在本文中，我们调用AI接口实现简单的聊天功能，并为聊天功能添加简单的记忆存储能力，这里先存储到文本中作为演示

python
import os
import uuid
from dataclasses import dataclass
from operator import itemgetter

from injector import inject
from langchain.memory import ConversationBufferWindowMemory
from langchain_community.chat_message_histories import FileChatMessageHistory
from langchain_community.chat_models import ChatTongyi
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.runnables import RunnablePassthrough, RunnableLambda

from internal.schema.app_schema import CompletionReq
from internal.service import AppService
from pkg.response import success_json, validate_error_json, success_message

    def debug(self, app_id: uuid.UUID):
        """聊天接口"""
        # 1. 提取从接口中获取的输入，POST
        req = CompletionReq()
        if not req.validate():
            return validate_error_json(req.errors)

        # 创建prompt于记忆
        prompt = ChatPromptTemplate.from_messages([
            ("system", "你是一个强大的聊天机器人，能根据用户的提问回答问题"),
            MessagesPlaceholder("history"),
            ("human", "{query}")
        ])

        memory = ConversationBufferWindowMemory(
            k=3,  # 保留最近的3轮对话
            input_key="query",
            output_key="output",
            return_messages=True,
            chat_memory=FileChatMessageHistory("./storage/memory/chat_history.txt")
        )

        # 创建大语言模型
        llm = ChatTongyi(model="qwen-max", dashscope_api_key=os.getenv("OPENAI_API_KEY"))
        # 创建链应用
        chain = RunnablePassthrough.assign(
            history=RunnableLambda(memory.load_memory_variables) | itemgetter("history")
        ) | prompt | llm | StrOutputParser()
        # 调用链应用
        chain_input = {"query": req.query.data}
        content = chain.invoke(chain_input)
        
        # 讲本轮对话添加到历史上下文中
        memory.save_context(chain_input, {"output": content})

        return success_json({"content": content})