使用 MongoDB Atlas 的长期记忆

使用 MongoDBStore 和 MongoDB Atlas 持久化智能体长期记忆。

长期记忆允许您的智能体跨不同的对话和会话存储和回忆信息。本指南展示了如何使用MongoDB Atlas作为持久化存储后端。

MongoDB将记忆存储为集合中的文档。通过Atlas向量搜索索引，相同的存储可以运行对存储记忆的语义搜索。

如需深入了解记忆类型和写入记忆的策略，请参阅记忆概念指南。

设置

安装

MongoDBStore与MongoDB检查点器一同打包：

npm

npm install @langchain/langgraph-checkpoint-mongodb

凭证

设置您的Atlas连接字符串：

export MONGODB_ATLAS_URI="your-atlas-connection-string"

如果您希望自动跟踪您的模型调用，设置您的LangSmith API密钥：

export LANGSMITH_API_KEY="your-api-key"
export LANGSMITH_TRACING="true"

使用

创建一个 MongoDBStore 并使用 fromConnString（等待 Promise）将其传递给 createAgent。fromConnString 连接客户端并调用 start() 以确保索引存在。从包根目录导入 MongoDBStore；没有 /store 子路径导出。

import { createAgent } from "langchain";
import { MongoDBStore } from "@langchain/langgraph-checkpoint-mongodb";

const MONGODB_ATLAS_URI = process.env.MONGODB_ATLAS_URI;
if (!MONGODB_ATLAS_URI) {
  throw new Error("MONGODB_ATLAS_URI is required");
}

const store = await MongoDBStore.fromConnString(MONGODB_ATLAS_URI);

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-6",
  tools: [],
  store,
});

记忆存储

LangGraph 将记忆存储为按 namespace 和 key 组织的 JSON 文档。命名空间通常包含用户或组织 ID 以保持记忆的作用域。

下面的示例配置了向量索引，以便 store.search 可以运行语义查询。传递一个嵌入实例和 indexConfig。如果你使用 OpenAIEmbeddings（或替换为另一个嵌入类），请安装 @langchain/openai：

import { OpenAIEmbeddings } from "@langchain/openai";
import { MongoDBStore } from "@langchain/langgraph-checkpoint-mongodb";

const MONGODB_ATLAS_URI = process.env.MONGODB_ATLAS_URI;
if (!MONGODB_ATLAS_URI) {
  throw new Error("MONGODB_ATLAS_URI is required");
}

const store = await MongoDBStore.fromConnString(MONGODB_ATLAS_URI, {
  embeddings: new OpenAIEmbeddings({ model: "text-embedding-3-small" }),
  indexConfig: {
    name: "store_vector_index",
    dims: 1536,
    similarityFunction: "cosine",
  },
});

const userId = "my-user";
const applicationContext = "chitchat";
const namespace = [userId, applicationContext];

await store.put(namespace, "a-memory", {
  rules: [
    "User likes short, direct language",
    "User only speaks English and TypeScript",
  ],
  "my-key": "my-value",
});

const item = await store.get(namespace, "a-memory");
const items = await store.search(namespace, {
  filter: { "my-key": "my-value" },
  query: "language preferences",
});

有关存储操作的更多信息，请参阅 存储 指南。

工具中读取长期记忆

工具可以使用 runtime 参数从存储中读取，LangGraph 会自动注入该参数：

import * as z from "zod";
import { createAgent, tool, type ToolRuntime } from "langchain";
import { MongoDBStore } from "@langchain/langgraph-checkpoint-mongodb";

const MONGODB_ATLAS_URI = process.env.MONGODB_ATLAS_URI;
if (!MONGODB_ATLAS_URI) {
  throw new Error("MONGODB_ATLAS_URI is required");
}

const store = await MongoDBStore.fromConnString(MONGODB_ATLAS_URI);

const contextSchema = z.object({ userId: z.string() });

await store.put(["users"], "user_123", {
  name: "John Smith",
  language: "English",
});

const getUserInfo = tool(
  async (_, runtime: ToolRuntime<unknown, z.infer<typeof contextSchema>>) => {
    const userId = runtime.context.userId;
    if (!userId) throw new Error("userId is required");
    const userInfo = await runtime.store?.get(["users"], userId);
    return userInfo?.value ? JSON.stringify(userInfo.value) : "Unknown user";
  },
  {
    name: "getUserInfo",
    description: "Look up user info by userId from the store.",
    schema: z.object({}),
  },
);

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-6",
  tools: [getUserInfo],
  contextSchema,
  store,
});

await agent.invoke(
  { messages: [{ role: "user", content: "look up user information" }] },
  { context: { userId: "user_123" } },
);

工具中写入长期记忆

工具还可以使用 runtime.store.put 向存储写入，以持久化跨线程的数据：

import * as z from "zod";
import { tool, createAgent, type ToolRuntime } from "langchain";
import { MongoDBStore } from "@langchain/langgraph-checkpoint-mongodb";

const MONGODB_ATLAS_URI = process.env.MONGODB_ATLAS_URI;
if (!MONGODB_ATLAS_URI) {
  throw new Error("MONGODB_ATLAS_URI is required");
}

const store = await MongoDBStore.fromConnString(MONGODB_ATLAS_URI);

const contextSchema = z.object({ userId: z.string() });

const UserInfo = z.object({ name: z.string() });

const saveUserInfo = tool(
  async (
    userInfo: z.infer<typeof UserInfo>,
    runtime: ToolRuntime<unknown, z.infer<typeof contextSchema>>,
  ) => {
    const userId = runtime.context.userId;
    if (!userId) throw new Error("userId is required");
    await runtime.store?.put(["users"], userId, userInfo);
    return "Successfully saved user info.";
  },
  { name: "save_user_info", description: "Save user info", schema: UserInfo },
);

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-6",
  tools: [saveUserInfo],
  contextSchema,
  store,
});

await agent.invoke(
  { messages: [{ role: "user", content: "My name is John Smith" }] },
  { context: { userId: "user_123" } },
);

const result = await store.get(["users"], "user_123");
console.log(result?.value);

参考文档

• 长期记忆
• 存储
• 存储集成
• 使用 MongoDB Atlas 的短期记忆

---

官方原文：src/oss/javascript/integrations/memory/mongodb-long-term-memory.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。