Langchain 的 Conversation summary memory

Langchain 的 Conversation summary memory

现在让我们看一下使用稍微复杂的内存类型 - ConversationSummaryMemory 。这种类型的记忆会随着时间的推移创建对话的摘要。这对于随着时间的推移压缩对话中的信息非常有用。对话摘要内存对发生的对话进行总结,并将当前摘要存储在内存中。然后可以使用该内存将迄今为止的对话摘要注入提示/链中。此内存对于较长的对话最有用,因为在提示中逐字保留过去的消息历史记录会占用太多令牌。

我们首先来探讨一下这种存储器的基本功能。

示例代码,

复制代码
from langchain.memory import ConversationSummaryMemory, ChatMessageHistory
from langchain.llms import OpenAI

memory = ConversationSummaryMemory(llm=OpenAI(temperature=0))
memory.save_context({"input": "hi"}, {"output": "whats up"})

memory.load_memory_variables({})

输出结果,

复制代码
    {'history': '\nThe human greets the AI, to which the AI responds.'}

我们还可以获取历史记录作为消息列表(如果您将其与聊天模型一起使用,这非常有用)。

复制代码
memory = ConversationSummaryMemory(llm=OpenAI(temperature=0), return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})

memory.load_memory_variables({})

输出结果,

复制代码
    {'history': [SystemMessage(content='\nThe human greets the AI, to which the AI responds.', additional_kwargs={})]}

我们也可以直接使用 predict_new_summary 方法。

复制代码
messages = memory.chat_memory.messages
previous_summary = ""
memory.predict_new_summary(messages, previous_summary)

输出结果,

复制代码
    '\nThe human greets the AI, to which the AI responds.'

Initializing with messages

如果您有此类之外的消息,您可以使用 ChatMessageHistory 轻松初始化该类。加载期间,将计算摘要。

示例代码,

复制代码
history = ChatMessageHistory()
history.add_user_message("hi")
history.add_ai_message("hi there!")

memory = ConversationSummaryMemory.from_messages(llm=OpenAI(temperature=0), chat_memory=history, return_messages=True)

memory.buffer

输出结果,

复制代码
    '\nThe human greets the AI, to which the AI responds with a friendly greeting.'

Using in a chain

让我们看一下在链中使用它的示例,再次设置 verbose=True 以便我们可以看到提示。

示例代码,

复制代码
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
llm = OpenAI(temperature=0)
conversation_with_summary = ConversationChain(
    llm=llm, 
    memory=ConversationSummaryMemory(llm=OpenAI()),
    verbose=True
)
conversation_with_summary.predict(input="Hi, what's up?")

输出结果,

复制代码
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    
    Human: Hi, what's up?
    AI:
    
    > Finished chain.





    " Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?"

示例代码,

复制代码
conversation_with_summary.predict(input="Tell me more about it!")

输出结果,

复制代码
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    
    The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue.
    Human: Tell me more about it!
    AI:
    
    > Finished chain.





    " Sure! The customer is having trouble with their computer not connecting to the internet. I'm helping them troubleshoot the issue and figure out what the problem is. So far, we've tried resetting the router and checking the network settings, but the issue still persists. We're currently looking into other possible solutions."

示例代码,

复制代码
conversation_with_summary.predict(input="Very cool -- what is the scope of the project?")

输出结果,

复制代码
    > Entering new ConversationChain chain...
    Prompt after formatting:
    The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
    
    Current conversation:
    
    The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue where their computer was not connecting to the internet. The AI was troubleshooting the issue and had already tried resetting the router and checking the network settings, but the issue still persisted and they were looking into other possible solutions.
    Human: Very cool -- what is the scope of the project?
    AI:
    
    > Finished chain.





    " The scope of the project is to troubleshoot the customer's computer issue and find a solution that will allow them to connect to the internet. We are currently exploring different possibilities and have already tried resetting the router and checking the network settings, but the issue still persists."

完结!

相关推荐
踏莎行hyx2 小时前
使用langchain连接llama.cpp部署的本地deepseek大模型开发简单的LLM应用
c++·ai·langchain·大模型·llama.cpp·deepseek
小陈phd20 小时前
langchain从入门到精通(四十一)——基于ReACT架构的Agent智能体设计与实现
react.js·架构·langchain
聚客AI20 小时前
🎯 RAG系统工业级部署指南:六步实现<3%幻觉率的问答系统
人工智能·langchain·llm
redreamSo2 天前
AI 绘图效率神器:Mermaid Previewer Sidebar Chrome 插件
chrome·langchain·aigc
聚客AI2 天前
⚡ 突破LLM三大局限:LangChain架构核心解析与最佳实践
人工智能·langchain·llm
董厂长2 天前
langchain :记忆组件混淆概念澄清 & 创建Conversational ReAct后显示指定 记忆组件
人工智能·深度学习·langchain·llm
敲键盘的小夜猫3 天前
LLM复杂记忆存储-多会话隔离案例实战
人工智能·python·langchain
王国强20093 天前
LangChain 核心原理全解析 —— 拆解智能体系统的底层逻辑
langchain
大模型开发3 天前
Java开发者LLM实战——使用LangChain4j构建本地RAG系统
程序员·langchain·llm
王国强20093 天前
Langchain-Chatchat 项目全景介绍 —— 中文本地智能问答系统的未来范式
langchain