> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-docs-zh.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 使用 MongoDB Atlas 的短期记忆

> 使用 MongoDBSaver 和 MongoDB Atlas 持久化智能体短期记忆。

[短期记忆](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/short-term-memory.md) 允许您的智能体在单个线程或会话中记住之前的交互。本指南演示如何使用 [MongoDB Atlas](https://www.mongodb.com/docs/atlas/) 作为持久化检查点后端。

MongoDB 将会话状态存储为集合中的文档，因此线程可以在进程重启和部署时恢复。

> [!TIP]
>
> 需要跨会话记忆信息？使用 [使用 MongoDB Atlas 的长期记忆](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/memory/mongodb-long-term-memory.md) 来存储和检索跨不同线程和会话的数据。

## 设置

### 安装

```bash npm theme={null}
npm install @langchain/langgraph-checkpoint-mongodb mongodb
```

```bash yarn theme={null}
yarn add @langchain/langgraph-checkpoint-mongodb mongodb
```

```bash pnpm theme={null}
pnpm add @langchain/langgraph-checkpoint-mongodb mongodb
```

### 凭据

设置你的Atlas连接字符串：

```bash theme={null}
export MONGODB_ATLAS_URI="your-atlas-connection-string"
```

若需自动追踪模型调用，请设置[LangSmith](https://docs.langchain.com/langsmith/home) API密钥：

```bash theme={null}
export LANGSMITH_API_KEY="your-api-key"
export LANGSMITH_TRACING="true"
```

## 使用方法

创建一个`MongoClient`，构造`MongoDBSaver`，并调用`setup()`一次以创建索引。没有`MongoDBSaver.fromConnString`辅助工具。

```typescript theme={null}
import { createAgent, tool } from "langchain";
import { MongoDBSaver } from "@langchain/langgraph-checkpoint-mongodb";
import { MongoClient } from "mongodb";
import * as z from "zod";

const getUserInfo = tool(() => "No user profile on file.", {
  name: "get_user_info",
  description: "Look up information about the current user.",
  schema: z.object({}),
});

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

const client = new MongoClient(MONGODB_ATLAS_URI);
const checkpointer = new MongoDBSaver({ client });
await checkpointer.setup();

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

const threadConfig = { configurable: { thread_id: "1" } };
let result = await agent.invoke(
  { messages: [{ role: "user", content: "Hi! My name is Bob." }] },
  threadConfig,
);
console.log(result.messages.at(-1)?.content);

result = await agent.invoke(
  { messages: [{ role: "user", content: "What's my name?" }] },
  threadConfig,
);
console.log(result.messages.at(-1)?.content);

await client.close();
```

## 下一步骤

* 在[短期记忆](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/short-term-memory.md)指南中自定义智能体状态、截断或总结历史记录，并从工具中访问记忆。需将相同的`MongoDBSaver`传递给`checkpointer`。
* 关于跨线程持久化，请参考[使用MongoDB Atlas实现长期记忆](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/memory/mongodb-long-term-memory.md)。
* 查看包含其他后端支持的[检查点库列表](https://langchain-docs-zh.mintlify.site/langchain/oss/langgraph/checkpointers.md#检查点库)。

***

> 官方原文：[src/oss/javascript/integrations/memory/mongodb-short-term-memory.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/javascript/integrations/memory/mongodb-short-term-memory.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.