聊天记忆缓冲区¶

**注意：** 此记忆示例已废弃，推荐使用更新更灵活的 Memory 类。请参阅最新文档。

ChatMemoryBuffer 是一个记忆缓冲区，它简单地存储符合 token 限制的最后 X 条消息。

%pip install llama-index-core

设置¶

In [ ]

from llama_index.core.memory import ChatMemoryBuffer

memory = ChatMemoryBuffer.from_defaults(token_limit=40000)

from llama_index.core.memory import ChatMemoryBuffer memory = ChatMemoryBuffer.from_defaults(token_limit=40000)

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="你好，你好吗？"), ChatMessage(role="assistant", content="我很好，谢谢！"), ] # put a list of messages memory.put_messages(chat_history) # put one message at a time # 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 token 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()

与代理一起使用¶

您可以在任何代理的 .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-..." 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)

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)

resp = await agent.run("你好，你好吗？", ctx=ctx, memory=memory)

In [ ]

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

print(memory.get_all())

In [ ]

print(memory.get_all())

回到顶部

[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?")])]