🐫 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.models.reka_model"></a>
<a id="camel.models.reka_model.RekaModel"></a>
## RekaModel
```python
class RekaModel(BaseModelBackend):
```
Reka API in a unified OpenAICompatibleModel interface.
**Parameters:**
- **model_type** (Union[ModelType, str]): Model for which a backend is created, one of REKA_* series.
- **model_config_dict** (Optional[Dict[str, Any]], optional): A dictionary that will be fed into:obj:`Reka.chat.create()`. If :obj:`None`, :obj:`RekaConfig().as_dict()` will be used. (default: :obj:`None`)
- **api_key** (Optional[str], optional): The API key for authenticating with the Reka service. (default: :obj:`None`)
- **url** (Optional[str], optional): The url to the Reka service. (default: :obj:`None`)
- **token_counter** (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)
- **timeout** (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:`None`) **kwargs (Any): Additional arguments to pass to the client initialization.
<a id="camel.models.reka_model.RekaModel.__init__"></a>
### __init__
```python
def __init__(
self,
model_type: Union[ModelType, str],
model_config_dict: Optional[Dict[str, Any]] = None,
api_key: Optional[str] = None,
url: Optional[str] = None,
token_counter: Optional[BaseTokenCounter] = None,
timeout: Optional[float] = None,
**kwargs: Any
):
```
<a id="camel.models.reka_model.RekaModel._map_finish_reason"></a>
### _map_finish_reason
```python
def _map_finish_reason(reka_reason: str):
```
Map a Reka finish reason to its OpenAI equivalent.
Reka's SDK types finish_reason as
`__INLINE_CODE_0__`, so a future
provider value is a normal, successful response rather than a
malformed one. An unrecognized reason falls back to "stop" (the
OpenAI default for a completed response) instead of raising, and
the raw value is logged so the mapping can be extended.
<a id="camel.models.reka_model.RekaModel._convert_reka_to_openai_response"></a>
### _convert_reka_to_openai_response
```python
def _convert_reka_to_openai_response(self, response: 'ChatResponse'):
```
Converts a Reka `ChatResponse` to an OpenAI-style `ChatCompletion`
response.
**Parameters:**
- **response** (ChatResponse): The response object from the Reka API.
**Returns:**
ChatCompletion: An OpenAI-compatible chat completion response.
<a id="camel.models.reka_model.RekaModel._convert_openai_to_reka_messages"></a>
### _convert_openai_to_reka_messages
```python
def _convert_openai_to_reka_messages(
self,
messages: List[OpenAIMessage],
response_format: Optional[Type[BaseModel]] = None,
tools: Optional[List[str]] = None
):
```
Converts OpenAI API messages to Reka API messages.
**Parameters:**
- **messages** (List[OpenAIMessage]): A list of messages in OpenAI format.
**Returns:**
List[ChatMessage]: A list of messages converted to Reka's format.
<a id="camel.models.reka_model.RekaModel.token_counter"></a>
### token_counter
```python
def token_counter(self):
```
**Returns:**
BaseTokenCounter: The token counter following the model's
tokenization style.
<a id="camel.models.reka_model.RekaModel._run"></a>
### _run
```python
def _run(
self,
messages: List[OpenAIMessage],
response_format: Optional[Type[BaseModel]] = None,
tools: Optional[List[Dict[str, Any]]] = None
):
```
Runs inference of Mistral chat completion.
**Parameters:**
- **messages** (List[OpenAIMessage]): Message list with the chat history in OpenAI API format.
**Returns:**
ChatCompletion.
<a id="camel.models.reka_model.RekaModel.stream"></a>
### stream
```python
def stream(self):
```
**Returns:**
bool: Whether the model is in stream mode.