Client Referencellms
semantic_router.llms.atlascloud
AtlasCloudLLM Objects
class AtlasCloudLLM(OpenAICompatibleLLM)LLM for Atlas Cloud, a preset of OpenAICompatibleLLM pointing at the Atlas Cloud gateway (https://api.atlascloud.ai/v1) and reading the API key from ATLASCLOUD_API_KEY. See https://docs.atlascloud.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 ATLASCLOUD_API_KEY, so a custom base_url or a key passed in code is lost.
__init__
def __init__(name: Optional[str] = None,
atlascloud_api_key: Optional[str] = None,
base_url: str = "https://api.atlascloud.ai/v1",
temperature: float = 0.01,
max_tokens: int = 200)Initialize the AtlasCloudLLM.
Arguments:
name(Optional[str]): The name of the Atlas Cloud model to use. Defaults to the ATLASCLOUD_CHAT_MODEL_NAME environment variable or deepseek-ai/deepseek-v4-flash.atlascloud_api_key(Optional[str]): The Atlas Cloud API key. Defaults to the ATLASCLOUD_API_KEY environment variable.base_url(str): The base URL for the Atlas Cloud API.temperature(float): The temperature of the LLM.max_tokens(int): The maximum number of tokens to generate.