会话缓冲区

这本笔记本展示了如何使用ConversationBufferMemory。这种记忆功能允许存储消息，然后以变量的形式提取消息。

我们首先可以将其作为字符串提取。

from langchain.memory import ConversationBufferMemory

memory = ConversationBufferMemory()
memory.save_context({"input": "hi"}, {"output": "whats up"})

memory.load_memory_variables({})

    {'history': 'Human: hi\nAI: whats up'}

我们还可以获得消息列表形式的历史记录（如果您使用聊天模型，这将非常有用）。

memory = ConversationBufferMemory(return_messages=True)
memory.save_context({"input": "hi"}, {"output": "whats up"})

memory.load_memory_variables({})

    {'history': [HumanMessage(content='hi', additional_kwargs={}),
      AIMessage(content='whats up', additional_kwargs={})]}

在链中使用

最后，让我们看看如何在链中使用它（设置verbose=True以便我们可以看到提示）。

from langchain_openai import OpenAI
from langchain.chains import ConversationChain
 
 
llm = OpenAI(temperature=0)
conversation = ConversationChain(
    llm=llm,
    verbose=True,
    memory=ConversationBufferMemory()
)

conversation.predict(input="Hi there!")



    > 进入新的ConversationChain链...
    格式化后的提示:
    以下是人类和AI之间友好的对话。AI健谈，并从其上下文中提供大量具体细节。如果AI不知道问题的答案，则如实表示不知道。

    当前对话：

    人类: Hi there!
    AI:

    > 完成链插入。



    " Hi there! It's nice to meet you. How can I help you today?"

conversation.predict(input="I'm doing well! Just having a conversation with an AI.")



    > 进入新的ConversationChain链...
    格式化后的提示:
    以下是人类和AI之间友好的对话。AI健谈，并从其上下文中提供大量具体细节。如果AI不知道问题的答案，则如实表示不知道。

    当前对话：
    人类: Hi there!
    AI:  Hi there! It's nice to meet you. How can I help you today?
    人类: I'm doing well! Just having a conversation with an AI.
    AI:

    > 完成链插入。



    " That's great! It's always nice to have a conversation with someone new. What would you like to talk about?"

conversation.predict(input="Tell me about yourself.")



    > 进入新的ConversationChain链...
    格式化后的提示:
    以下是人类和AI之间友好的对话。AI健谈，并从其上下文中提供大量具体细节。如果AI不知道问题的答案，则如实表示不知道。

    当前对话：
    人类: Hi there!
    AI:  Hi there! It's nice to meet you. How can I help you today?
    人类: I'm doing well! Just having a conversation with an AI.
    AI:  That's great! It's always nice to have a conversation with someone new. What would you like to talk about?
    人类: Tell me about yourself.
    AI:

    > 完成链插入。



    " Sure! I'm an AI created to help people with their everyday tasks. I'm programmed to understand natural language and provide helpful information. I'm also constantly learning and updating my knowledge base so I can provide more accurate and helpful answers."

多个记忆类（MultipleMemory）缓冲窗口（BufferWindow）