如何修剪消息

pip install -qU langchain-openai

from langchain_core.messages import (
    AIMessage,
    HumanMessage,
    SystemMessage,
    ToolMessage,
    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("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_encoder
    token_counter=ChatOpenAI(model="gpt-4o"),
    # 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,
)

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,
)

trim_messages(
    messages,
    max_tokens=56,
    strategy="last",
    token_counter=ChatOpenAI(model="gpt-4o"),
    include_system=True,
    allow_partial=True,
)

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

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

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,
)

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)

trimmer.invoke(messages)

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


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

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"}},
)