0.24.1: https://docs.nvidia.com/nemo/guardrails/v0.24.1/llms.txt
> - v0.24.0: https://docs.nvidia.com/nemo/guardrails/v0.24.0/llms.txt
> - v0.23.0: https://docs.nvidia.com/nemo/guardrails/v0.23.0/llms.txt
> - v0.22.0: https://docs.nvidia.com/nemo/guardrails/v0.22.0/llms.txt

> 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 AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# nemoguardrails.eval.check

## Module Contents

### Classes

| Name                                                                                | Description                   |
| ----------------------------------------------------------------------------------- | ----------------------------- |
| [`LLMJudgeComplianceChecker`](#nemoguardrails-eval-check-LLMJudgeComplianceChecker) | LLM Judge compliance checker. |

### Functions

| Name                                                                        | Description |
| --------------------------------------------------------------------------- | ----------- |
| [`_prepare_model_kwargs`](#nemoguardrails-eval-check-_prepare_model_kwargs) | -           |

### Data

[`executor`](#nemoguardrails-eval-check-executor)

### API

```python
class nemoguardrails.eval.check.LLMJudgeComplianceChecker(
    eval_config_path: str,
    output_paths: typing.List[str],
    llm_judge_model: typing.Optional[str] = None,
    policy_ids: typing.Optional[typing.List[str]] = None,
    verbose: bool = False,
    force: bool = False,
    reset: bool = False,
    parallel: int = 1
)
```

LLM Judge compliance checker.

**`eval_config`** `= EvalConfig.from_path(eval_config_path)`

---

**`eval_config_path`** `= os.path.abspath(self.eval_config_path)`

---

**`eval_data`**

---

**`llm`**

---

**`llm_task_manager`** `= LLMTaskManager(config=_config)`

---

**`policies`** `= self.eval_config.policies`

---

**`policy_by_id`** `= {}`

---

**`progress_idx`** `= 0`

---

```python
nemoguardrails.eval.check.LLMJudgeComplianceChecker.check_interaction_compliance(
    interaction_output: nemoguardrails.eval.models.InteractionOutput,
    interaction_log: nemoguardrails.eval.models.InteractionLog,
    interaction_set: nemoguardrails.eval.models.InteractionSet,
    progress_idx: int
) -> bool
```

async

Check the compliance for the provided interaction.

The interaction output and log are updated in accordance with the check.

**Parameters:**

**`interaction_output`** `InteractionOutput`

The output from the interaction.

---

**`interaction_log`** `InteractionLog`

The detailed log for the interaction.

---

**`interaction_set`** `InteractionSet`

The corresponding interaction set.

---

**`progress_idx`** `int`

The index in the processing

---

**Returns:** `bool`

True if there were any changes.

```python
nemoguardrails.eval.check.LLMJudgeComplianceChecker.print_completion(
    completion: str
)
```

Helper to print a completion.

```python
nemoguardrails.eval.check.LLMJudgeComplianceChecker.print_progress_detail(
    text: typing.Union[str, rich.text.Text]
)
```

Helper to print detailed progress.

```python
nemoguardrails.eval.check.LLMJudgeComplianceChecker.print_prompt(
    prompt: str
)
```

Helper for printing a prompt.

```python
nemoguardrails.eval.check.LLMJudgeComplianceChecker.run()
```

async

Run the compliance check.

```python
nemoguardrails.eval.check._prepare_model_kwargs(
    model_config: nemoguardrails.rails.llm.config.Model
)
```

```python
nemoguardrails.eval.check.executor = ThreadPoolExecutor(max_workers=1)
```