如何修剪消息

先决条件

本指南假定您熟悉以下概念

本指南中的方法还需要 langchain-core>=0.2.9。

所有模型都有有限的上下文窗口，这意味着它们可以接受的 tokens 输入数量是有限制的。如果您有非常长的消息或链/代理累积了很长的消息历史记录，您需要管理传递给模型的消息的长度。

trim_messages 可用于将聊天历史记录的大小减少到指定的 token 计数或指定的消息计数。

如果将修剪后的聊天历史记录直接传递回聊天模型，则修剪后的聊天历史记录应满足以下属性

生成的聊天历史记录应是有效的。通常，这意味着应满足以下属性
- 聊天历史记录开始于 (1) HumanMessage 或 (2) SystemMessage 后跟 HumanMessage。
- 聊天历史记录结束于 HumanMessage 或 ToolMessage。
- ToolMessage 只能在涉及工具调用的 AIMessage 之后出现。
这可以通过设置 start_on="human" 和 ends_on=("human", "tool") 来实现。
它包括最近的消息并删除聊天历史记录中的旧消息。这可以通过设置 strategy="last" 来实现。
通常，新的聊天历史记录应包括 SystemMessage（如果它存在于原始聊天历史记录中），因为 SystemMessage 包括对聊天模型的特殊指令。SystemMessage 几乎总是历史记录中的第一条消息（如果存在）。这可以通过设置 include_system=True 来实现。

基于 token 计数修剪

在这里，我们将基于 token 计数修剪聊天历史记录。修剪后的聊天历史记录将生成一个有效的聊天历史记录，其中包含 SystemMessage。

为了保留最新的消息，我们设置 strategy="last"。我们还将设置 include_system=True 以包含 SystemMessage，并设置 start_on="human" 以确保生成的聊天历史记录有效。

当基于 token 计数使用 trim_messages 时，这是一个很好的默认配置。请记住为您的用例调整 token_counter 和 max_tokens。

请注意，对于我们的 token_counter，我们可以传入一个函数（稍后会详细介绍）或一个语言模型（因为语言模型具有消息 token 计数方法）。当您修剪消息以适应特定模型的上下文窗口时，传入模型是有意义的

pip install -qU langchain-openai

from langchain_core.messages import (
    AIMessage,
    HumanMessage,
    SystemMessage,
    ToolMessage,
    trim_messages,
)
from langchain_core.messages.utils import count_tokens_approximately

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("what do you call a speechless parrot"),
]


trim_messages(
    messages,
    # Keep the last <= n_count tokens of the messages.
    strategy="last",
    # Remember to adjust based on your model
    # or else pass a custom token_counter
    token_counter=count_tokens_approximately,
    # Most chat models expect that chat history starts with either:
    # (1) a HumanMessage or
    # (2) a SystemMessage followed by a HumanMessage
    # Remember to adjust based on the desired conversation
    # length
    max_tokens=45,
    # Most chat models expect that chat history starts with either:
    # (1) a HumanMessage or
    # (2) a SystemMessage followed by a HumanMessage
    start_on="human",
    # Most chat models expect that chat history ends with either:
    # (1) a HumanMessage or
    # (2) a ToolMessage
    end_on=("human", "tool"),
    # 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,
)

[SystemMessage(content="you're a good assistant, you always respond with a joke.", additional_kwargs={}, response_metadata={}),
 HumanMessage(content='what do you call a speechless parrot', additional_kwargs={}, response_metadata={})]

基于消息计数修剪

或者，我们可以通过设置 token_counter=len，基于消息计数修剪聊天历史记录。在这种情况下，每条消息将计为一个 token，而 max_tokens 将控制最大消息数。

当基于消息计数使用 trim_messages 时，这是一个很好的默认配置。请记住为您的用例调整 max_tokens。

trim_messages(
    messages,
    # Keep the last <= n_count tokens of the messages.
    strategy="last",
    token_counter=len,
    # When token_counter=len, each message
    # will be counted as a single token.
    # Remember to adjust for your use case
    max_tokens=5,
    # Most chat models expect that chat history starts with either:
    # (1) a HumanMessage or
    # (2) a SystemMessage followed by a HumanMessage
    start_on="human",
    # Most chat models expect that chat history ends with either:
    # (1) a HumanMessage or
    # (2) a ToolMessage
    end_on=("human", "tool"),
    # 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,
)

[SystemMessage(content="you're a good assistant, you always respond with a joke.", additional_kwargs={}, response_metadata={}),
 HumanMessage(content='and who is harrison chasing anyways', additional_kwargs={}, response_metadata={}),
 AIMessage(content="Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!", additional_kwargs={}, response_metadata={}),
 HumanMessage(content='what do you call a speechless parrot', additional_kwargs={}, response_metadata={})]

高级用法

您可以使用 trim_messages 作为构建块来创建更复杂的处理逻辑。

如果我们想要允许分割消息的内容，我们可以指定 allow_partial=True

trim_messages(
    messages,
    max_tokens=56,
    strategy="last",
    token_counter=count_tokens_approximately,
    include_system=True,
    allow_partial=True,
)

[SystemMessage(content="you're a good assistant, you always respond with a joke.", additional_kwargs={}, response_metadata={}),
 AIMessage(content="\nWhy, he's probably chasing after the last cup of coffee in the office!", additional_kwargs={}, response_metadata={}),
 HumanMessage(content='what do you call a speechless parrot', additional_kwargs={}, response_metadata={})]

默认情况下，SystemMessage 将不包括在内，因此您可以通过设置 include_system=False 或删除 include_system 参数来删除它。

trim_messages(
    messages,
    max_tokens=45,
    strategy="last",
    token_counter=count_tokens_approximately,
)

[AIMessage(content="Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!", additional_kwargs={}, response_metadata={}),
 HumanMessage(content='what do you call a speechless parrot', additional_kwargs={}, response_metadata={})]

我们可以通过指定 strategy="first" 来执行获取第一个 max_tokens 的翻转操作

trim_messages(
    messages,
    max_tokens=45,
    strategy="first",
    token_counter=count_tokens_approximately,
)

[SystemMessage(content="you're a good assistant, you always respond with a joke.", additional_kwargs={}, response_metadata={}),
 HumanMessage(content="i wonder why it's called langchain", additional_kwargs={}, response_metadata={})]

使用 `ChatModel` 作为 token 计数器

您可以将 ChatModel 作为 token 计数器传递。这将使用 ChatModel.get_num_tokens_from_messages。让我们演示如何将其与 OpenAI 一起使用

from langchain_openai import ChatOpenAI

trim_messages(
    messages,
    max_tokens=45,
    strategy="first",
    token_counter=ChatOpenAI(model="gpt-4o"),
)

API 参考：ChatOpenAI

[SystemMessage(content="you're a good assistant, you always respond with a joke.", additional_kwargs={}, response_metadata={}),
 HumanMessage(content="i wonder why it's called langchain", additional_kwargs={}, response_metadata={})]

编写自定义 token 计数器

我们可以编写一个自定义 token 计数器函数，该函数接受消息列表并返回一个整数。

pip install -qU tiktoken

from typing import List

import tiktoken
from langchain_core.messages import BaseMessage, ToolMessage


def str_token_counter(text: str) -> int:
    enc = tiktoken.get_encoding("o200k_base")
    return len(enc.encode(text))


def tiktoken_counter(messages: List[BaseMessage]) -> int:
    """Approximately reproduce https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb

    For simplicity only supports str Message.contents.
    """
    num_tokens = 3  # every reply is primed with <|start|>assistant<|message|>
    tokens_per_message = 3
    tokens_per_name = 1
    for msg in messages:
        if isinstance(msg, HumanMessage):
            role = "user"
        elif isinstance(msg, AIMessage):
            role = "assistant"
        elif isinstance(msg, ToolMessage):
            role = "tool"
        elif isinstance(msg, SystemMessage):
            role = "system"
        else:
            raise ValueError(f"Unsupported messages type {msg.__class__}")
        num_tokens += (
            tokens_per_message
            + str_token_counter(role)
            + str_token_counter(msg.content)
        )
        if msg.name:
            num_tokens += tokens_per_name + str_token_counter(msg.name)
    return num_tokens


trim_messages(
    messages,
    token_counter=tiktoken_counter,
    # Keep the last <= n_count tokens of the messages.
    strategy="last",
    # When token_counter=len, each message
    # will be counted as a single token.
    # Remember to adjust for your use case
    max_tokens=45,
    # Most chat models expect that chat history starts with either:
    # (1) a HumanMessage or
    # (2) a SystemMessage followed by a HumanMessage
    start_on="human",
    # Most chat models expect that chat history ends with either:
    # (1) a HumanMessage or
    # (2) a ToolMessage
    end_on=("human", "tool"),
    # 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,
)

API 参考：BaseMessage | ToolMessage

[SystemMessage(content="you're a good assistant, you always respond with a joke.", additional_kwargs={}, response_metadata={}),
 HumanMessage(content='what do you call a speechless parrot', additional_kwargs={}, response_metadata={})]

链式

trim_messages 可以命令式（如上所示）或声明式使用，使其易于与链中的其他组件组合

llm = ChatOpenAI(model="gpt-4o")

# Notice we don't pass in messages. This creates
# a RunnableLambda that takes messages as input
trimmer = trim_messages(
    token_counter=llm,
    # Keep the last <= n_count tokens of the messages.
    strategy="last",
    # When token_counter=len, each message
    # will be counted as a single token.
    # Remember to adjust for your use case
    max_tokens=45,
    # Most chat models expect that chat history starts with either:
    # (1) a HumanMessage or
    # (2) a SystemMessage followed by a HumanMessage
    start_on="human",
    # Most chat models expect that chat history ends with either:
    # (1) a HumanMessage or
    # (2) a ToolMessage
    end_on=("human", "tool"),
    # 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,
)

chain = trimmer | llm
chain.invoke(messages)

AIMessage(content='A "polly-no-wanna-cracker"!', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 32, 'total_tokens': 43, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_90d33c15d4', 'finish_reason': 'stop', 'logprobs': None}, id='run-b1f8b63b-6bc2-4df4-b3b9-dfc4e3e675fe-0', usage_metadata={'input_tokens': 32, 'output_tokens': 11, 'total_tokens': 43, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})

查看 LangSmith 跟踪，我们可以看到在消息传递到模型之前，它们首先被修剪：https://smith.langchain.com/public/65af12c4-c24d-4824-90f0-6547566e59bb/r

仅查看修剪器，我们可以看到它是一个 Runnable 对象，可以像所有 Runnables 一样调用

trimmer.invoke(messages)

[SystemMessage(content="you're a good assistant, you always respond with a joke.", additional_kwargs={}, response_metadata={}),
 HumanMessage(content='what do you call a speechless parrot', additional_kwargs={}, response_metadata={})]

与 ChatMessageHistory 一起使用

当处理聊天历史记录时，修剪消息特别有用，聊天历史记录可能会变得任意长

from langchain_core.chat_history import InMemoryChatMessageHistory
from langchain_core.runnables.history import RunnableWithMessageHistory

chat_history = InMemoryChatMessageHistory(messages=messages[:-1])


def dummy_get_session_history(session_id):
    if session_id != "1":
        return InMemoryChatMessageHistory()
    return chat_history


trimmer = trim_messages(
    max_tokens=45,
    strategy="last",
    token_counter=llm,
    # 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,
    # 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",
)

chain = trimmer | llm
chain_with_history = RunnableWithMessageHistory(chain, dummy_get_session_history)
chain_with_history.invoke(
    [HumanMessage("what do you call a speechless parrot")],
    config={"configurable": {"session_id": "1"}},
)

API 参考：InMemoryChatMessageHistory | RunnableWithMessageHistory

AIMessage(content='A "polygon"!', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 4, 'prompt_tokens': 32, 'total_tokens': 36, 'completion_tokens_details': {'reasoning_tokens': 0}}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_c17d3befe7', 'finish_reason': 'stop', 'logprobs': None}, id='run-71d9fce6-bb0c-4bb3-acc8-d5eaee6ae7bc-0', usage_metadata={'input_tokens': 32, 'output_tokens': 4, 'total_tokens': 36})

查看 LangSmith 跟踪，我们可以看到我们检索了所有消息，但在消息传递到模型之前，它们被修剪为仅包含系统消息和最后一条人类消息：https://smith.langchain.com/public/17dd700b-9994-44ca-930c-116e00997315/r

API 参考

有关所有参数的完整描述，请访问 API 参考：https://python.langchain.ac.cn/api_reference/core/messages/langchain_core.messages.utils.trim_messages.html

基于 token 计数修剪​

基于消息计数修剪​

高级用法​

使用 ChatModel 作为 token 计数器​

编写自定义 token 计数器​

链式​

与 ChatMessageHistory 一起使用​

API 参考​

此页是否对您有帮助？