从 ConversationBufferMemory 或 ConversationStringBufferMemory 迁移

ConversationBufferMemory 和 ConversationStringBufferMemory 用于在人类与AI助手之间保持对话记录，而无需任何额外处理。

笔记

ConversationStringBufferMemory 等价于 ConversationBufferMemory，但其目标是未针对聊天模型的 LLM。

使用现有现代原语处理对话历史的方法有：

1. 使用 LangGraph 持久化 以及对消息历史记录的适当处理
2. 使用 LCEL 与 RunnableWithMessageHistory 结合，并对消息历史记录进行适当的处理。

大多数用户会发现 LangGraph持久化 在使用和配置上比相应的LCEL更简单，尤其是在更复杂的用例中。

设置

%%capture --no-stderr
%pip install --upgrade --quiet langchain-openai langchain

import os
from getpass import getpass

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass()

与 LLMChain / ConversationChain 一起使用

此部分展示了如何迁移离开与 ConversationBufferMemory 或 ConversationStringBufferMemory 一起使用的 LLMChain 或 ConversationChain。

旧版

以下是使用 ConversationBufferMemory 的示例，配合 LLMChain 或等效的 ConversationChain。

详细信息

from langchain.chains import LLMChain
from langchain.memory import ConversationBufferMemory
from langchain_core.messages import SystemMessage
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.prompts.chat import (
    ChatPromptTemplate,
    HumanMessagePromptTemplate,
    MessagesPlaceholder,
)
from langchain_openai import ChatOpenAI

prompt = ChatPromptTemplate(
    [
        MessagesPlaceholder(variable_name="chat_history"),
        HumanMessagePromptTemplate.from_template("{text}"),
    ]
)

memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)

legacy_chain = LLMChain(
    llm=ChatOpenAI(),
    prompt=prompt,
    memory=memory,
)

legacy_result = legacy_chain.invoke({"text": "my name is bob"})
print(legacy_result)

legacy_result = legacy_chain.invoke({"text": "what was my name"})

API 参考：LLMChain | ConversationBufferMemory | SystemMessage | ChatPromptTemplate | ChatPromptTemplate | HumanMessagePromptTemplate | MessagesPlaceholder | ChatOpenAI

{'text': 'Hello Bob! How can I assist you today?', 'chat_history': [HumanMessage(content='my name is bob', additional_kwargs={}, response_metadata={}), AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, response_metadata={})]}

legacy_result["text"]

'Your name is Bob. How can I assist you today, Bob?'

笔记

请注意，单个 memory 对象中不支持分离对话线程

LangGraph

下面的示例展示了如何使用 LangGraph 实现 ConversationChain 或 LLMChain，其中包含 ConversationBufferMemory。

此示例假设您已经对 LangGraph 有一定程度的了解。如果您还不熟悉，请参阅 LangGraph 快速入门指南 获取更多详细信息。

LangGraph 提供了许多额外的功能（例如时间旅行和中断），并且在其他更复杂（和更真实）的架构中也能很好地工作。

详细信息

import uuid

from IPython.display import Image, display
from langchain_core.messages import HumanMessage
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import START, MessagesState, StateGraph

# Define a new graph
workflow = StateGraph(state_schema=MessagesState)

# Define a chat model
model = ChatOpenAI()


# Define the function that calls the model
def call_model(state: MessagesState):
    response = model.invoke(state["messages"])
    # We return a list, because this will get added to the existing list
    return {"messages": response}


# Define the two nodes we will cycle between
workflow.add_edge(START, "model")
workflow.add_node("model", call_model)


# Adding memory is straight forward in langgraph!
memory = MemorySaver()

app = workflow.compile(
    checkpointer=memory
)


# The thread id is a unique key that identifies
# this particular conversation.
# We'll just generate a random uuid here.
# This enables a single application to manage conversations among multiple users.
thread_id = uuid.uuid4()
config = {"configurable": {"thread_id": thread_id}}


input_message = HumanMessage(content="hi! I'm bob")
for event in app.stream({"messages": [input_message]}, config, stream_mode="values"):
    event["messages"][-1].pretty_print()

# Here, let's confirm that the AI remembers our name!
input_message = HumanMessage(content="what was my name?")
for event in app.stream({"messages": [input_message]}, config, stream_mode="values"):
    event["messages"][-1].pretty_print()

API 参考：HumanMessage | MemorySaver | StateGraph

================================ Human Message =================================

hi! I'm bob
================================== Ai Message ==================================

Hello Bob! How can I assist you today?
================================ Human Message =================================

what was my name?
================================== Ai Message ==================================

Your name is Bob. How can I help you today, Bob?

LCEL 可运行的带消息历史记录功能

或者，如果你有一个简单的链，可以将链中的聊天模型包装在 RunnableWithMessageHistory 中。

请参阅以下迁移指南以获取更多信息。

与预构建代理一起使用

此示例展示了如何使用代理执行器与使用 create_tool_calling_agent 函数构建的预构建代理。

如果您正在使用旧版 LangChain 预构建代理之一，您应该能够用新版的 langgraph 预构建代理 替换该代码，它利用了聊天模型的原生工具调用功能，可能开箱即用效果更好。

旧版用法

详细信息

from langchain import hub
from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain.memory import ConversationBufferMemory
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = ChatOpenAI(temperature=0)


@tool
def get_user_age(name: str) -> str:
    """Use this tool to find the user's age."""
    # This is a placeholder for the actual implementation
    if "bob" in name.lower():
        return "42 years old"
    return "41 years old"


tools = [get_user_age]

prompt = ChatPromptTemplate.from_messages(
    [
        ("placeholder", "{chat_history}"),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}"),
    ]
)

# Construct the Tools agent
agent = create_tool_calling_agent(model, tools, prompt)
# Instantiate memory
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)

# Create an agent
agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(
    agent=agent,
    tools=tools,
    memory=memory,  # Pass the memory to the executor
)

# Verify that the agent can use tools
print(agent_executor.invoke({"input": "hi! my name is bob what is my age?"}))
print()
# Verify that the agent has access to conversation history.
# The agent should be able to answer that the user's name is bob.
print(agent_executor.invoke({"input": "do you remember my name?"}))

API 参考：hub |AgentExecutor | create_tool_calling_agent | ConversationBufferMemory | 工具 |ChatOpenAI

{'input': 'hi! my name is bob what is my age?', 'chat_history': [HumanMessage(content='hi! my name is bob what is my age?', additional_kwargs={}, response_metadata={}), AIMessage(content='Bob, you are 42 years old.', additional_kwargs={}, response_metadata={})], 'output': 'Bob, you are 42 years old.'}

{'input': 'do you remember my name?', 'chat_history': [HumanMessage(content='hi! my name is bob what is my age?', additional_kwargs={}, response_metadata={}), AIMessage(content='Bob, you are 42 years old.', additional_kwargs={}, response_metadata={}), HumanMessage(content='do you remember my name?', additional_kwargs={}, response_metadata={}), AIMessage(content='Yes, your name is Bob.', additional_kwargs={}, response_metadata={})], 'output': 'Yes, your name is Bob.'}

LangGraph

您可以按照标准的LangChain教程来 构建一个代理，并深入了解其工作原理。

此示例在此处明确展示，以便用户更容易比较传统实现与相应的 langgraph 实现。

此示例展示了如何向 langgraph 中的 预构建的 react 代理 添加记忆功能。

有关更多详细信息，请参阅 langgraph 中的 如何向预构建的 ReAct 代理添加记忆 指南。

详细信息

import uuid

from langchain_core.messages import HumanMessage
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.checkpoint.memory import MemorySaver
from langgraph.prebuilt import create_react_agent


@tool
def get_user_age(name: str) -> str:
    """Use this tool to find the user's age."""
    # This is a placeholder for the actual implementation
    if "bob" in name.lower():
        return "42 years old"
    return "41 years old"


memory = MemorySaver()
model = ChatOpenAI()
app = create_react_agent(
    model,
    tools=[get_user_age],
    checkpointer=memory,
)

# The thread id is a unique key that identifies
# this particular conversation.
# We'll just generate a random uuid here.
# This enables a single application to manage conversations among multiple users.
thread_id = uuid.uuid4()
config = {"configurable": {"thread_id": thread_id}}

# Tell the AI that our name is Bob, and ask it to use a tool to confirm
# that it's capable of working like an agent.
input_message = HumanMessage(content="hi! I'm bob. What is my age?")

for event in app.stream({"messages": [input_message]}, config, stream_mode="values"):
    event["messages"][-1].pretty_print()

# Confirm that the chat bot has access to previous conversation
# and can respond to the user saying that the user's name is Bob.
input_message = HumanMessage(content="do you remember my name?")

for event in app.stream({"messages": [input_message]}, config, stream_mode="values"):
    event["messages"][-1].pretty_print()

API 参考：HumanMessage | 工具 |ChatOpenAI | MemorySaver | create_react_agent

================================ Human Message =================================

hi! I'm bob. What is my age?
================================== Ai Message ==================================
Tool Calls:
  get_user_age (call_oEDwEbIDNdokwqhAV6Azn47c)
 Call ID: call_oEDwEbIDNdokwqhAV6Azn47c
  Args:
    name: bob
================================= Tool Message =================================
Name: get_user_age

42 years old
================================== Ai Message ==================================

Bob, you are 42 years old! If you need any more assistance or information, feel free to ask.
================================ Human Message =================================

do you remember my name?
================================== Ai Message ==================================

Yes, your name is Bob. If you have any other questions or need assistance, feel free to ask!

如果我们使用不同的线程 ID，就会开启一个新的对话，机器人将不知道我们的名字！

config = {"configurable": {"thread_id": "123456789"}}

input_message = HumanMessage(content="hi! do you remember my name?")

for event in app.stream({"messages": [input_message]}, config, stream_mode="values"):
    event["messages"][-1].pretty_print()

================================ Human Message =================================

hi! do you remember my name?
================================== Ai Message ==================================

Hello! Yes, I remember your name. It's great to see you again! How can I assist you today?

下一步

探索使用LangGraph进行持久化：

• LangGraph 快速入门教程
• 如何为你的图添加持久性（“记忆”）
• 如何管理对话历史
• 如何添加对话历史摘要

通过简单的 LCEL 实现持久化存储（更复杂的用例建议使用 langgraph）：

• 如何添加消息历史记录

处理消息历史记录：

• 如何修剪消息
• 如何过滤消息
• 如何合并消息运行