48 lines
1.7 KiB
Python
48 lines
1.7 KiB
Python
from typing import Dict, List, Optional
|
|
|
|
from openai import OpenAI
|
|
|
|
from mem0.configs.llms.base import BaseLlmConfig
|
|
from mem0.llms.base import LLMBase
|
|
|
|
|
|
class LMStudioLLM(LLMBase):
|
|
def __init__(self, config: Optional[BaseLlmConfig] = None):
|
|
super().__init__(config)
|
|
|
|
self.config.model = self.config.model or "lmstudio-community/Meta-Llama-3.1-70B-Instruct-GGUF/Meta-Llama-3.1-70B-Instruct-IQ2_M.gguf"
|
|
self.config.api_key = self.config.api_key or "lm-studio"
|
|
|
|
self.client = OpenAI(base_url=self.config.lmstudio_base_url, api_key=self.config.api_key)
|
|
|
|
def generate_response(
|
|
self,
|
|
messages: List[Dict[str, str]],
|
|
response_format: dict = {"type": "json_object"},
|
|
tools: Optional[List[Dict]] = None,
|
|
tool_choice: str = "auto"
|
|
):
|
|
"""
|
|
Generate a response based on the given messages using LM Studio.
|
|
|
|
Args:
|
|
messages (list): List of message dicts containing 'role' and 'content'.
|
|
response_format (str or object, optional): Format of the response. Defaults to "text".
|
|
tools (list, optional): List of tools that the model can call. Defaults to None.
|
|
tool_choice (str, optional): Tool choice method. Defaults to "auto".
|
|
|
|
Returns:
|
|
str: The generated response.
|
|
"""
|
|
params = {
|
|
"model": self.config.model,
|
|
"messages": messages,
|
|
"temperature": self.config.temperature,
|
|
"max_tokens": self.config.max_tokens,
|
|
"top_p": self.config.top_p
|
|
}
|
|
if response_format:
|
|
params["response_format"] = response_format
|
|
|
|
response = self.client.chat.completions.create(**params)
|
|
return response.choices[0].message.content |