semantic_router.llms.requesty

RequestyLLM Objects

class RequestyLLM(OpenAICompatibleLLM)

LLM for Requesty, a preset of OpenAICompatibleLLM pointing at the Requesty router (https://router.requesty.ai/v1) and reading the API key from REQUESTY_API_KEY. See https://docs.requesty.ai for more information and https://app.requesty.ai/api-keys to create a key.

Limits inherited from semantic-router 0.x:

• Dynamic routes extract function inputs only when called synchronously; an async call returns the route with function_call=None.
• A router config file saves only the class and model name. Reloading one uses the default base_url and REQUESTY_API_KEY, so a custom base_url or a key passed in code is lost.

__init__

def __init__(name: Optional[str] = None,
             requesty_api_key: Optional[str] = None,
             base_url: str = "https://router.requesty.ai/v1",
             temperature: float = 0.01,
             max_tokens: int = 200)

Initialize the RequestyLLM.

Arguments:

• name (Optional[str]): The name of the Requesty model to use. Defaults to the REQUESTY_CHAT_MODEL_NAME environment variable or openai/gpt-4o-mini.
• requesty_api_key (Optional[str]): The Requesty API key. Defaults to the REQUESTY_API_KEY environment variable.
• base_url (str): The base URL for the Requesty API.
• temperature (float): The temperature of the LLM.
• max_tokens (int): The maximum number of tokens to generate.