Skip to content
Learni
View all tutorials
Cloud & IA

How to Integrate AWS Bedrock in a Node.js App in 2026

18 minINTERMEDIATE
AWSNode.jsBedrock
Lire en français

Introduction

AWS Bedrock provides access to foundation models like Claude 3 or Llama 3 without managing infrastructure. This tutorial shows how to integrate it into a Node.js application for text generation and streaming responses. You'll learn best practices for configuration, authentication, and error handling for production deployments.

Prerequisites

  • Node.js 20+
  • AWS account with Bedrock access
  • Basic TypeScript knowledge
  • AWS CLI configured

Installing Dependencies

terminal
npm init -y
npm install @aws-sdk/client-bedrock-runtime dotenv

Installs the official AWS SDK for Bedrock and dotenv for securely managing environment variables.

Bedrock Client Configuration

src/bedrockClient.ts
import { BedrockRuntimeClient } from '@aws-sdk/client-bedrock-runtime';
import * as dotenv from 'dotenv';

dotenv.config();

export const bedrockClient = new BedrockRuntimeClient({
  region: process.env.AWS_REGION || 'us-east-1',
  credentials: {
    accessKeyId: process.env.AWS_ACCESS_KEY_ID!,
    secretAccessKey: process.env.AWS_SECRET_ACCESS_KEY!,
  },
});

Initializes the Bedrock client with AWS credentials. Use environment variables to avoid hardcoding keys.

Simple Model Invocation

src/invokeModel.ts
import { InvokeModelCommand } from '@aws-sdk/client-bedrock-runtime';
import { bedrockClient } from './bedrockClient';

export async function invokeClaude(prompt: string) {
  const command = new InvokeModelCommand({
    modelId: 'anthropic.claude-3-sonnet-20240229-v1:0',
    contentType: 'application/json',
    accept: 'application/json',
    body: JSON.stringify({
      anthropic_version: 'bedrock-2023-05-31',
      max_tokens: 1000,
      messages: [{ role: 'user', content: prompt }],
    }),
  });
  const response = await bedrockClient.send(command);
  return JSON.parse(new TextDecoder().decode(response.body));
}

Sends a request to Claude 3 Sonnet. The request body must follow Anthropic's specific format.

Streaming Response Handling

src/streamResponse.ts
import { InvokeModelWithResponseStreamCommand } from '@aws-sdk/client-bedrock-runtime';
import { bedrockClient } from './bedrockClient';

export async function streamClaude(prompt: string) {
  const command = new InvokeModelWithResponseStreamCommand({
    modelId: 'anthropic.claude-3-sonnet-20240229-v1:0',
    contentType: 'application/json',
    body: JSON.stringify({
      anthropic_version: 'bedrock-2023-05-31',
      max_tokens: 1000,
      messages: [{ role: 'user', content: prompt }],
    }),
  });
  const response = await bedrockClient.send(command);
  for await (const event of response.body!) {
    if (event.chunk) {
      const chunk = JSON.parse(new TextDecoder().decode(event.chunk.bytes));
      if (chunk.delta?.text) process.stdout.write(chunk.delta.text);
    }
  }
}

Uses streaming to display tokens as they arrive, improving the user experience.

Error Handling

src/errorHandler.ts
import { BedrockRuntimeServiceException } from '@aws-sdk/client-bedrock-runtime';

export function handleBedrockError(error: unknown) {
  if (error instanceof BedrockRuntimeServiceException) {
    console.error(`Bedrock error: ${error.name} - ${error.message}`);
    if (error.name === 'ValidationException') {
      throw new Error('Invalid prompt or incorrect parameters');
    }
  }
  throw error;
}

Catches Bedrock-specific exceptions to provide clear, actionable error messages.

Best Practices

  • Always validate and sanitize prompts before sending
  • Use models via aliases to simplify updates
  • Implement retry with exponential backoff
  • Monitor costs with CloudWatch
  • Store credentials via IAM roles instead of static keys

Common Mistakes to Avoid

  • Forgetting to request model access in the Bedrock console
  • Using an incorrect body format for the chosen model
  • Not handling token limits and timeouts
  • Ignoring regional differences for certain models

Further Reading

Explore our advanced generative AI and AWS courses: https://learni-group.com/formations

How to Integrate AWS Bedrock with Node.js in 2026 | Learni