🐫 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
AzureOpenAIModel
class AzureOpenAIModel(BaseModelBackend):
Azure OpenAI API in a unified BaseModelBackend interface.
Parameters:
- model_type (Union[ModelType, str]): Model for which a backend is created, Should be the deployment name you chose when you deployed an azure model.
- model_config_dict (Optional[Dict[str, Any]], optional): A dictionary that will be fed into:obj:
openai.ChatCompletion.create(). If :obj:None, :obj:ChatGPTConfig().as_dict()will be used. (default: :obj:None) - api_key (Optional[str], optional): The API key for authenticating with the OpenAI service. (default: :obj:
None) - url (Optional[str], optional): The url to the OpenAI service. (default: :obj:
None) - api_version (Optional[str], optional): The api version for the model. (default: :obj:
None) - azure_ad_token (Optional[str], optional): Your Azure Active Directory token, https://www.microsoft.com/en-us/security/business/ identity-access/microsoft-entra-id. (default: :obj:
None) - azure_ad_token_provider (Optional[AzureADTokenProvider], optional): A function that returns an Azure Active Directory token, will be invoked on every request. (default: :obj:
None) - token_counter (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:
OpenAITokenCounterwill 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) - max_retries (int, optional): Maximum number of retries for API calls. (default: :obj:
3) - client (Optional[Any], optional): A custom synchronous AzureOpenAI client instance. If provided, this client will be used instead of creating a new one. Useful for RL frameworks like AReaL or rLLM that provide Azure OpenAI-compatible clients. The client should implement the AzureOpenAI client interface with
.chat.completions.create()and.beta.chat.completions.parse()methods. (default: :obj:None) - async_client (Optional[Any], optional): A custom asynchronous AzureOpenAI client instance. If provided, this client will be used instead of creating a new one. The client should implement the AsyncAzureOpenAI client interface. (default: :obj:
None) - azure_deployment_name (Optional[str], optional): Deprecated. Use
model_typeparameter instead. This parameter is kept for backward compatibility and will be removed in a future version. (default: :obj:None) **kwargs (Any): Additional arguments to pass to the client initialization. Ignored if custom clients are provided. - References:
- https: //learn.microsoft.com/en-us/azure/ai-services/openai/
init
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,
timeout: Optional[float] = None,
token_counter: Optional[BaseTokenCounter] = None,
api_version: Optional[str] = None,
azure_ad_token_provider: Optional['AzureADTokenProvider'] = None,
azure_ad_token: Optional[str] = None,
max_retries: int = 3,
client: Optional[Any] = None,
async_client: Optional[Any] = None,
azure_deployment_name: Optional[str] = None,
**kwargs: Any
):
token_counter
def token_counter(self):
Returns:
BaseTokenCounter: The token counter following the model's tokenization style.
_run
def _run(
self,
messages: List[OpenAIMessage],
response_format: Optional[Type[BaseModel]] = None,
tools: Optional[List[Dict[str, Any]]] = None
):
Runs inference of Azure OpenAI chat completion.
Parameters:
- messages (List[OpenAIMessage]): Message list with the chat history in OpenAI API format.
- response_format (Optional[Type[BaseModel]]): The format of the response.
- tools (Optional[List[Dict[str, Any]]]): The schema of the tools to use for the request.
Returns:
Union[ChatCompletion, Stream[ChatCompletionChunk]]:
ChatCompletion in the non-stream mode, or
Stream[ChatCompletionChunk] in the stream mode.
ChatCompletionStreamManager[BaseModel] for
structured output streaming.
_request_chat_completion
def _request_chat_completion(
self,
messages: List[OpenAIMessage],
tools: Optional[List[Dict[str, Any]]] = None
):
_request_parse
def _request_parse(
self,
messages: List[OpenAIMessage],
response_format: Type[BaseModel],
tools: Optional[List[Dict[str, Any]]] = None
):
_request_stream_parse
def _request_stream_parse(
self,
messages: List[OpenAIMessage],
response_format: Type[BaseModel],
tools: Optional[List[Dict[str, Any]]] = None
):
Request streaming structured output parsing.
stream
def stream(self):
Returns:
bool: Whether the model is in stream mode.