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

# Google Places 集成

> 使用 LangChain JavaScript 集成 Google Places 工具。

Google Places 工具允许您的代理利用 Google Places API，从关于 Google Places 上列出的地点的文本中查找地址、电话号码、网站等信息。

## 设置

您需要从 [Google 这里](https://developers.google.com/maps/documentation/places/web-service/overview)获取 API 密钥，并[启用新的 Places API](https://console.cloud.google.com/apis/library/places.googleapis.com)。然后，将您的 API 密钥设置为 `process.env.GOOGLE_PLACES_API_KEY`，或将其作为 `apiKey` 构造函数参数传入。

## 用法

<Tip>
  请参阅[此部分了解安装 LangChain 包的一般说明](/oss/javascript/langchain/install)。
</Tip>

```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm install @langchain/openai @langchain/community @langchain/core
```

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { GooglePlacesAPI } from "@langchain/community/tools/google_places";
import { OpenAI } from "@langchain/openai";
import { initializeAgentExecutorWithOptions } from "@langchain/classic/agents";

export async function run() {
  const model = new OpenAI({
    temperature: 0,
  });

  const tools = [new GooglePlacesAPI()];

  const executor = await initializeAgentExecutorWithOptions(tools, model, {
    agentType: "zero-shot-react-description",
    verbose: true,
  });

  const res = await executor.invoke({
    input: "Where is the University of Toronto - Scarborough? ",
  });

  console.log(res.output);
}
```

## 相关内容

* 工具[概念指南](/oss/javascript/langchain/tools)
* 工具[操作指南](/oss/javascript/langchain/tools)

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档](/use-these-docs)通过 MCP 连接到 Claude、VSCode 等，以获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/javascript/integrations/tools/google_places.mdx)或[提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>