> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# autogen.oai.client_utils.validate_parameter

<code class="doc-symbol doc-symbol-heading doc-symbol-function" />

#### validate\_parameter

```python theme={null}
validate_parameter(
    params: dict[str, Any],
    param_name: str,
    allowed_types: tuple[Any, ...],
    allow_None: bool,
    default_value: Any,
    numerical_bound: tuple[float | None, float | None] | None,
    allowed_values: list[Any] | None
) -> Any
```

Validates a given config parameter, checking its type, values, and setting defaults
Parameters: <br />    params (Dict\[str, Any]): Dictionary containing parameters to validate.<br />    param\_name (str): The name of the parameter to validate.<br />    allowed\_types (Tuple): Tuple of acceptable types for the parameter.<br />    allow\_None (bool): Whether the parameter can be `None`.<br />    default\_value (Any): The default value to use if the parameter is invalid or missing.<br />    numerical\_bound (Optional\[Tuple\[Optional\[float], Optional\[float]]]): <br />        A tuple specifying the lower and upper bounds for numerical parameters.<br />        Each bound can be `None` if not applicable.<br />    allowed\_values (Optional\[List\[Any]]): A list of acceptable values for the parameter.<br />        Can be `None` if no specific values are required.<br />Returns: <br />    Any: The validated parameter value or the default value if validation fails.<br />Raises: <br />    TypeError: If `allowed_values` is provided but is not a list.<br />Example Usage:

```python theme={null}
    # Validating a numerical parameter within specific bounds
    params = \{"temperature": 0.5, "safety_model": "Meta-Llama/Llama-Guard-7b"}
    temperature = validate_parameter(params, "temperature", (int, float), True, 0.7, (0, 1), None)
    # Result: 0.5

    # Validating a parameter that can be one of a list of allowed values
    model = validate_parameter(
    params, "safety_model", str, True, None, None, ["Meta-Llama/Llama-Guard-7b", "Meta-Llama/Llama-Guard-13b"]
    )
    # If "safety_model" is missing or invalid in params, defaults to "default"
```

<b>Parameters:</b>

| Name              | Description                                            |
| ----------------- | ------------------------------------------------------ |
| `params`          | **Type:** dict\[str, typing.Any]                       |
| `param_name`      | **Type:** str                                          |
| `allowed_types`   | **Type:** tuple\[typing.Any, ...]                      |
| `allow_None`      | **Type:** bool                                         |
| `default_value`   | **Type:** Any                                          |
| `numerical_bound` | **Type:** tuple\[float \| None, float \| None] \| None |
| `allowed_values`  | **Type:** list\[typing.Any] \| None                    |

<b>Returns:</b>

| Type | Description                                                                  |
| ---- | ---------------------------------------------------------------------------- |
| Any  | Any: The validated parameter value or the default value if validation fails. |

<br />