Amazon Bedrock Runtime examples using SDK for JavaScript (v3)

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

/**
 * @typedef {Object} Content
 * @property {string} text
 *
 * @typedef {Object} Usage
 * @property {number} input_tokens
 * @property {number} output_tokens
 *
 * @typedef {Object} ResponseBody
 * @property {Content[]} content
 * @property {Usage} usage
 */

import { fileURLToPath } from "url";
import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

const AWS_REGION = "us-east-1";

const MODEL_ID = "anthropic.claude-3-haiku-20240307-v1:0";
const PROMPT = "Hi. In a short paragraph, explain what you can do.";

const hello = async () => {
  console.log("=".repeat(35));
  console.log("Welcome to the Amazon Bedrock demo!");
  console.log("=".repeat(35));

  console.log("Model: Anthropic Claude 3 Haiku");
  console.log(`Prompt: ${PROMPT}\n`);
  console.log("Invoking model...\n");

  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: AWS_REGION });

  // Prepare the payload for the model.
  const payload = {
    anthropic_version: "bedrock-2023-05-31",
    max_tokens: 1000,
    messages: [{ role: "user", content: [{ type: "text", text: PROMPT }] }],
  };

  // Invoke Claude with the payload and wait for the response.
  const apiResponse = await client.send(
    new InvokeModelCommand({
      contentType: "application/json",
      body: JSON.stringify(payload),
      modelId: MODEL_ID,
    }),
  );

  // Decode and return the response(s)
  const decodedResponseBody = new TextDecoder().decode(apiResponse.body);
  /** @type {ResponseBody} */
  const responseBody = JSON.parse(decodedResponseBody);
  const responses = responseBody.content;

  if (responses.length === 1) {
    console.log(`Response: ${responses[0].text}`);
  } else {
    console.log("Haiku returned multiple responses:");
    console.log(responses);
  }

  console.log(`\nNumber of input tokens:   ${responseBody.usage.input_tokens}`);
  console.log(`Number of output tokens: ${responseBody.usage.output_tokens}`);
};

if (process.argv[1] === fileURLToPath(import.meta.url)) {
  await hello();
}

Send a text message to AI21 Labs Jurassic-2, using Bedrock's Converse API.

// Use the Conversation API to send a text message to AI21 Labs Jurassic-2.

import {
  BedrockRuntimeClient,
  ConverseCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Jurassic-2 Mid.
const modelId = "ai21.j2-mid-v1";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the response text.
  const responseText = response.output.message.content[0].text;
  console.log(responseText);
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Use the Invoke Model API to send a text message.

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

import { fileURLToPath } from "url";

import { FoundationModels } from "../../config/foundation_models.js";
import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

/**
 * @typedef {Object} Data
 * @property {string} text
 *
 * @typedef {Object} Completion
 * @property {Data} data
 *
 * @typedef {Object} ResponseBody
 * @property {Completion[]} completions
 */

/**
 * Invokes an AI21 Labs Jurassic-2 model.
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "ai21.j2-mid-v1".
 */
export const invokeModel = async (prompt, modelId = "ai21.j2-mid-v1") => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Prepare the payload for the model.
  const payload = {
    prompt,
    maxTokens: 500,
    temperature: 0.5,
  };

  // Invoke the model with the payload and wait for the response.
  const command = new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  // Decode and return the response(s).
  const decodedResponseBody = new TextDecoder().decode(apiResponse.body);
  /** @type {ResponseBody} */
  const responseBody = JSON.parse(decodedResponseBody);
  return responseBody.completions[0].data.text;
};

// Invoke the function if this file was run directly.
if (process.argv[1] === fileURLToPath(import.meta.url)) {
  const prompt =
    'Complete the following in one sentence: "Once upon a time..."';
  const modelId = FoundationModels.JURASSIC2_MID.modelId;
  console.log(`Prompt: ${prompt}`);
  console.log(`Model ID: ${modelId}`);

  try {
    console.log("-".repeat(53));
    const response = await invokeModel(prompt, modelId);
    console.log(response);
  } catch (err) {
    console.log(err);
  }
}

Send a text message to Amazon Titan Text, using Bedrock's Converse API.

// Use the Conversation API to send a text message to Amazon Titan Text.

import {
  BedrockRuntimeClient,
  ConverseCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Titan Text Premier.
const modelId = "amazon.titan-text-premier-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the response text.
  const responseText = response.output.message.content[0].text;
  console.log(responseText);
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Send a text message to Amazon Titan Text, using Bedrock's Converse API and process the response stream in real-time.

// Use the Conversation API to send a text message to Amazon Titan Text.

import {
  BedrockRuntimeClient,
  ConverseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Titan Text Premier.
const modelId = "amazon.titan-text-premier-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseStreamCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the streamed response text in real-time.
  for await (const item of response.stream) {
    if (item.contentBlockDelta) {
      process.stdout.write(item.contentBlockDelta.delta?.text);
    }
  }
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Use the Invoke Model API to send a text message.

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

import { fileURLToPath } from "url";

import { FoundationModels } from "../../config/foundation_models.js";
import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

/**
 * @typedef {Object} ResponseBody
 * @property {Object[]} results
 */

/**
 * Invokes an Amazon Titan Text generation model.
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "amazon.titan-text-express-v1".
 */
export const invokeModel = async (
  prompt,
  modelId = "amazon.titan-text-express-v1",
) => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Prepare the payload for the model.
  const payload = {
    inputText: prompt,
    textGenerationConfig: {
      maxTokenCount: 4096,
      stopSequences: [],
      temperature: 0,
      topP: 1,
    },
  };

  // Invoke the model with the payload and wait for the response.
  const command = new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  // Decode and return the response.
  const decodedResponseBody = new TextDecoder().decode(apiResponse.body);
  /** @type {ResponseBody} */
  const responseBody = JSON.parse(decodedResponseBody);
  return responseBody.results[0].outputText;
};

// Invoke the function if this file was run directly.
if (process.argv[1] === fileURLToPath(import.meta.url)) {
  const prompt =
    'Complete the following in one sentence: "Once upon a time..."';
  const modelId = FoundationModels.TITAN_TEXT_G1_EXPRESS.modelId;
  console.log(`Prompt: ${prompt}`);
  console.log(`Model ID: ${modelId}`);

  try {
    console.log("-".repeat(53));
    const response = await invokeModel(prompt, modelId);
    console.log(response);
  } catch (err) {
    console.log(err);
  }
}

Send a text message to Anthropic Claude, using Bedrock's Converse API.

// Use the Conversation API to send a text message to Anthropic Claude.

import {
  BedrockRuntimeClient,
  ConverseCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Claude 3 Haiku.
const modelId = "anthropic.claude-3-haiku-20240307-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the response text.
  const responseText = response.output.message.content[0].text;
  console.log(responseText);
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Send a text message to Anthropic Claude, using Bedrock's Converse API and process the response stream in real-time.

// Use the Conversation API to send a text message to Anthropic Claude.

import {
  BedrockRuntimeClient,
  ConverseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Claude 3 Haiku.
const modelId = "anthropic.claude-3-haiku-20240307-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseStreamCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the streamed response text in real-time.
  for await (const item of response.stream) {
    if (item.contentBlockDelta) {
      process.stdout.write(item.contentBlockDelta.delta?.text);
    }
  }
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Use the Invoke Model API to send a text message.

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

import { fileURLToPath } from "url";

import { FoundationModels } from "../../config/foundation_models.js";
import {
  BedrockRuntimeClient,
  InvokeModelCommand,
  InvokeModelWithResponseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

/**
 * @typedef {Object} ResponseContent
 * @property {string} text
 *
 * @typedef {Object} MessagesResponseBody
 * @property {ResponseContent[]} content
 *
 * @typedef {Object} Delta
 * @property {string} text
 *
 * @typedef {Object} Message
 * @property {string} role
 *
 * @typedef {Object} Chunk
 * @property {string} type
 * @property {Delta} delta
 * @property {Message} message
 */

/**
 * Invokes Anthropic Claude 3 using the Messages API.
 *
 * To learn more about the Anthropic Messages API, go to:
 * https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "anthropic.claude-3-haiku-20240307-v1:0".
 */
export const invokeModel = async (
  prompt,
  modelId = "anthropic.claude-3-haiku-20240307-v1:0",
) => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Prepare the payload for the model.
  const payload = {
    anthropic_version: "bedrock-2023-05-31",
    max_tokens: 1000,
    messages: [
      {
        role: "user",
        content: [{ type: "text", text: prompt }],
      },
    ],
  };

  // Invoke Claude with the payload and wait for the response.
  const command = new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  // Decode and return the response(s)
  const decodedResponseBody = new TextDecoder().decode(apiResponse.body);
  /** @type {MessagesResponseBody} */
  const responseBody = JSON.parse(decodedResponseBody);
  return responseBody.content[0].text;
};

/**
 * Invokes Anthropic Claude 3 and processes the response stream.
 *
 * To learn more about the Anthropic Messages API, go to:
 * https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "anthropic.claude-3-haiku-20240307-v1:0".
 */
export const invokeModelWithResponseStream = async (
  prompt,
  modelId = "anthropic.claude-3-haiku-20240307-v1:0",
) => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Prepare the payload for the model.
  const payload = {
    anthropic_version: "bedrock-2023-05-31",
    max_tokens: 1000,
    messages: [
      {
        role: "user",
        content: [{ type: "text", text: prompt }],
      },
    ],
  };

  // Invoke Claude with the payload and wait for the API to respond.
  const command = new InvokeModelWithResponseStreamCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  let completeMessage = "";

  // Decode and process the response stream
  for await (const item of apiResponse.body) {
    /** @type Chunk */
    const chunk = JSON.parse(new TextDecoder().decode(item.chunk.bytes));
    const chunk_type = chunk.type;

    if (chunk_type === "content_block_delta") {
      const text = chunk.delta.text;
      completeMessage = completeMessage + text;
      process.stdout.write(text);
    }
  }

  // Return the final response
  return completeMessage;
};

// Invoke the function if this file was run directly.
if (process.argv[1] === fileURLToPath(import.meta.url)) {
  const prompt = 'Write a paragraph starting with: "Once upon a time..."';
  const modelId = FoundationModels.CLAUDE_3_HAIKU.modelId;
  console.log(`Prompt: ${prompt}`);
  console.log(`Model ID: ${modelId}`);

  try {
    console.log("-".repeat(53));
    const response = await invokeModel(prompt, modelId);
    console.log("\n" + "-".repeat(53));
    console.log("Final structured response:");
    console.log(response);
  } catch (err) {
    console.log(`\n${err}`);
  }
}

Use the Invoke Model API to send a text message and process the response stream in real-time.

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

import { fileURLToPath } from "url";

import { FoundationModels } from "../../config/foundation_models.js";
import {
  BedrockRuntimeClient,
  InvokeModelCommand,
  InvokeModelWithResponseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

/**
 * @typedef {Object} ResponseContent
 * @property {string} text
 *
 * @typedef {Object} MessagesResponseBody
 * @property {ResponseContent[]} content
 *
 * @typedef {Object} Delta
 * @property {string} text
 *
 * @typedef {Object} Message
 * @property {string} role
 *
 * @typedef {Object} Chunk
 * @property {string} type
 * @property {Delta} delta
 * @property {Message} message
 */

/**
 * Invokes Anthropic Claude 3 using the Messages API.
 *
 * To learn more about the Anthropic Messages API, go to:
 * https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "anthropic.claude-3-haiku-20240307-v1:0".
 */
export const invokeModel = async (
  prompt,
  modelId = "anthropic.claude-3-haiku-20240307-v1:0",
) => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Prepare the payload for the model.
  const payload = {
    anthropic_version: "bedrock-2023-05-31",
    max_tokens: 1000,
    messages: [
      {
        role: "user",
        content: [{ type: "text", text: prompt }],
      },
    ],
  };

  // Invoke Claude with the payload and wait for the response.
  const command = new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  // Decode and return the response(s)
  const decodedResponseBody = new TextDecoder().decode(apiResponse.body);
  /** @type {MessagesResponseBody} */
  const responseBody = JSON.parse(decodedResponseBody);
  return responseBody.content[0].text;
};

/**
 * Invokes Anthropic Claude 3 and processes the response stream.
 *
 * To learn more about the Anthropic Messages API, go to:
 * https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "anthropic.claude-3-haiku-20240307-v1:0".
 */
export const invokeModelWithResponseStream = async (
  prompt,
  modelId = "anthropic.claude-3-haiku-20240307-v1:0",
) => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Prepare the payload for the model.
  const payload = {
    anthropic_version: "bedrock-2023-05-31",
    max_tokens: 1000,
    messages: [
      {
        role: "user",
        content: [{ type: "text", text: prompt }],
      },
    ],
  };

  // Invoke Claude with the payload and wait for the API to respond.
  const command = new InvokeModelWithResponseStreamCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  let completeMessage = "";

  // Decode and process the response stream
  for await (const item of apiResponse.body) {
    /** @type Chunk */
    const chunk = JSON.parse(new TextDecoder().decode(item.chunk.bytes));
    const chunk_type = chunk.type;

    if (chunk_type === "content_block_delta") {
      const text = chunk.delta.text;
      completeMessage = completeMessage + text;
      process.stdout.write(text);
    }
  }

  // Return the final response
  return completeMessage;
};

// Invoke the function if this file was run directly.
if (process.argv[1] === fileURLToPath(import.meta.url)) {
  const prompt = 'Write a paragraph starting with: "Once upon a time..."';
  const modelId = FoundationModels.CLAUDE_3_HAIKU.modelId;
  console.log(`Prompt: ${prompt}`);
  console.log(`Model ID: ${modelId}`);

  try {
    console.log("-".repeat(53));
    const response = await invokeModel(prompt, modelId);
    console.log("\n" + "-".repeat(53));
    console.log("Final structured response:");
    console.log(response);
  } catch (err) {
    console.log(`\n${err}`);
  }
}

Send a text message to Cohere Command, using Bedrock's Converse API.

// Use the Conversation API to send a text message to Cohere Command.

import {
  BedrockRuntimeClient,
  ConverseCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Command R.
const modelId = "cohere.command-r-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the response text.
  const responseText = response.output.message.content[0].text;
  console.log(responseText);
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Send a text message to Cohere Command, using Bedrock's Converse API and process the response stream in real-time.

// Use the Conversation API to send a text message to Cohere Command.

import {
  BedrockRuntimeClient,
  ConverseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Command R.
const modelId = "cohere.command-r-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseStreamCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the streamed response text in real-time.
  for await (const item of response.stream) {
    if (item.contentBlockDelta) {
      process.stdout.write(item.contentBlockDelta.delta?.text);
    }
  }
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Send a text message to Meta Llama, using Bedrock's Converse API.

// Use the Conversation API to send a text message to Meta Llama.

import {
  BedrockRuntimeClient,
  ConverseCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Llama 3 8b Instruct.
const modelId = "meta.llama3-8b-instruct-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the response text.
  const responseText = response.output.message.content[0].text;
  console.log(responseText);
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Send a text message to Meta Llama, using Bedrock's Converse API and process the response stream in real-time.

// Use the Conversation API to send a text message to Meta Llama.

import {
  BedrockRuntimeClient,
  ConverseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Llama 3 8b Instruct.
const modelId = "meta.llama3-8b-instruct-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseStreamCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the streamed response text in real-time.
  for await (const item of response.stream) {
    if (item.contentBlockDelta) {
      process.stdout.write(item.contentBlockDelta.delta?.text);
    }
  }
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Use the Invoke Model API to send a text message.

// Send a prompt to Meta Llama 2 and print the response.

import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region of your choice.
const client = new BedrockRuntimeClient({ region: "us-west-2" });

// Set the model ID, e.g., Llama 2 Chat 13B.
const modelId = "meta.llama2-13b-chat-v1";

// Define the user message to send.
const userMessage =
  "Describe the purpose of a 'hello world' program in one sentence.";

// Embed the message in Llama 2's prompt format.
const prompt = `<s>[INST] ${userMessage} [/INST]`;

// Format the request payload using the model's native structure.
const request = {
  prompt,
  // Optional inference parameters:
  max_gen_len: 512,
  temperature: 0.5,
  top_p: 0.9,
};

// Encode and send the request.
const response = await client.send(
  new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(request),
    modelId,
  }),
);

// Decode the native response body.
/** @type {{ generation: string }} */
const nativeResponse = JSON.parse(new TextDecoder().decode(response.body));

// Extract and print the generated text.
const responseText = nativeResponse.generation;
console.log(responseText);

// Learn more about the Llama 2 prompt format at:
// https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-2

Use the Invoke Model API to send a text message.

// Send a prompt to Meta Llama 3 and print the response.

import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region of your choice.
const client = new BedrockRuntimeClient({ region: "us-west-2" });

// Set the model ID, e.g., Llama 3 8B Instruct.
const modelId = "meta.llama3-8b-instruct-v1:0";

// Define the user message to send.
const userMessage =
  "Describe the purpose of a 'hello world' program in one sentence.";

// Embed the message in Llama 3's prompt format.
const prompt = `
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
${userMessage}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
`;

// Format the request payload using the model's native structure.
const request = {
  prompt,
  // Optional inference parameters:
  max_gen_len: 512,
  temperature: 0.5,
  top_p: 0.9,
};

// Encode and send the request.
const response = await client.send(
  new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(request),
    modelId,
  }),
);

// Decode the native response body.
/** @type {{ generation: string }} */
const nativeResponse = JSON.parse(new TextDecoder().decode(response.body));

// Extract and print the generated text.
const responseText = nativeResponse.generation;
console.log(responseText);

// Learn more about the Llama 3 prompt format at:
// https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/#special-tokens-used-with-meta-llama-3

Use the Invoke Model API to send a text message and process the response stream in real-time.

// Send a prompt to Meta Llama 2 and print the response stream in real-time.

import {
  BedrockRuntimeClient,
  InvokeModelWithResponseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region of your choice.
const client = new BedrockRuntimeClient({ region: "us-west-2" });

// Set the model ID, e.g., Llama 2 Chat 13B.
const modelId = "meta.llama2-13b-chat-v1";

// Define the user message to send.
const userMessage =
  "Describe the purpose of a 'hello world' program in one sentence.";

// Embed the message in Llama 2's prompt format.
const prompt = `<s>[INST] ${userMessage} [/INST]`;

// Format the request payload using the model's native structure.
const request = {
  prompt,
  // Optional inference parameters:
  max_gen_len: 512,
  temperature: 0.5,
  top_p: 0.9,
};

// Encode and send the request.
const responseStream = await client.send(
  new InvokeModelWithResponseStreamCommand({
    contentType: "application/json",
    body: JSON.stringify(request),
    modelId,
  }),
);

// Extract and print the response stream in real-time.
for await (const event of responseStream.body) {
  /** @type {{ generation: string }} */
  const chunk = JSON.parse(new TextDecoder().decode(event.chunk.bytes));
  if (chunk.generation) {
    process.stdout.write(chunk.generation);
  }
}

// Learn more about the Llama 3 prompt format at:
// https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/#special-tokens-used-with-meta-llama-3

Use the Invoke Model API to send a text message and process the response stream in real-time.

// Send a prompt to Meta Llama 3 and print the response stream in real-time.

import {
  BedrockRuntimeClient,
  InvokeModelWithResponseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region of your choice.
const client = new BedrockRuntimeClient({ region: "us-west-2" });

// Set the model ID, e.g., Llama 3 8B Instruct.
const modelId = "meta.llama3-8b-instruct-v1:0";

// Define the user message to send.
const userMessage =
  "Describe the purpose of a 'hello world' program in one sentence.";

// Embed the message in Llama 3's prompt format.
const prompt = `
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
${userMessage}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
`;

// Format the request payload using the model's native structure.
const request = {
  prompt,
  // Optional inference parameters:
  max_gen_len: 512,
  temperature: 0.5,
  top_p: 0.9,
};

// Encode and send the request.
const responseStream = await client.send(
  new InvokeModelWithResponseStreamCommand({
    contentType: "application/json",
    body: JSON.stringify(request),
    modelId,
  }),
);

// Extract and print the response stream in real-time.
for await (const event of responseStream.body) {
  /** @type {{ generation: string }} */
  const chunk = JSON.parse(new TextDecoder().decode(event.chunk.bytes));
  if (chunk.generation) {
    process.stdout.write(chunk.generation);
  }
}

// Learn more about the Llama 3 prompt format at:
// https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/#special-tokens-used-with-meta-llama-3

Send a text message to Mistral, using Bedrock's Converse API.

// Use the Conversation API to send a text message to Mistral.

import {
  BedrockRuntimeClient,
  ConverseCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Mistral Large.
const modelId = "mistral.mistral-large-2402-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the response text.
  const responseText = response.output.message.content[0].text;
  console.log(responseText);
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Send a text message to Mistral, using Bedrock's Converse API and process the response stream in real-time.

// Use the Conversation API to send a text message to Mistral.

import {
  BedrockRuntimeClient,
  ConverseStreamCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region you want to use.
const client = new BedrockRuntimeClient({ region: "us-east-1" });

// Set the model ID, e.g., Mistral Large.
const modelId = "mistral.mistral-large-2402-v1:0";

// Start a conversation with the user message.
const userMessage =
  "Describe the purpose of a 'hello world' program in one line.";
const conversation = [
  {
    role: "user",
    content: [{ text: userMessage }],
  },
];

// Create a command with the model ID, the message, and a basic configuration.
const command = new ConverseStreamCommand({
  modelId,
  messages: conversation,
  inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 },
});

try {
  // Send the command to the model and wait for the response
  const response = await client.send(command);

  // Extract and print the streamed response text in real-time.
  for await (const item of response.stream) {
    if (item.contentBlockDelta) {
      process.stdout.write(item.contentBlockDelta.delta?.text);
    }
  }
} catch (err) {
  console.log(`ERROR: Can't invoke '${modelId}'. Reason: ${err}`);
  process.exit(1);
}

Use the Invoke Model API to send a text message.

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

import { fileURLToPath } from "url";

import { FoundationModels } from "../../config/foundation_models.js";
import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

/**
 * @typedef {Object} Output
 * @property {string} text
 *
 * @typedef {Object} ResponseBody
 * @property {Output[]} outputs
 */

/**
 * Invokes a Mistral 7B Instruct model.
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "mistral.mistral-7b-instruct-v0:2".
 */
export const invokeModel = async (
  prompt,
  modelId = "mistral.mistral-7b-instruct-v0:2",
) => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Mistral instruct models provide optimal results when embedding
  // the prompt into the following template:
  const instruction = `<s>[INST] ${prompt} [/INST]`;

  // Prepare the payload.
  const payload = {
    prompt: instruction,
    max_tokens: 500,
    temperature: 0.5,
  };

  // Invoke the model with the payload and wait for the response.
  const command = new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  // Decode and return the response.
  const decodedResponseBody = new TextDecoder().decode(apiResponse.body);
  /** @type {ResponseBody} */
  const responseBody = JSON.parse(decodedResponseBody);
  return responseBody.outputs[0].text;
};

// Invoke the function if this file was run directly.
if (process.argv[1] === fileURLToPath(import.meta.url)) {
  const prompt =
    'Complete the following in one sentence: "Once upon a time..."';
  const modelId = FoundationModels.MISTRAL_7B.modelId;
  console.log(`Prompt: ${prompt}`);
  console.log(`Model ID: ${modelId}`);

  try {
    console.log("-".repeat(53));
    const response = await invokeModel(prompt, modelId);
    console.log(response);
  } catch (err) {
    console.log(err);
  }
}

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

import { fileURLToPath } from "url";
import {
  Scenario,
  ScenarioAction,
  ScenarioInput,
  ScenarioOutput,
} from "@aws-doc-sdk-examples/lib/scenario/index.js";
import { FoundationModels } from "../config/foundation_models.js";

/**
 * @typedef {Object} ModelConfig
 * @property {Function} module
 * @property {Function} invoker
 * @property {string} modelId
 * @property {string} modelName
 */

const greeting = new ScenarioOutput(
  "greeting",
  "Welcome to the Amazon Bedrock Runtime client demo!",
  { header: true },
);

const selectModel = new ScenarioInput("model", "First, select a model:", {
  type: "select",
  choices: Object.values(FoundationModels).map((model) => ({
    name: model.modelName,
    value: model,
  })),
});

const enterPrompt = new ScenarioInput("prompt", "Now, enter your prompt:", {
  type: "input",
});

const printDetails = new ScenarioOutput(
  "print details",
  /**
   * @param {{ model: ModelConfig, prompt: string }} c
   */
  (c) => console.log(`Invoking ${c.model.modelName} with '${c.prompt}'...`),
  { slow: false },
);

const invokeModel = new ScenarioAction(
  "invoke model",
  /**
   * @param {{ model: ModelConfig, prompt: string, response: string }} c
   */
  async (c) => {
    const modelModule = await c.model.module();
    const invoker = c.model.invoker(modelModule);
    c.response = await invoker(c.prompt, c.model.modelId);
  },
);

const printResponse = new ScenarioOutput(
  "print response",
  /**
   * @param {{ response: string }} c
   */
  (c) => c.response,
  { slow: false },
);

const scenario = new Scenario("Amazon Bedrock Runtime Demo", [
  greeting,
  selectModel,
  enterPrompt,
  printDetails,
  invokeModel,
  printResponse,
]);

if (process.argv[1] === fileURLToPath(import.meta.url)) {
  scenario.run();
}