Skip to main content

​
OllamaLLM Objects

class OllamaLLM(BaseLLM)
LLM for Ollama. Enables fully local LLM use, helpful for local implementation of dynamic routes.

​
__init__

def __init__(name: str = "openhermes",
             temperature: float = 0.2,
             max_tokens: Optional[int] = 200,
             stream: bool = False)
Initialize the OllamaLLM. Arguments:
  • name (str): The name of the Ollama model to use.
  • temperature (float): The temperature of the LLM.
  • max_tokens (Optional[int]): The maximum number of tokens to generate.
  • stream (bool): Whether to stream the response.

​
__call__

def __call__(messages: List[Message],
             temperature: Optional[float] = None,
             name: Optional[str] = None,
             max_tokens: Optional[int] = None,
             stream: Optional[bool] = None) -> str
Call the OllamaLLM. Arguments:
  • messages (List[Message]): The messages to pass to the OllamaLLM.
  • temperature (Optional[float]): The temperature of the LLM.
  • name (Optional[str]): The name of the Ollama model to use.
  • max_tokens (Optional[int]): The maximum number of tokens to generate.
  • stream (Optional[bool]): Whether to stream the response.