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

# Bedrock 集成

> 使用 LangChain JavaScript 与 Bedrock 大语言模型集成。

<Warning>
  **您当前正在查阅的页面是关于将 Amazon Bedrock 模型用作文本补全模型的文档。Bedrock 上提供的许多流行模型是[聊天补全模型](/oss/javascript/langchain/models)。**

  您可能想查看[此页面](/oss/javascript/integrations/chat/bedrock/)。
</Warning>

> [Amazon Bedrock](https://aws.amazon.com/bedrock/) 是一项完全托管的服务，通过 API 提供来自领先 AI 初创公司和亚马逊的基础模型 (FMs)。您可以从广泛的 FMs 中选择最适合您用例的模型。

本文将帮助您开始使用 LangChain 的 Bedrock 补全模型 (LLMs)。有关 `Bedrock` 功能和配置选项的详细文档，请参阅 [API 参考](https://reference.langchain.com/javascript/langchain-community/llms/bedrock/Bedrock)。

## 概述

### 集成详情

| 类                                                                                                | 包                                                                            |  本地 | 可序列化 | [Python 支持](https://python.langchain.com/docs/integrations/llms/bedrock) |                                               下载量                                              |                                              版本                                              |
| :----------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------- | :-: | :--: | :----------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------: |
| [`Bedrock`](https://reference.langchain.com/javascript/langchain-community/llms/bedrock/Bedrock) | [`@langchain/community`](https://www.npmjs.com/package/@langchain/community) |  ❌  |   ✅  |                                     ✅                                    | ![NPM - 下载量](https://img.shields.io/npm/dm/@langchain/community?style=flat-square\&label=%20&) | ![NPM - 版本](https://img.shields.io/npm/v/@langchain/community?style=flat-square\&label=%20&) |

## 设置

要访问 Bedrock 模型，您需要创建一个 AWS 账户，获取 API 密钥，并安装 `@langchain/community` 集成以及几个对等依赖项。

### 凭证

前往 [aws.amazon.com](https://aws.amazon.com) 注册 AWS Bedrock 并生成 API 密钥。完成后，设置以下环境变量：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export BEDROCK_AWS_REGION="your-region-url"
export BEDROCK_AWS_ACCESS_KEY_ID="your-access-key-id"
export BEDROCK_AWS_SECRET_ACCESS_KEY="your-secret-access-key"
```

如果您希望自动追踪模型调用，还可以通过取消注释以下行来设置您的 [LangSmith](/langsmith/home) API 密钥：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"
```

### 安装

LangChain Bedrock 集成位于 `@langchain/community` 包中：

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

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

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @langchain/community @langchain/core
  ```
</CodeGroup>

并安装对等依赖项：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```
</CodeGroup>

您也可以在 Web 环境（如 Edge 函数或 Cloudflare Workers）中使用 Bedrock，方法是省略 `@aws-sdk/credential-provider-node` 依赖项并使用 `web` 入口点：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

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

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

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

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @langchain/community @langchain/core
  ```
</CodeGroup>

并安装对等依赖项：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```
</CodeGroup>

您也可以在 Web 环境（如 Edge 函数或 Cloudflare Workers）中使用 Bedrock，方法是省略 `@aws-sdk/credential-provider-node` 依赖项并使用 `web` 入口点：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

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

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

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

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @langchain/community @langchain/core
  ```
</CodeGroup>

并安装对等依赖项：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```
</CodeGroup>

您也可以在 Web 环境（如 Edge 函数或 Cloudflare Workers）中使用 Bedrock，方法是省略 `@aws-sdk/credential-provider-node` 依赖项并使用 `web` 入口点：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types
  ```
</CodeGroup>

## 实例化

现在我们可以实例化模型对象并生成聊天补全：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
// @lc-docs-hide-cell
// Deno 需要这些导入以及加载环境变量的方式。
// 我们不想在文档中暴露这些。
// 在此单元格下方，我们有一个包含 Node 代码的 TypeScript markdown 代码块。
import "@aws-sdk/credential-provider-node";
import "@smithy/protocol-http";
import "@aws-crypto/sha256-js";
import "@smithy/protocol-http";
import "@smithy/signature-v4";
import "@smithy/eventstream-codec";
import "@smithy/util-utf8";
import "@aws-sdk/types";
import { Bedrock } from "@langchain/community/llms/bedrock"
import { getEnvironmentVariable } from "@langchain/core/utils/env";

const llm = new Bedrock({
  model: "anthropic.claude-v2",
  region: "us-east-1",
  // endpointUrl: "custom.amazonaws.com",
  credentials: {
    accessKeyId: getEnvironmentVariable("BEDROCK_AWS_ACCESS_KEY_ID"),
    secretAccessKey: getEnvironmentVariable("BEDROCK_AWS_SECRET_ACCESS_KEY"),
  },
  temperature: 0,
  maxTokens: undefined,
  maxRetries: 2,
  // 其他参数...
})
```

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { Bedrock } from "@langchain/community/llms/bedrock"

const llm = new Bedrock({
  model: "anthropic.claude-v2",
  region: process.env.BEDROCK_AWS_REGION ?? "us-east-1",
  // endpointUrl: "custom.amazonaws.com",
  credentials: {
    accessKeyId: process.env.BEDROCK_AWS_ACCESS_KEY_ID,
    secretAccessKey: process.env.BEDROCK_AWS_SECRET_ACCESS_KEY,
  },
  temperature: 0,
  maxTokens: undefined,
  maxRetries: 2,
  // 其他参数...
})
```

## 调用

请注意，某些模型需要特定的提示技术。例如，Anthropic 的 Claude-v2 模型如果提示不以 `Human:` 开头，则会抛出错误。

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const inputText = "Human: Bedrock is an AI company that\nAssistant: "

const completion = await llm.invoke(inputText)
completion
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
" Here are a few key points about Bedrock AI:\n" +
  "\n" +
  "- Bedrock was founded in 2021 and is based in San Fran"... 116 more characters
```

***

## API 参考

有关所有 Bedrock 功能和配置的详细文档，请前往 [API 参考](https://reference.langchain.com/javascript/langchain-community/llms/bedrock/Bedrock)。

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\javascript\integrations\llms\bedrock.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>