38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
from collections.abc import Iterable
|
|
from typing import Optional, Union
|
|
|
|
from langchain.callbacks.manager import CallbackManager
|
|
from langchain.callbacks.stdout import StdOutCallbackHandler
|
|
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
|
|
from langchain_community.llms.ollama import Ollama
|
|
|
|
from embedchain.config import BaseLlmConfig
|
|
from embedchain.helpers.json_serializable import register_deserializable
|
|
from embedchain.llm.base import BaseLlm
|
|
|
|
|
|
@register_deserializable
|
|
class OllamaLlm(BaseLlm):
|
|
def __init__(self, config: Optional[BaseLlmConfig] = None):
|
|
super().__init__(config=config)
|
|
if self.config.model is None:
|
|
self.config.model = "llama2"
|
|
|
|
def get_llm_model_answer(self, prompt):
|
|
return self._get_answer(prompt=prompt, config=self.config)
|
|
|
|
@staticmethod
|
|
def _get_answer(prompt: str, config: BaseLlmConfig) -> Union[str, Iterable]:
|
|
callback_manager = [StreamingStdOutCallbackHandler()] if config.stream else [StdOutCallbackHandler()]
|
|
|
|
llm = Ollama(
|
|
model=config.model,
|
|
system=config.system_prompt,
|
|
temperature=config.temperature,
|
|
top_p=config.top_p,
|
|
callback_manager=CallbackManager(callback_manager),
|
|
base_url=config.base_url,
|
|
)
|
|
|
|
return llm.invoke(prompt)
|