semantic_router.llms.orcarouter

OrcaRouterLLM Objects

class OrcaRouterLLM(OpenAICompatibleLLM)

LLM for OrcaRouter, a preset of OpenAICompatibleLLM pointing at the OrcaRouter gateway (https://api.orcarouter.ai/v1) and reading the API key from ORCAROUTER_API_KEY. See https://www.orcarouter.ai for more information.

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 ORCAROUTER_API_KEY, so a custom base_url or a key passed in code is lost.

__init__

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

Initialize the OrcaRouterLLM.

Arguments:

• name (Optional[str]): The name of the OrcaRouter model to use. Defaults to the ORCAROUTER_CHAT_MODEL_NAME environment variable or orcarouter/auto.
• orcarouter_api_key (Optional[str]): The OrcaRouter API key. Defaults to the ORCAROUTER_API_KEY environment variable.
• base_url (str): The base URL for the OrcaRouter API.
• temperature (float): The temperature of the LLM.
• max_tokens (int): The maximum number of tokens to generate.