Skip to main content

如何添加消息历史

前提条件

本指南假定您熟悉以下概念：

note

本指南之前介绍了 RunnableWithMessageHistory 抽象。您可以在 v0.2 文档 中查看该版本的指南。

LangGraph 实现相较于 RunnableWithMessageHistory 提供了许多优势，包括持久化应用程序状态的任意组件的能力（而不仅仅是消息）。

在构建聊天机器人时，将对话状态传递到链中并从中取出至关重要。LangGraph 实现了一个内置的持久化层，允许链状态自动在内存中或外部后端（如 SQLite、Postgres 或 Redis）中持久化。详细信息可以在 LangGraph 持久化文档中找到。

在本指南中，我们演示了如何通过将任意 LangChain 可运行对象包装在一个最小的 LangGraph 应用程序中来添加持久化功能。这使我们能够持久化消息历史和链状态的其他元素，简化多轮应用程序的开发。它还支持多个线程，使单个应用程序可以分别与多个用户进行交互。

准备工作​

yarn add @langchain/core @langchain/langgraph

我们还设置一个聊天模型，用于以下示例。

Pick your chat model:

Install dependencies

tip

See this section for general instructions on installing integration packages.

yarn add @langchain/groq

Add environment variables

GROQ_API_KEY=your-api-key

Instantiate the model

import { ChatGroq } from "@langchain/groq";

const llm = new ChatGroq({
  model: "llama-3.3-70b-versatile",
  temperature: 0
});

示例：消息输入​

为聊天模型添加记忆提供了一个简单的示例。聊天模型接受消息列表作为输入，并输出一条消息。LangGraph 包含一个内置的 MessagesState，我们可以为此目的使用它。

下面，我们： 1. 将图状态定义为消息列表； 2. 向图中添加一个调用聊天模型的节点； 3. 使用内存检查点存储运行之间的消息来编译该图。

LangGraph 应用程序的输出是其状态。

import {
  START,
  END,
  MessagesAnnotation,
  StateGraph,
  MemorySaver,
} from "@langchain/langgraph";

// Define the function that calls the model
const callModel = async (state: typeof MessagesAnnotation.State) => {
  const response = await llm.invoke(state.messages);
  // Update message history with response:
  return { messages: response };
};

// Define a new graph
const workflow = new StateGraph(MessagesAnnotation)
  // Define the (single) node in the graph
  .addNode("model", callModel)
  .addEdge(START, "model")
  .addEdge("model", END);

// Add memory
const memory = new MemorySaver();
const app = workflow.compile({ checkpointer: memory });

运行应用程序时，我们会传入一个指定thread_id的配置对象。该 ID 用于区分对话线程（例如，不同用户之间的对话）。

import { v4 as uuidv4 } from "uuid";

const config = { configurable: { thread_id: uuidv4() } };

然后我们可以调用该应用程序：

const input = [
  {
    role: "user",
    content: "Hi! I'm Bob.",
  },
];
const output = await app.invoke({ messages: input }, config);
// The output contains all messages in the state.
// This will log the last message in the conversation.
console.log(output.messages[output.messages.length - 1]);
AIMessage {
  "id": "chatcmpl-ABTqCeKnMQmG9IH8dNF5vPjsgXtcM",
  "content": "Hi Bob! How can I assist you today?",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 10,
      "promptTokens": 12,
      "totalTokens": 22
    },
    "finish_reason": "stop",
    "system_fingerprint": "fp_e375328146"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 12,
    "output_tokens": 10,
    "total_tokens": 22
  }
}
const input2 = [
  {
    role: "user",
    content: "What's my name?",
  },
];
const output2 = await app.invoke({ messages: input2 }, config);
console.log(output2.messages[output2.messages.length - 1]);
AIMessage {
  "id": "chatcmpl-ABTqD5jrJXeKCpvoIDp47fvgw2OPn",
  "content": "Your name is Bob. How can I help you today, Bob?",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 14,
      "promptTokens": 34,
      "totalTokens": 48
    },
    "finish_reason": "stop",
    "system_fingerprint": "fp_e375328146"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 34,
    "output_tokens": 14,
    "total_tokens": 48
  }
}

请注意，不同线程的状态是相互分离的。如果我们使用新的 thread_id 向线程发出相同的查询，模型会表示它不知道答案：

const config2 = { configurable: { thread_id: uuidv4() } };
const input3 = [
  {
    role: "user",
    content: "What's my name?",
  },
];
const output3 = await app.invoke({ messages: input3 }, config2);
console.log(output3.messages[output3.messages.length - 1]);
AIMessage {
  "id": "chatcmpl-ABTqDkctxwmXjeGOZpK6Km8jdCqdl",
  "content": "I'm sorry, but I don't have access to personal information about users. How can I assist you today?",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 21,
      "promptTokens": 11,
      "totalTokens": 32
    },
    "finish_reason": "stop",
    "system_fingerprint": "fp_52a7f40b0b"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 11,
    "output_tokens": 21,
    "total_tokens": 32
  }
}

示例：对象输入​

LangChain 可运行对象通常通过单个对象参数中不同的键接受多个输入。一个常见的例子是带有多个参数的提示模板。

之前我们的可运行对象是一个聊天模型，这里我们将提示模板和聊天模型串联在一起。

import {
  ChatPromptTemplate,
  MessagesPlaceholder,
} from "@langchain/core/prompts";

const prompt = ChatPromptTemplate.fromMessages([
  ["system", "Answer in {language}."],
  new MessagesPlaceholder("messages"),
]);

const runnable = prompt.pipe(llm);

在此场景中，我们定义图状态包含这些参数（除了消息历史）。

请注意以下状态中的定义： - 对 messages 列表的更新会追加消息； - 对 language 字符串的更新会覆盖该字符串。

import {
  START,
  END,
  StateGraph,
  MemorySaver,
  MessagesAnnotation,
  Annotation,
} from "@langchain/langgraph";

// Define the State
const GraphAnnotation = Annotation.Root({
  language: Annotation<string>(),
  // Spread `MessagesAnnotation` into the state to add the `messages` field.
  ...MessagesAnnotation.spec,
});

// Define the function that calls the model
const callModel2 = async (state: typeof GraphAnnotation.State) => {
  const response = await runnable.invoke(state);
  // Update message history with response:
  return { messages: [response] };
};

const workflow2 = new StateGraph(GraphAnnotation)
  .addNode("model", callModel2)
  .addEdge(START, "model")
  .addEdge("model", END);

const app2 = workflow2.compile({ checkpointer: new MemorySaver() });
const config3 = { configurable: { thread_id: uuidv4() } };
const input4 = {
  messages: [
    {
      role: "user",
      content: "What's my name?",
    },
  ],
  language: "Spanish",
};
const output4 = await app2.invoke(input4, config3);
console.log(output4.messages[output4.messages.length - 1]);
AIMessage {
  "id": "chatcmpl-ABTqFnCASRB5UhZ7XAbbf5T0Bva4U",
  "content": "Lo siento, pero no tengo suficiente información para saber tu nombre. ¿Cómo te llamas?",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 19,
      "promptTokens": 19,
      "totalTokens": 38
    },
    "finish_reason": "stop",
    "system_fingerprint": "fp_e375328146"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 19,
    "output_tokens": 19,
    "total_tokens": 38
  }
}

管理消息历史记录​

消息历史记录（以及应用程序状态的其他元素）可以通过 .getState 访问：

const state = (await app2.getState(config3)).values;

console.log(`Language: ${state.language}`);
console.log(state.messages);
Language: Spanish
[
  HumanMessage {
    "content": "What's my name?",
    "additional_kwargs": {},
    "response_metadata": {}
  },
  AIMessage {
    "id": "chatcmpl-ABTqFnCASRB5UhZ7XAbbf5T0Bva4U",
    "content": "Lo siento, pero no tengo suficiente información para saber tu nombre. ¿Cómo te llamas?",
    "additional_kwargs": {},
    "response_metadata": {
      "tokenUsage": {
        "completionTokens": 19,
        "promptTokens": 19,
        "totalTokens": 38
      },
      "finish_reason": "stop",
      "system_fingerprint": "fp_e375328146"
    },
    "tool_calls": [],
    "invalid_tool_calls": []
  }
]

我们还可以通过 .updateState 来更新状态。例如，我们可以手动添加一条新消息：

const _ = await app2.updateState(config3, {
  messages: [{ role: "user", content: "test" }],
});
const state2 = (await app2.getState(config3)).values;

console.log(`Language: ${state2.language}`);
console.log(state2.messages);
Language: Spanish
[
  HumanMessage {
    "content": "What's my name?",
    "additional_kwargs": {},
    "response_metadata": {}
  },
  AIMessage {
    "id": "chatcmpl-ABTqFnCASRB5UhZ7XAbbf5T0Bva4U",
    "content": "Lo siento, pero no tengo suficiente información para saber tu nombre. ¿Cómo te llamas?",
    "additional_kwargs": {},
    "response_metadata": {
      "tokenUsage": {
        "completionTokens": 19,
        "promptTokens": 19,
        "totalTokens": 38
      },
      "finish_reason": "stop",
      "system_fingerprint": "fp_e375328146"
    },
    "tool_calls": [],
    "invalid_tool_calls": []
  },
  HumanMessage {
    "content": "test",
    "additional_kwargs": {},
    "response_metadata": {}
  }
]

有关管理状态（包括删除消息）的详细信息，请参阅 LangGraph 文档：

Was this page helpful?


You can also leave detailed feedback on GitHub.