🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Python agentai-societiesartificial-intelligencecommunicative-aicooperative-aideep-learninglarge-language-modelsmulti-agent-systemsnatural-language-processing
<a id="camel.agents.critic_agent"></a>
<a id="camel.agents.critic_agent.CriticAgent"></a>
## CriticAgent
```python
class CriticAgent(ChatAgent):
```
A class for the critic agent that assists in selecting an option.
**Parameters:**
- **system_message** (Union[BaseMessage, str], optional): The system message for the chat agent. (default: :obj:`None`) model (Union[BaseModelBackend, Tuple[str, str], str, ModelType, Tuple[ModelPlatformType, ModelType], List[BaseModelBackend], List[str], List[ModelType], List[Tuple[str, str]], List[Tuple[ModelPlatformType, ModelType]]], optional): The model backend(s) to use. Can be a single instance, a specification (string, enum, tuple), or a list of instances or specifications to be managed by `ModelManager`. If a list of specifications (not `BaseModelBackend` instances) is provided, they will be instantiated using `ModelFactory`. (default: :obj:`ModelPlatformType.DEFAULT` with `ModelType.DEFAULT`)
- **message_window_size** (int, optional): The maximum number of previous messages to include in the context window. If `None`, no windowing is performed. (default: :obj:`6`)
- **retry_attempts** (int, optional): The number of retry attempts if the critic fails to return a valid option. (default: :obj:`2`)
- **verbose** (bool, optional): Whether to print the critic's messages.
- **logger_color** (Any): The color of the menu options displayed to the user. (default: :obj:`Fore.MAGENTA`)
<a id="camel.agents.critic_agent.CriticAgent.__init__"></a>
### __init__
```python
def __init__(
self,
system_message: Optional[Union[BaseMessage, str]] = None,
model: Optional[Union[BaseModelBackend, Tuple[str, str], str, ModelType, Tuple[ModelPlatformType, ModelType], List[BaseModelBackend], List[str], List[ModelType], List[Tuple[str, str]], List[Tuple[ModelPlatformType, ModelType]]]] = None,
memory: Optional[AgentMemory] = None,
message_window_size: int = 6,
retry_attempts: int = 2,
verbose: bool = False,
logger_color: Any = Fore.MAGENTA
):
```
<a id="camel.agents.critic_agent.CriticAgent.flatten_options"></a>
### flatten_options
```python
def flatten_options(self, messages: Sequence[BaseMessage]):
```
Flattens the options to the critic.
**Parameters:**
- **messages** (Sequence[BaseMessage]): A list of `BaseMessage` objects.
**Returns:**
str: A string containing the flattened options to the critic.
<a id="camel.agents.critic_agent.CriticAgent.get_option"></a>
### get_option
```python
def get_option(self, input_message: BaseMessage):
```
Gets the option selected by the critic.
**Parameters:**
- **input_message** (BaseMessage): A `BaseMessage` object representing the input message.
**Returns:**
str: The option selected by the critic.
<a id="camel.agents.critic_agent.CriticAgent.parse_critic"></a>
### parse_critic
```python
def parse_critic(self, critic_msg: BaseMessage):
```
Parses the critic's message and extracts the choice.
**Parameters:**
- **critic_msg** (BaseMessage): A `BaseMessage` object representing the critic's response.
**Returns:**
Optional[str]: The critic's choice as a string, or None if the
message could not be parsed.
<a id="camel.agents.critic_agent.CriticAgent.reduce_step"></a>
### reduce_step
```python
def reduce_step(self, input_messages: Sequence[BaseMessage]):
```
Performs one step of the conversation by flattening options to the
critic, getting the option, and parsing the choice.
**Parameters:**
- **input_messages** (Sequence[BaseMessage]): A list of BaseMessage objects.
**Returns:**
ChatAgentResponse: A `ChatAgentResponse` object includes the
critic's choice.
<a id="camel.agents.critic_agent.CriticAgent.clone"></a>
### clone
```python
def clone(self, with_memory: bool = False):
```
Creates a new instance of :obj:`CriticAgent` with the same
configuration as the current instance.
**Parameters:**
- **with_memory** (bool): Whether to copy the memory (conversation history) to the new agent. If True, the new agent will have the same conversation history. If False, the new agent will have a fresh memory with only the system message. (default: :obj:`False`)
**Returns:**
CriticAgent: A new instance of :obj:`CriticAgent` with the same
configuration.