> ## 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.agentchat.group.llm_condition.LLMCondition

<h2 id="autogen.agentchat.group.llm_condition.LLMCondition" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

  <span class="doc doc-object-name doc-class-name">LLMCondition</span>
</h2>

```python theme={null}
LLMCondition(**data: Any)
```

Protocol for conditions evaluated by an LLM.<br />Create a new model by parsing and validating input data from keyword arguments.<br />Raises \[`ValidationError`]\[pydantic\_core.ValidationError] if the input data cannot be
validated to form a valid model.<br />`self` is explicitly positional-only to allow `self` as a field name.

<b>Parameters:</b>

| Name     | Description   |
| -------- | ------------- |
| `**data` | **Type:** Any |

### Class Attributes

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

#### model\_config

<br />

<br />

### Instance Methods

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

#### get\_prompt

```python theme={null}
get_prompt(
    self,
    agent: ConversableAgent,
    messages: list[dict[str, Any]]
) -> str
```

Get the prompt text for LLM evaluation.<br />

<b>Parameters:</b>

| Name       | Description                                                                 |
| ---------- | --------------------------------------------------------------------------- |
| `agent`    | The agent evaluating the condition<br /><br />**Type:** ConversableAgent    |
| `messages` | The conversation history<br /><br />**Type:** list\[dict\[str, typing.Any]] |

<b>Returns:</b>

| Type | Description                                |
| ---- | ------------------------------------------ |
| str  | The prompt text to be evaluated by the LLM |

<br />