迁移 ConversationBufferWindowMemory 或 ConversationTokenBufferMemory

如果您尝试迁移下面列出的旧内存类之一，请遵循本指南：

内存类型	描述
ConversationBufferWindowMemory	Keeps the last n messages of the conversation. Drops the oldest messages when there are more than n messages.
ConversationTokenBufferMemory	Keeps only the most recent messages in the conversation under the constraint that the total number of tokens in the conversation does not exceed a certain limit.

ConversationBufferWindowMemory和ConversationTokenBufferMemory在原始对话历史记录的基础上应用其他处理，以将对话历史记录修剪为适合聊天模型的上下文窗口的大小。

这种处理功能可以使用 LangChain 内置的 trim_messages 函数来实现。

重要

首先，我们将探索一种简单的方法，该方法涉及将处理逻辑应用于整个对话历史记录。

虽然这种方法很容易实现，但它有一个缺点：随着对话的增长，延迟也会增加，因为逻辑在每个回合都会重新应用于对话中的所有先前交换。

更高级的策略侧重于逐步更新对话历史记录以避免冗余处理。

例如，langgraph 关于摘要的操作指南演示了 如何在丢弃旧消息的同时维护对话的运行摘要，确保它们在以后的轮次中不会被重新处理。

建立

%%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()

LLMChain / Conversation Chain 的遗留用法

详

from langchain.chains import LLMChain
from langchain.memory import ConversationBufferWindowMemory
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(
    [
        SystemMessage(content="You are a helpful assistant."),
        MessagesPlaceholder(variable_name="chat_history"),
        HumanMessagePromptTemplate.from_template("{text}"),
    ]
)

memory = ConversationBufferWindowMemory(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"})
print(legacy_result)

API 参考：LLMChain | ConversationBufferWindowMemory | 系统消息 | ChatPromptTemplate 模板 | ChatPromptTemplate 模板 | HumanMessagePromptTemplate （简体中文） | 消息占位符 | 聊天OpenAI

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

重新实现 ConversationBufferWindowMemory 逻辑

让我们首先创建适当的逻辑来处理对话历史记录，然后我们将了解如何将其集成到应用程序中。您稍后可以将此基本设置替换为根据您的特定需求定制的更高级 logic。

我们将使用trim_messages实现将最后一个n对话的消息。当消息数量超过时，它将丢弃最早的消息n.

此外，我们还将保留系统消息（如果存在），如果存在，则它是对话中包含聊天模型说明的第一条消息。

from langchain_core.messages import (
    AIMessage,
    BaseMessage,
    HumanMessage,
    SystemMessage,
    trim_messages,
)
from langchain_openai import ChatOpenAI

messages = [
    SystemMessage("you're a good assistant, you always respond with a joke."),
    HumanMessage("i wonder why it's called langchain"),
    AIMessage(
        'Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'
    ),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage(
        "Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"
    ),
    HumanMessage("why is 42 always the answer?"),
    AIMessage(
        "Because it’s the only number that’s constantly right, even when it doesn’t add up!"
    ),
    HumanMessage("What did the cow say?"),
]

API 参考：AIMessage | BaseMessage | HumanMessage （人工消息） | 系统消息 | trim_messages | 聊天OpenAI

from langchain_core.messages import trim_messages

selected_messages = trim_messages(
    messages,
    token_counter=len,  # <-- len will simply count the number of messages rather than tokens
    max_tokens=5,  # <-- allow up to 5 messages.
    strategy="last",
    # Most chat models expect that chat history starts with either:
    # (1) a HumanMessage or
    # (2) a SystemMessage followed by a HumanMessage
    # start_on="human" makes sure we produce a valid chat history
    start_on="human",
    # Usually, we want to keep the SystemMessage
    # if it's present in the original history.
    # The SystemMessage has special instructions for the model.
    include_system=True,
    allow_partial=False,
)

for msg in selected_messages:
    msg.pretty_print()

API 参考：trim_messages

================================ System Message ================================

you're a good assistant, you always respond with a joke.
================================== Ai Message ==================================

Hmmm let me think.

Why, he's probably chasing after the last cup of coffee in the office!
================================ Human Message =================================

why is 42 always the answer?
================================== Ai Message ==================================

Because it’s the only number that’s constantly right, even when it doesn’t add up!
================================ Human Message =================================

What did the cow say?

重新实现 ConversationTokenBufferMemory 逻辑

在这里，我们将使用trim_messagesto 将 System Message 和 Conversation 中的最新消息保持在 Records 中 Token 总数不超过特定限制的约束下。

from langchain_core.messages import trim_messages

selected_messages = trim_messages(
    messages,
    # Please see API reference for trim_messages for other ways to specify a token counter.
    token_counter=ChatOpenAI(model="gpt-4o"),
    max_tokens=80,  # <-- token limit
    # The start_on is specified
    # Most chat models expect that chat history starts with either:
    # (1) a HumanMessage or
    # (2) a SystemMessage followed by a HumanMessage
    # start_on="human" makes sure we produce a valid chat history
    start_on="human",
    # Usually, we want to keep the SystemMessage
    # if it's present in the original history.
    # The SystemMessage has special instructions for the model.
    include_system=True,
    strategy="last",
)

for msg in selected_messages:
    msg.pretty_print()

API 参考：trim_messages

================================ System Message ================================

you're a good assistant, you always respond with a joke.
================================ Human Message =================================

why is 42 always the answer?
================================== Ai Message ==================================

Because it’s the only number that’s constantly right, even when it doesn’t add up!
================================ Human Message =================================

What did the cow say?

LangGraph 的现代用法

下面的示例展示了如何使用 LangGraph 添加简单的对话预处理逻辑。

注意

如果您想避免每次都对整个对话历史记录运行计算，您可以按照 演示摘要的操作指南 如何丢弃较旧的消息，确保它们在以后的轮次中不会被重新处理。

详

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):
    selected_messages = trim_messages(
        state["messages"],
        token_counter=len,  # <-- len will simply count the number of messages rather than tokens
        max_tokens=5,  # <-- allow up to 5 messages.
        strategy="last",
        # Most chat models expect that chat history starts with either:
        # (1) a HumanMessage or
        # (2) a SystemMessage followed by a HumanMessage
        # start_on="human" makes sure we produce a valid chat history
        start_on="human",
        # Usually, we want to keep the SystemMessage
        # if it's present in the original history.
        # The SystemMessage has special instructions for the model.
        include_system=True,
        allow_partial=False,
    )

    response = model.invoke(selected_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.
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!
config = {"configurable": {"thread_id": thread_id}}
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 （节省内存） | 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, Bob?

与预构建的 langgraph 代理一起使用

此示例显示了 Agent Executor 与使用 create_tool_calling_agent 函数构建的预构建代理的用法。

如果您使用的是旧的 LangChain 预构建代理之一，您应该能够 将该代码替换为新的 LangGraph 预构建代理，该代理利用 聊天模型的本机工具调用功能，并且开箱即用可能会效果更好。

详

import uuid

from langchain_core.messages import (
    AIMessage,
    BaseMessage,
    HumanMessage,
    SystemMessage,
    trim_messages,
)
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()


def prompt(state) -> list[BaseMessage]:
    """Given the agent state, return a list of messages for the chat model."""
    # We're using the message processor defined above.
    return trim_messages(
        state["messages"],
        token_counter=len,  # <-- len will simply count the number of messages rather than tokens
        max_tokens=5,  # <-- allow up to 5 messages.
        strategy="last",
        # Most chat models expect that chat history starts with either:
        # (1) a HumanMessage or
        # (2) a SystemMessage followed by a HumanMessage
        # start_on="human" makes sure we produce a valid chat history
        start_on="human",
        # Usually, we want to keep the SystemMessage
        # if it's present in the original history.
        # The SystemMessage has special instructions for the model.
        include_system=True,
        allow_partial=False,
    )



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

# The thread id is a unique key that identifies
# this particular conversation.
# We'll just generate a random uuid here.
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：AIMessage | BaseMessage | HumanMessage （人工消息） | 系统消息 | trim_messages | 工具 | 聊天OpenAI | MemorySaver （节省内存） | create_react_agent

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

hi! I'm bob. What is my age?
================================== Ai Message ==================================
Tool Calls:
  get_user_age (call_jsMvoIFv970DhqqLCJDzPKsp)
 Call ID: call_jsMvoIFv970DhqqLCJDzPKsp
  Args:
    name: bob
================================= Tool Message =================================
Name: get_user_age

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

Bob, you are 42 years old.
================================ Human Message =================================

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

Yes, your name is Bob.

LCEL：添加预处理步骤

添加复杂对话管理的最简单方法是在聊天模型前面引入预处理步骤，并将完整的对话历史记录传递给预处理步骤。

这种方法在概念上很简单，在许多情况下都适用;例如，如果使用 RunnableWithMessageHistory 而不是包装聊天模型，请使用预处理器包装聊天模型。

这种方法的明显缺点是，延迟会随着对话历史记录的增长而开始增加，原因有两个：

1. 随着对话时间的延长，可能需要从用于存储对话历史记录的任何存储中获取更多数据（如果不将其存储在内存中）。
2. 预处理逻辑最终会做很多冗余的计算，重复 conversation 前面步骤的计算。

谨慎

如果您想使用聊天模型的工具调用能力，记得在向模型添加历史预处理步骤之前，将工具绑定到模型上！

详

from langchain_core.messages import (
    AIMessage,
    BaseMessage,
    HumanMessage,
    SystemMessage,
    trim_messages,
)
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

model = ChatOpenAI()


@tool
def what_did_the_cow_say() -> str:
    """Check to see what the cow said."""
    return "foo"


message_processor = trim_messages(  # Returns a Runnable if no messages are provided
    token_counter=len,  # <-- len will simply count the number of messages rather than tokens
    max_tokens=5,  # <-- allow up to 5 messages.
    strategy="last",
    # The start_on is specified
    # to make sure we do not generate a sequence where
    # a ToolMessage that contains the result of a tool invocation
    # appears before the AIMessage that requested a tool invocation
    # as this will cause some chat models to raise an error.
    start_on=("human", "ai"),
    include_system=True,  # <-- Keep the system message
    allow_partial=False,
)

# Note that we bind tools to the model first!
model_with_tools = model.bind_tools([what_did_the_cow_say])

model_with_preprocessor = message_processor | model_with_tools

full_history = [
    SystemMessage("you're a good assistant, you always respond with a joke."),
    HumanMessage("i wonder why it's called langchain"),
    AIMessage(
        'Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'
    ),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage(
        "Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"
    ),
    HumanMessage("why is 42 always the answer?"),
    AIMessage(
        "Because it’s the only number that’s constantly right, even when it doesn’t add up!"
    ),
    HumanMessage("What did the cow say?"),
]


# We pass it explicity to the model_with_preprocesor for illustrative purposes.
# If you're using `RunnableWithMessageHistory` the history will be automatically
# read from the source the you configure.
model_with_preprocessor.invoke(full_history).pretty_print()

API 参考：AIMessage | BaseMessage | HumanMessage （人工消息） | 系统消息 | trim_messages | 工具 | 聊天OpenAI

================================== Ai Message ==================================
Tool Calls:
  what_did_the_cow_say (call_urHTB5CShhcKz37QiVzNBlIS)
 Call ID: call_urHTB5CShhcKz37QiVzNBlIS
  Args:

如果您需要实现更高效的逻辑，并希望使用RunnableWithMessageHistory目前实现这一目标的方法 是从 BaseChatMessageHistory 继承的子类，而 定义适当的逻辑add_messages（这并不是简单地附加历史记录，而是重写它）。

除非您有充分的理由实施此解决方案，否则您应该改用 LangGraph。

后续步骤

使用 LangGraph 探索持久化：

• LangGraph 快速入门教程
• 如何向图形添加持久性（“内存”）
• 如何管理对话记录
• 如何添加对话历史记录摘要

使用简单的 LCEL 添加持久性（对于更复杂的用例，首选 langgraph）：

• 如何添加消息历史记录

使用消息历史记录：

• 如何修剪消息
• 如何过滤消息
• 如何合并消息运行