Invoke Meta Llama on Amazon Bedrock using Bedrock's Converse API with a response stream

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

// Use the Converse API to send a text message to Meta Llama
// and print the response stream.

using System;
using System.Collections.Generic;
using System.Linq;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

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

// Define the user message.
var userMessage = "Describe the purpose of a 'hello world' program in one line.";

// Create a request with the model ID, the user message, and an inference configuration.
var request = new ConverseStreamRequest
{
    ModelId = modelId,
    Messages = new List<Message>
    {
        new Message
        {
            Role = ConversationRole.User,
            Content = new List<ContentBlock> { new ContentBlock { Text = userMessage } }
        }
    },
    InferenceConfig = new InferenceConfiguration()
    {
        MaxTokens = 512,
        Temperature = 0.5F,
        TopP = 0.9F
    }
};

try
{
    // Send the request to the Bedrock Runtime and wait for the result.
    var response = await client.ConverseStreamAsync(request);

    // Extract and print the streamed response text in real-time.
    foreach (var chunk in response.Stream.AsEnumerable())
    {
        if (chunk is ContentBlockDeltaEvent)
        {
            Console.Write((chunk as ContentBlockDeltaEvent).Delta.Text);
        }
    }
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

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

// Use the Converse API to send a text message to Meta Llama
// and print the response stream.

import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeAsyncClient;
import software.amazon.awssdk.services.bedrockruntime.model.ContentBlock;
import software.amazon.awssdk.services.bedrockruntime.model.ConversationRole;
import software.amazon.awssdk.services.bedrockruntime.model.ConverseStreamResponseHandler;
import software.amazon.awssdk.services.bedrockruntime.model.Message;

import java.util.concurrent.ExecutionException;

public class ConverseStream {

    public static void main(String[] args) {

        // Create a Bedrock Runtime client in the AWS Region you want to use.
        // Replace the DefaultCredentialsProvider with your preferred credentials provider.
        var client = BedrockRuntimeAsyncClient.builder()
                .credentialsProvider(DefaultCredentialsProvider.create())
                .region(Region.US_EAST_1)
                .build();

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

        // Create the input text and embed it in a message object with the user role.
        var inputText = "Describe the purpose of a 'hello world' program in one line.";
        var message = Message.builder()
                .content(ContentBlock.fromText(inputText))
                .role(ConversationRole.USER)
                .build();

        // Create a handler to extract and print the response text in real-time.
        var responseStreamHandler = ConverseStreamResponseHandler.builder()
                .subscriber(ConverseStreamResponseHandler.Visitor.builder()
                        .onContentBlockDelta(chunk -> {
                            String responseText = chunk.delta().text();
                            System.out.print(responseText);
                        }).build()
                ).onError(err ->
                        System.err.printf("Can't invoke '%s': %s", modelId, err.getMessage())
                ).build();

        try {
            // Send the message with a basic inference configuration and attach the handler.
            client.converseStream(request -> request
                    .modelId(modelId)
                    .messages(message)
                    .inferenceConfig(config -> config
                            .maxTokens(512)
                            .temperature(0.5F)
                            .topP(0.9F)
                    ), responseStreamHandler).get();

        } catch (ExecutionException | InterruptedException e) {
            System.err.printf("Can't invoke '%s': %s", modelId, e.getCause().getMessage());
        }
    }
}

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);
}

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
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

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

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)