聊天摘要记忆缓冲区¶

注意： 此记忆示例已被弃用，推荐使用更新、更灵活的 Memory 类。请参阅 最新文档。

ChatSummaryMemoryBuffer 是一个记忆缓冲区，它存储符合令牌限制的最后 X 条消息。它还将聊天历史摘要为一条消息。

In [ ]

%pip install llama-index-core

%pip install llama-index-core

设置¶

In [ ]

from llama_index.core.memory import ChatSummaryMemoryBuffer

memory = ChatSummaryMemoryBuffer.from_defaults(
    token_limit=40000,
    # optional set the summary prompt, here's the default:
    # summarize_prompt=(
    #     "The following is a conversation between the user and assistant. "
    #     "Write a concise summary about the contents of this conversation."
    # )
)

from llama_index.core.memory import ChatSummaryMemoryBuffer memory = ChatSummaryMemoryBuffer.from_defaults( token_limit=40000, # 可选：设置摘要提示词，以下是默认提示词： # summarize_prompt=( # "以下是用户与助手之间的对话。请对本次对话内容进行简洁摘要。" # ) )

独立使用¶

In [ ]

from llama_index.core.llms import ChatMessage

chat_history = [
    ChatMessage(role="user", content="Hello, how are you?"),
    ChatMessage(role="assistant", content="I'm doing well, thank you!"),
]

# put a list of messages
memory.put_messages(chat_history)

# put one message at a time
# memory.put_message(chat_history[0])

from llama_index.core.llms import ChatMessage chat_history = [ ChatMessage(role="user", content="Hello, how are you?"), ChatMessage(role="assistant", content="I'm doing well, thank you!"), ] # 放入消息列表 memory.put_messages(chat_history) # 一次放入一条消息 # memory.put_message(chat_history[0])

In [ ]

# Get the last X messages that fit into a token limit
history = memory.get()

# 获取符合令牌限制的最后 X 条消息 history = memory.get()

In [ ]

# Get all messages
all_history = memory.get_all()

# 获取所有消息 all_history = memory.get_all()

In [ ]

# clear the memory
memory.reset()

# 清空记忆 memory.reset()

与 Agent 结合使用¶

您可以在任何 agent 的 .run() 方法中设置记忆。

In [ ]

import os

os.environ["OPENAI_API_KEY"] = "sk-proj-..."

import os os.environ["OPENAI_API_KEY"] = "sk-proj-..."

In [ ]

from llama_index.core.agent.workflow import ReActAgent, FunctionAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI


memory = ChatMemoryBuffer.from_defaults(token_limit=40000)

agent = FunctionAgent(tools=[], llm=OpenAI(model="gpt-4o-mini"))

# context to hold the chat history/state
ctx = Context(agent)

from llama_index.core.agent.workflow import ReActAgent, FunctionAgent from llama_index.core.workflow import Context from llama_index.llms.openai import OpenAI memory = ChatMemoryBuffer.from_defaults(token_limit=40000) agent = FunctionAgent(tools=[], llm=OpenAI(model="gpt-4o-mini")) # 用于保存聊天历史/状态的上下文 ctx = Context(agent)

In [ ]

resp = await agent.run("Hello, how are you?", ctx=ctx, memory=memory)

resp = await agent.run("Hello, how are you?", ctx=ctx, memory=memory)

In [ ]

print(memory.get_all())

print(memory.get_all())

[ChatMessage(role=<MessageRole.USER: 'user'>, additional_kwargs={}, blocks=[TextBlock(block_type='text', text='Hello, how are you?')]), ChatMessage(role=<MessageRole.ASSISTANT: 'assistant'>, additional_kwargs={}, blocks=[TextBlock(block_type='text', text="Hello! I'm just a program, so I don't have feelings, but I'm here and ready to help you. How can I assist you today?")])]