v0.4.0 支持任意替换的模型，改进配置文件

好好好好好好好好好

src/plugins/memory_system/llm_module.py

@@ -1,68 +0,0 @@
-import os
-import requests
-from typing import Tuple, Union
-import time
-from nonebot import get_driver
-import aiohttp
-import asyncio
-from src.plugins.chat.config import global_config
-driver = get_driver()
-config = driver.config
-
-class LLMModel:
-    # def __init__(self, model_name="deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", **kwargs):
-    def __init__(self, model_name=global_config.SILICONFLOW_MODEL_V3, **kwargs):
-        self.model_name = model_name
-        self.params = kwargs
-        self.api_key = config.siliconflow_key
-        self.base_url = config.siliconflow_base_url
-
-    async def generate_response(self, prompt: str) -> Tuple[str, str]:
-        """根据输入的提示生成模型的响应"""
-        headers = {
-            "Authorization": f"Bearer {self.api_key}",
-            "Content-Type": "application/json"
-        }
-        
-        # 构建请求体
-        data = {
-            "model": self.model_name,
-            "messages": [{"role": "user", "content": prompt}],
-            "temperature": 0.5,
-            **self.params
-        }
-        
-        # 发送请求到完整的chat/completions端点
-        api_url = f"{self.base_url.rstrip('/')}/chat/completions"
-        
-        max_retries = 3
-        base_wait_time = 15
-        
-        for retry in range(max_retries):
-            try:
-                async with aiohttp.ClientSession() as session:
-                    async with session.post(api_url, headers=headers, json=data) as response:
-                        if response.status == 429:
-                            wait_time = base_wait_time * (2 ** retry)  # 指数退避
-                            print(f"遇到请求限制(429)，等待{wait_time}秒后重试...")
-                            await asyncio.sleep(wait_time)
-                            continue
-                            
-                        response.raise_for_status()  # 检查其他响应状态
-                        
-                        result = await response.json()
-                        if "choices" in result and len(result["choices"]) > 0:
-                            content = result["choices"][0]["message"]["content"]
-                            reasoning_content = result["choices"][0]["message"].get("reasoning_content", "")
-                            return content, reasoning_content
-                        return "没有返回结果", ""
-                
-            except Exception as e:
-                if retry < max_retries - 1:  # 如果还有重试机会
-                    wait_time = base_wait_time * (2 ** retry)
-                    print(f"请求失败，等待{wait_time}秒后重试... 错误: {str(e)}")
-                    await asyncio.sleep(wait_time)
-                else:
-                    return f"请求失败: {str(e)}", ""
-        
-        return "达到最大重试次数，请求仍然失败", ""

src/plugins/memory_system/memory.py

@@ -1,19 +1,16 @@
 # -*- coding: utf-8 -*-
 import os
 import jieba
-from .llm_module import LLMModel
 import networkx as nx
 import matplotlib.pyplot as plt
-import math
 from collections import Counter
 import datetime
 import random
 import time
 from ..chat.config import global_config
-import sys
 from ...common.database import Database # 使用正确的导入语法
 from ..chat.utils import calculate_information_content, get_cloest_chat_from_db
-   
+from ..models.utils_model import LLM_request
 class Memory_graph:
     def __init__(self):
         self.G = nx.Graph()  # 使用 networkx 的图结构
@@ -169,8 +166,8 @@ class Memory_graph:
 class Hippocampus:
     def __init__(self,memory_graph:Memory_graph):
         self.memory_graph = memory_graph
-        self.llm_model = LLMModel()
-        self.llm_model_small = LLMModel(model_name="deepseek-ai/DeepSeek-V2.5")
+        self.llm_model = LLM_request(model = global_config.llm_normal,temperature=0.5)
+        self.llm_model_small = LLM_request(model = global_config.llm_normal_minor,temperature=0.5)
         
     def get_memory_sample(self,chat_size=20,time_frequency:dict={'near':2,'mid':4,'far':3}):
         current_timestamp = datetime.datetime.now().timestamp()