Skip to content

如何为您的图添加跨线程持久性

前提条件

本指南假设您熟悉以下内容:

上一个指南中,您学习了如何在单一线程上跨多个交互持久化图状态。LangGraph 还允许您在**多个线程**之间持久化数据。例如,您可以将有关用户(他们的姓名或偏好)的信息存储在共享内存中,并在新的会话线程中重用它们。

在本指南中,我们将展示如何构建和使用一个使用Store接口实现共享内存的图。

注意

本指南中使用的 Store API 支持是在 LangGraph v0.2.32 中添加的。

本指南中使用的 Store API 的 索引查询 参数支持是在 LangGraph v0.2.54 中添加的。

设置

首先,让我们安装所需的包并设置我们的 API 密钥

%%capture --no-stderr
%pip install -U langchain_openai langgraph
import getpass
import os


def _set_env(var: str):
    if not os.environ.get(var):
        os.environ[var] = getpass.getpass(f"{var}: ")


_set_env("ANTHROPIC_API_KEY")
_set_env("OPENAI_API_KEY")

设置 LangSmith 用于 LangGraph 开发

注册 LangSmith 可以快速发现并解决您的 LangGraph 项目中的问题,提高项目性能。LangSmith 允许您使用跟踪数据来调试、测试和监控使用 LangGraph 构建的 LLM 应用程序——此处了解更多入门信息。

定义存储

在这个示例中,我们将创建一个图,该图能够检索用户偏好信息。我们将通过定义一个 InMemoryStore 来实现,这是一个可以存储内存数据并查询这些数据的对象。然后,我们在编译图时传递存储对象。这使得图中的每个节点都可以访问存储:当你定义节点函数时,可以定义 store 关键字参数,LangGraph 将自动传递你编译图时使用的存储对象。

使用 Store 接口存储对象时,你需要定义两部分内容:

  • 对象的命名空间,一个元组(类似于目录)
  • 对象的键(类似于文件名)

在我们的示例中,我们将使用 ("memories", <user_id>) 作为命名空间,并使用随机 UUID 作为每个新记忆的键。

重要的是,为了确定用户,我们将通过节点函数的配置关键字参数传递 user_id

让我们先定义一个已经填充了一些关于用户的记忆的 InMemoryStore

from langgraph.store.memory import InMemoryStore
from langchain_openai import OpenAIEmbeddings

in_memory_store = InMemoryStore(
    index={
        "embed": OpenAIEmbeddings(model="text-embedding-3-small"),
        "dims": 1536,
    }
)

API Reference: OpenAIEmbeddings

创建图表

import uuid
from typing import Annotated
from typing_extensions import TypedDict

from langchain_anthropic import ChatAnthropic
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, MessagesState, START
from langgraph.checkpoint.memory import MemorySaver
from langgraph.store.base import BaseStore


model = ChatAnthropic(model="claude-3-5-sonnet-20240620")


# NOTE: we're passing the Store param to the node --
# this is the Store we compile the graph with
def call_model(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
    user_id = config["configurable"]["user_id"]
    namespace = ("memories", user_id)
    memories = store.search(namespace, query=str(state["messages"][-1].content))
    info = "\n".join([d.value["data"] for d in memories])
    system_msg = f"You are a helpful assistant talking to the user. User info: {info}"

    # Store new memories if the user asks the model to remember
    last_message = state["messages"][-1]
    if "remember" in last_message.content.lower():
        memory = "User name is Bob"
        store.put(namespace, str(uuid.uuid4()), {"data": memory})

    response = model.invoke(
        [{"role": "system", "content": system_msg}] + state["messages"]
    )
    return {"messages": response}


builder = StateGraph(MessagesState)
builder.add_node("call_model", call_model)
builder.add_edge(START, "call_model")

# NOTE: we're passing the store object here when compiling the graph
graph = builder.compile(checkpointer=MemorySaver(), store=in_memory_store)
# If you're using LangGraph Cloud or LangGraph Studio, you don't need to pass the store or checkpointer when compiling the graph, since it's done automatically.

API Reference: ChatAnthropic | RunnableConfig | StateGraph | START | MemorySaver

注意

如果您使用的是LangGraph Cloud或LangGraph Studio,则在编译图时不需要传递store,因为这是自动完成的。

运行图!

现在让我们在配置中指定一个用户ID,并告诉模型我们的名字:

config = {"configurable": {"thread_id": "1", "user_id": "1"}}
input_message = {"role": "user", "content": "Hi! Remember: my name is Bob"}
for chunk in graph.stream({"messages": [input_message]}, config, stream_mode="values"):
    chunk["messages"][-1].pretty_print()
================================ Human Message =================================

Hi! Remember: my name is Bob
================================== Ai Message ==================================

Hello Bob! It's nice to meet you. I'll remember that your name is Bob. How can I assist you today?

config = {"configurable": {"thread_id": "2", "user_id": "1"}}
input_message = {"role": "user", "content": "what is my name?"}
for chunk in graph.stream({"messages": [input_message]}, config, stream_mode="values"):
    chunk["messages"][-1].pretty_print()
================================ Human Message =================================

what is my name?
================================== Ai Message ==================================

Your name is Bob.
我们现在可以检查内存中的存储,并验证确实为用户保存了记忆:

for memory in in_memory_store.search(("memories", "1")):
    print(memory.value)
{'data': 'User name is Bob'}
现在让我们为另一个用户运行图,以验证关于第一个用户的记忆是自包含的:

config = {"configurable": {"thread_id": "3", "user_id": "2"}}
input_message = {"role": "user", "content": "what is my name?"}
for chunk in graph.stream({"messages": [input_message]}, config, stream_mode="values"):
    chunk["messages"][-1].pretty_print()
================================ Human Message =================================

what is my name?
================================== Ai Message ==================================

I apologize, but I don't have any information about your name. As an AI assistant, I don't have access to personal information about users unless it has been specifically shared in our conversation. If you'd like, you can tell me your name and I'll be happy to use it in our discussion.

Comments