49 lines
1.5 KiB
Python
49 lines
1.5 KiB
Python
import os
|
|
from typing import Dict, List, Optional
|
|
|
|
from openai import OpenAI
|
|
|
|
from mem0.configs.llms.base import BaseLlmConfig
|
|
from mem0.llms.base import LLMBase
|
|
|
|
|
|
class XAILLM(LLMBase):
|
|
def __init__(self, config: Optional[BaseLlmConfig] = None):
|
|
super().__init__(config)
|
|
|
|
if not self.config.model:
|
|
self.config.model = "grok-2-latest"
|
|
|
|
api_key = self.config.api_key or os.getenv("XAI_API_KEY")
|
|
base_url = (
|
|
self.config.xai_base_url
|
|
or os.getenv("XAI_API_BASE")
|
|
or "https://api.x.ai/v1"
|
|
)
|
|
self.client = OpenAI(api_key=api_key, base_url=base_url)
|
|
|
|
def generate_response(self, messages: List[Dict[str, str]], response_format=None):
|
|
"""
|
|
Generate a response based on the given messages using XAI.
|
|
|
|
Args:
|
|
messages (list): List of message dicts containing 'role' and 'content'.
|
|
response_format (str or object, optional): Format of the response. Defaults to "text".
|
|
|
|
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
|