Amazon Bedrock Embeddor

Embeddings

Overview

Generate embeddings using Amazon Bedrock's embedding models. Supports multiple model options and flexible AWS authentication methods.

Key Features

Multiple AWS auth methods
Custom endpoint support
Region flexibility
Profile-based config

Supported Models

amazon.titan-embed-text-v1
cohere.embed-english-v3
cohere.embed-multilingual-v3

Configuration

Required Parameters

modelIdBedrock model identifier

Authentication (One Required)

awsAccessKeyId &awsSecretAccessKey
credentialsProfileName

Optional Parameters

awsSessionTokenTemporary session token
regionNameAWS region (default: us-east-1)
endpointUrlCustom endpoint URL

Example Usage

const embeddor = new AmazonBedrockEmbeddor({
  modelId: "amazon.titan-embed-text-v1",
  awsAccessKeyId: "YOUR_ACCESS_KEY",
  awsSecretAccessKey: "YOUR_SECRET_KEY",
  regionName: "us-west-2"
});

// Generate embeddings
const result = await embeddor.embed({
  input: "Your text to embed"
});

// Using profile-based auth
const profileEmbeddor = new AmazonBedrockEmbeddor({
  modelId: "cohere.embed-english-v3",
  credentialsProfileName: "my-aws-profile",
  regionName: "us-east-1"
});

Best Practices

Use environment variables for credentials
Implement proper error handling
Monitor token usage and costs

Tips

Cache embeddings for repeated content
Batch requests when possible
Use appropriate model for your use case

Response Format

{
  "embeddings": number[],
  "metadata": {
    "model_id": string,
    "dimensions": number,
    "processing_time": number
  },
  "usage": {
    "input_tokens": number,
    "total_tokens": number
  },
  "status": {
    "success": boolean,
    "error": string | null
  }
}