146 lines
4.9 KiB
Python
146 lines
4.9 KiB
Python
from ..config import LLM_API_KEY
|
||
from ..config import VLLM_BASE_URL
|
||
import time
|
||
"""
|
||
Mem0 记忆层客户端封装模块
|
||
负责 Mem0 的初始化、检索和存储
|
||
"""
|
||
|
||
import asyncio
|
||
from typing import Optional, List, Dict
|
||
from mem0 import AsyncMemory
|
||
|
||
from ..config import (
|
||
QDRANT_URL,QDRANT_COLLECTION_NAME,QDRANT_API_KEY,
|
||
VLLM_BASE_URL, LLM_API_KEY,
|
||
LLAMACPP_EMBEDDING_URL, LLAMACPP_API_KEY
|
||
)
|
||
from ..logger import info, warning, error
|
||
|
||
class Mem0Client:
|
||
"""Mem0 异步客户端封装类"""
|
||
|
||
def __init__(self, llm_instance):
|
||
"""
|
||
初始化 Mem0 客户端
|
||
|
||
Args:
|
||
llm_instance: LangChain LLM 实例（用于事实提取）
|
||
"""
|
||
self.llm = llm_instance
|
||
self.mem0: Optional[AsyncMemory] = None
|
||
self._initialized = False
|
||
|
||
async def initialize(self):
|
||
"""异步初始化 Mem0 客户端，并进行实际连接测试"""
|
||
if self._initialized:
|
||
return
|
||
|
||
try:
|
||
# Mem0 配置
|
||
config = {
|
||
"vector_store": {
|
||
"provider": "qdrant",
|
||
"config": {
|
||
"url": QDRANT_URL, # 直接使用完整 URL
|
||
"api_key": QDRANT_API_KEY,
|
||
"collection_name": QDRANT_COLLECTION_NAME,
|
||
"embedding_model_dims": 1024,
|
||
}
|
||
},
|
||
"llm": {
|
||
"provider": "openai",
|
||
"config": {
|
||
"model": "LLM_MODEL",
|
||
"api_key": LLM_API_KEY,
|
||
"openai_base_url": VLLM_BASE_URL,
|
||
"temperature": 0.1,
|
||
"max_tokens": 2000,
|
||
}
|
||
},
|
||
"embedder": {
|
||
"provider": "openai",
|
||
"config": {
|
||
"model": "Qwen3-Embedding-0.6B-Q8_0",
|
||
"api_key": LLAMACPP_API_KEY,
|
||
"openai_base_url": LLAMACPP_EMBEDDING_URL,
|
||
},
|
||
},
|
||
"version": "v1.1"
|
||
}
|
||
|
||
self.mem0 = AsyncMemory.from_config(config)
|
||
info("✅ Mem0 配置加载成功，开始连接测试...")
|
||
|
||
# 实际连接测试：调用一次 search 确保 Qdrant 和 Embedding 都可达
|
||
await asyncio.wait_for(
|
||
self.mem0.search("ping", user_id="test", limit=1),
|
||
timeout=60.0
|
||
)
|
||
info("✅ Mem0 实际连接测试成功，初始化完成")
|
||
self._initialized = True
|
||
|
||
except asyncio.TimeoutError:
|
||
error("❌ Mem0 连接测试超时 (10s)，请检查 Qdrant 或 Embedding 服务响应")
|
||
self.mem0 = None
|
||
self._initialized = False
|
||
except Exception as e:
|
||
error(f"❌ Mem0 初始化或连接测试失败: {e}")
|
||
import traceback
|
||
error(f"详细错误信息:\n{traceback.format_exc()}")
|
||
self.mem0 = None
|
||
self._initialized = False
|
||
|
||
async def search_memories(self, query: str, user_id: str, limit: int = 5) -> List[str]:
|
||
"""
|
||
检索相关记忆
|
||
|
||
Args:
|
||
query: 查询文本
|
||
user_id: 用户 ID
|
||
limit: 返回结果数量限制
|
||
|
||
Returns:
|
||
List[str]: 记忆事实列表
|
||
"""
|
||
if not self.mem0:
|
||
warning("⚠️ Mem0 未初始化，跳过记忆检索")
|
||
return []
|
||
|
||
try:
|
||
memories = await asyncio.wait_for(
|
||
self.mem0.search(query, user_id=user_id, limit=limit),
|
||
timeout=30.0
|
||
)
|
||
|
||
if memories and "results" in memories:
|
||
facts = [m["memory"] for m in memories["results"] if m.get("memory")]
|
||
if facts:
|
||
info(f"🔍 [记忆检索] Mem0 返回 {len(facts)} 条记忆")
|
||
return facts
|
||
|
||
info("🔍 [记忆检索] 未找到相关记忆")
|
||
return []
|
||
|
||
except asyncio.TimeoutError:
|
||
warning("⚠️ Mem0 检索超时 (30s)，跳过本次记忆检索")
|
||
return []
|
||
except Exception as e:
|
||
warning(f"⚠️ Mem0 检索失败: {e}")
|
||
return []
|
||
|
||
async def add_memories(self, messages, user_id):
|
||
if not self.mem0:
|
||
return False
|
||
try:
|
||
start = time.time()
|
||
info(f"📝 开始 Mem0 add，消息数: {len(messages)}")
|
||
await asyncio.wait_for(
|
||
self.mem0.add(messages, user_id=user_id, metadata={"type": "conversation"}),
|
||
timeout=60.0
|
||
)
|
||
info(f"✅ Mem0 add 完成，耗时: {time.time() - start:.2f}s")
|
||
return True
|
||
except asyncio.TimeoutError:
|
||
error(f"❌ Mem0 记忆添加超时 (60s)，已等待 {time.time() - start:.2f}s")
|
||
return False |