SDK for Java 2.x를 사용한 Amazon Bedrock 런타임 예제

Java 기반 모델(FM) 플레이그라운드는 Amazon Bedrock을 Java와 함께 사용하는 방법을 보여주는 스프링 부트 샘플 애플리케이션입니다. 이 예제는 Java 개발자가 Amazon Bedrock을 사용하여 생성형 AI 지원 애플리케이션을 구축하는 방법을 보여줍니다. 다음 네 가지 플레이그라운드를 사용하여 Amazon Bedrock 기반 모델을 테스트하고 상호 작용할 수 있습니다.

또한 이 예제에서는 액세스할 수 있는 기본 모델을 해당 특성과 함께 나열하고 표시합니다. 소스 코드 및 배포 지침은 GitHub의 프로젝트를 참조하세요.

Bedrock의 Converse AI21를 사용하여 Word Labs Jurassic-2로 텍스트 메시지를 보냅니다API.

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

import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
import software.amazon.awssdk.services.bedrockruntime.model.ContentBlock;
import software.amazon.awssdk.services.bedrockruntime.model.ConversationRole;
import software.amazon.awssdk.services.bedrockruntime.model.ConverseResponse;
import software.amazon.awssdk.services.bedrockruntime.model.Message;

public class Converse {

    public static String converse() {

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

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

        // 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();

        try {
            // Send the message with a basic inference configuration.
            ConverseResponse response = client.converse(request -> request
                    .modelId(modelId)
                    .messages(message)
                    .inferenceConfig(config -> config
                            .maxTokens(512)
                            .temperature(0.5F)
                            .topP(0.9F)));

            // Retrieve the generated text from Bedrock's response object.
            var responseText = response.output().message().content().get(0).text();
            System.out.println(responseText);

            return responseText;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        converse();
    }
}

Bedrock의 Converse API를 비동기 Java 클라이언트와 함께 사용하여 AI21 Labs Jurassic-2로 텍스트 메시지를 보냅니다.

// Use the Converse API to send a text message to AI21 Labs Jurassic-2
// with the async Java client.

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.Message;

import java.util.concurrent.CompletableFuture;
import java.util.concurrent.ExecutionException;

public class ConverseAsync {

    public static String converseAsync() {

        // 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., Jurassic-2 Mid.
        var modelId = "ai21.j2-mid-v1";

        // 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();

        // Send the message with a basic inference configuration.
        var request = client.converse(params -> params
                .modelId(modelId)
                .messages(message)
                .inferenceConfig(config -> config
                        .maxTokens(512)
                        .temperature(0.5F)
                        .topP(0.9F))
        );

        // Prepare a future object to handle the asynchronous response.
        CompletableFuture<String> future = new CompletableFuture<>();

        // Handle the response or error using the future object.
        request.whenComplete((response, error) -> {
            if (error == null) {
                // Extract the generated text from Bedrock's response object.
                String responseText = response.output().message().content().get(0).text();
                future.complete(responseText);
            } else {
                future.completeExceptionally(error);
            }
        });

        try {
            // Wait for the future object to complete and retrieve the generated text.
            String responseText = future.get();
            System.out.println(responseText);

            return responseText;

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

    public static void main(String[] args) {
        converseAsync();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보냅니다.

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

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class InvokeModel {

    public static String invokeModel() {

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

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

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-jurassic2.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{prompt}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/completions/0/data/text").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

Amazon Titan Image Generator로 이미지를 생성합니다.

// Create an image with the Amazon Titan Image Generator.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

import java.math.BigInteger;
import java.security.SecureRandom;

import static com.example.bedrockruntime.libs.ImageTools.displayImage;

public class InvokeModel {

    public static String invokeModel() {

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

        // Set the model ID, e.g., Titan Image G1.
        var modelId = "amazon.titan-image-generator-v1";

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-titan-image.html
        var nativeRequestTemplate = """
                {
                    "taskType": "TEXT_IMAGE",
                    "textToImageParams": { "text": "{{prompt}}" },
                    "imageGenerationConfig": { "seed": {{seed}} }
                }""";

        // Define the prompt for the image generation.
        var prompt = "A stylized picture of a cute old steampunk robot";

        // Get a random 31-bit seed for the image generation (max. 2,147,483,647).
        var seed = new BigInteger(31, new SecureRandom());

        // Embed the prompt and seed in the model's native request payload.
        var nativeRequest = nativeRequestTemplate
                .replace("{{prompt}}", prompt)
                .replace("{{seed}}", seed.toString());

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated image data from the model's response.
            var base64ImageData = new JSONPointer("/images/0").queryFrom(responseBody).toString();

            return base64ImageData;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        System.out.println("Generating image. This may take a few seconds...");

        String base64ImageData = invokeModel();

        displayImage(base64ImageData);
    }
}

Bedrock의 Converse API를 사용하여 Amazon Titan Text로 문자 메시지를 보냅니다.

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

import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
import software.amazon.awssdk.services.bedrockruntime.model.ContentBlock;
import software.amazon.awssdk.services.bedrockruntime.model.ConversationRole;
import software.amazon.awssdk.services.bedrockruntime.model.ConverseResponse;
import software.amazon.awssdk.services.bedrockruntime.model.Message;

public class Converse {

    public static String converse() {

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

        // Set the model ID, e.g., Titan Text Premier.
        var modelId = "amazon.titan-text-premier-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();


        try {
            // Send the message with a basic inference configuration.
            ConverseResponse response = client.converse(request -> request
                    .modelId(modelId)
                    .messages(message)
                    .inferenceConfig(config -> config
                            .maxTokens(512)
                            .temperature(0.5F)
                            .topP(0.9F)));

            // Retrieve the generated text from Bedrock's response object.
            var responseText = response.output().message().content().get(0).text();
            System.out.println(responseText);

            return responseText;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        converse();
    }
}

비동기 Java 클라이언트와 함께 Bedrock의 Converse API를 사용하여 Amazon Titan Text로 텍스트 메시지를 보냅니다.

// Use the Converse API to send a text message to Amazon Titan Text
// with the async Java client.

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.Message;

import java.util.concurrent.CompletableFuture;
import java.util.concurrent.ExecutionException;

public class ConverseAsync {

    public static String converseAsync() {

        // 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., Titan Text Premier.
        var modelId = "amazon.titan-text-premier-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();

        // Send the message with a basic inference configuration.
        var request = client.converse(params -> params
                .modelId(modelId)
                .messages(message)
                .inferenceConfig(config -> config
                        .maxTokens(512)
                        .temperature(0.5F)
                        .topP(0.9F))
        );

        // Prepare a future object to handle the asynchronous response.
        CompletableFuture<String> future = new CompletableFuture<>();

        // Handle the response or error using the future object.
        request.whenComplete((response, error) -> {
            if (error == null) {
                // Extract the generated text from Bedrock's response object.
                String responseText = response.output().message().content().get(0).text();
                future.complete(responseText);
            } else {
                future.completeExceptionally(error);
            }
        });

        try {
            // Wait for the future object to complete and retrieve the generated text.
            String responseText = future.get();
            System.out.println(responseText);

            return responseText;

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

    public static void main(String[] args) {
        converseAsync();
    }
}

Bedrock의 Converse API를 사용하여 Amazon Titan Text로 문자 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the Converse API to send a text message to Amazon Titan Text
// 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., Titan Text Premier.
        var modelId = "amazon.titan-text-premier-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());
        }
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보냅니다.

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

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class InvokeModel {

    public static String invokeModel() {

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

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

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-titan-text.html
        var nativeRequestTemplate = "{ \"inputText\": \"{{prompt}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/results/0/outputText").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the native inference API to send a text message to Amazon Titan Text
// and print the response stream.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeAsyncClient;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamRequest;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler;

import java.util.concurrent.ExecutionException;

import static software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler.Visitor;

public class InvokeModelWithResponseStream {

    public static String invokeModelWithResponseStream() throws ExecutionException, InterruptedException {

        // 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., Titan Text Premier.
        var modelId = "amazon.titan-text-premier-v1:0";

        // The InvokeModelWithResponseStream API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-titan-text.html
        var nativeRequestTemplate = "{ \"inputText\": \"{{prompt}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        // Create a request with the model ID and the model's native request payload.
        var request = InvokeModelWithResponseStreamRequest.builder()
                .body(SdkBytes.fromUtf8String(nativeRequest))
                .modelId(modelId)
                .build();

        // Prepare a buffer to accumulate the generated response text.
        var completeResponseTextBuffer = new StringBuilder();

        // Prepare a handler to extract, accumulate, and print the response text in real-time.
        var responseStreamHandler = InvokeModelWithResponseStreamResponseHandler.builder()
                .subscriber(Visitor.builder().onChunk(chunk -> {
                    // Extract and print the text from the model's native response.
                    var response = new JSONObject(chunk.bytes().asUtf8String());
                    var text = new JSONPointer("/outputText").queryFrom(response);
                    System.out.print(text);

                    // Append the text to the response text buffer.
                    completeResponseTextBuffer.append(text);
                }).build()).build();

        try {
            // Send the request and wait for the handler to process the response.
            client.invokeModelWithResponseStream(request, responseStreamHandler).get();

            // Return the complete response text.
            return completeResponseTextBuffer.toString();

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

    public static void main(String[] args) throws ExecutionException, InterruptedException {
        invokeModelWithResponseStream();
    }
}

Titan Text Embeddings V2를 사용하여 첫 번째 임베딩을 생성합니다.

// Generate and print an embedding with Amazon Titan Text Embeddings.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class InvokeModel {

    public static String invokeModel() {

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

        // Set the model ID, e.g., Titan Text Embeddings V2.
        var modelId = "amazon.titan-embed-text-v2:0";

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-titan-embed-text.html
        var nativeRequestTemplate = "{ \"inputText\": \"{{inputText}}\" }";

        // The text to convert into an embedding.
        var inputText = "Please recommend books with a theme similar to the movie 'Inception'.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{inputText}}", inputText);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/embedding").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

Titan Text Embeddings V2를 호출하여 차원 수와 정규화를 구성합니다.

    /**
     * Invoke Amazon Titan Text Embeddings V2 with additional inference parameters.
     *
     * @param inputText  - The text to convert to an embedding.
     * @param dimensions - The number of dimensions the output embeddings should have.
     *                   Values accepted by the model: 256, 512, 1024.
     * @param normalize  - A flag indicating whether or not to normalize the output embeddings.
     * @return The {@link JSONObject} representing the model's response.
     */
    public static JSONObject invokeModel(String inputText, int dimensions, boolean normalize) {

        // Create a Bedrock Runtime client in the AWS Region of your choice.
        var client = BedrockRuntimeClient.builder()
                .region(Region.US_WEST_2)
                .build();

        // Set the model ID, e.g., Titan Embed Text v2.0.
        var modelId = "amazon.titan-embed-text-v2:0";

        // Create the request for the model.
        var nativeRequest = """
                {
                    "inputText": "%s",
                    "dimensions": %d,
                    "normalize": %b
                }
                """.formatted(inputText, dimensions, normalize);

        // Encode and send the request.
        var response = client.invokeModel(request -> {
            request.body(SdkBytes.fromUtf8String(nativeRequest));
            request.modelId(modelId);
        });

        // Decode the model's response.
        var modelResponse = new JSONObject(response.body().asUtf8String());

        // Extract and print the generated embedding and the input text token count.
        var embedding = modelResponse.getJSONArray("embedding");
        var inputTokenCount = modelResponse.getBigInteger("inputTextTokenCount");
        System.out.println("Embedding: " + embedding);
        System.out.println("\nInput token count: " + inputTokenCount);

        // Return the model's native response.
        return modelResponse;
    }

Bedrock의 Converse API를 사용하여 Anthropic Claude에 문자 메시지를 보냅니다.

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

import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
import software.amazon.awssdk.services.bedrockruntime.model.ContentBlock;
import software.amazon.awssdk.services.bedrockruntime.model.ConversationRole;
import software.amazon.awssdk.services.bedrockruntime.model.ConverseResponse;
import software.amazon.awssdk.services.bedrockruntime.model.Message;

public class Converse {

    public static String converse() {

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

        // Set the model ID, e.g., Claude 3 Haiku.
        var modelId = "anthropic.claude-3-haiku-20240307-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();


        try {
            // Send the message with a basic inference configuration.
            ConverseResponse response = client.converse(request -> request
                    .modelId(modelId)
                    .messages(message)
                    .inferenceConfig(config -> config
                            .maxTokens(512)
                            .temperature(0.5F)
                            .topP(0.9F)));

            // Retrieve the generated text from Bedrock's response object.
            var responseText = response.output().message().content().get(0).text();
            System.out.println(responseText);

            return responseText;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        converse();
    }
}

Bedrock의 Converse API를 비동기 Java 클라이언트와 함께 사용하여 Anthropic Claude에 문자 메시지를 보냅니다.

// Use the Converse API to send a text message to Anthropic Claude
// with the async Java client.

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.Message;

import java.util.concurrent.CompletableFuture;
import java.util.concurrent.ExecutionException;

public class ConverseAsync {

    public static String converseAsync() {

        // 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., Claude 3 Haiku.
        var modelId = "anthropic.claude-3-haiku-20240307-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();

        // Send the message with a basic inference configuration.
        var request = client.converse(params -> params
                .modelId(modelId)
                .messages(message)
                .inferenceConfig(config -> config
                        .maxTokens(512)
                        .temperature(0.5F)
                        .topP(0.9F))
        );

        // Prepare a future object to handle the asynchronous response.
        CompletableFuture<String> future = new CompletableFuture<>();

        // Handle the response or error using the future object.
        request.whenComplete((response, error) -> {
            if (error == null) {
                // Extract the generated text from Bedrock's response object.
                String responseText = response.output().message().content().get(0).text();
                future.complete(responseText);
            } else {
                future.completeExceptionally(error);
            }
        });

        try {
            // Wait for the future object to complete and retrieve the generated text.
            String responseText = future.get();
            System.out.println(responseText);

            return responseText;

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

    public static void main(String[] args) {
        converseAsync();
    }
}

Bedrock의 Converse API를 사용하여 Anthropic Claude에 문자 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the Converse API to send a text message to Anthropic Claude
// 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., Claude 3 Haiku.
        var modelId = "anthropic.claude-3-haiku-20240307-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());
        }
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보냅니다.

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

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class InvokeModel {

    public static String invokeModel() {

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

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

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
        var nativeRequestTemplate = """
                {
                    "anthropic_version": "bedrock-2023-05-31",
                    "max_tokens": 512,
                    "temperature": 0.5,
                    "messages": [{
                        "role": "user",
                        "content": "{{prompt}}"
                    }]
                }""";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/content/0/text").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the native inference API to send a text message to Anthropic Claude
// and print the response stream.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeAsyncClient;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamRequest;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler;

import java.util.Objects;
import java.util.concurrent.ExecutionException;

import static software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler.Visitor;

public class InvokeModelWithResponseStream {

    public static String invokeModelWithResponseStream() throws ExecutionException, InterruptedException {

        // 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., Claude 3 Haiku.
        var modelId = "anthropic.claude-3-haiku-20240307-v1:0";

        // The InvokeModelWithResponseStream API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
        var nativeRequestTemplate = """
                {
                    "anthropic_version": "bedrock-2023-05-31",
                    "max_tokens": 512,
                    "temperature": 0.5,
                    "messages": [{
                        "role": "user",
                        "content": "{{prompt}}"
                    }]
                }""";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        // Create a request with the model ID and the model's native request payload.
        var request = InvokeModelWithResponseStreamRequest.builder()
                .body(SdkBytes.fromUtf8String(nativeRequest))
                .modelId(modelId)
                .build();

        // Prepare a buffer to accumulate the generated response text.
        var completeResponseTextBuffer = new StringBuilder();

        // Prepare a handler to extract, accumulate, and print the response text in real-time.
        var responseStreamHandler = InvokeModelWithResponseStreamResponseHandler.builder()
                .subscriber(Visitor.builder().onChunk(chunk -> {
                    var response = new JSONObject(chunk.bytes().asUtf8String());

                    // Extract and print the text from the content blocks.
                    if (Objects.equals(response.getString("type"), "content_block_delta")) {
                        var text = new JSONPointer("/delta/text").queryFrom(response);
                        System.out.print(text);

                        // Append the text to the response text buffer.
                        completeResponseTextBuffer.append(text);
                    }
                }).build()).build();

        try {
            // Send the request and wait for the handler to process the response.
            client.invokeModelWithResponseStream(request, responseStreamHandler).get();

            // Return the complete response text.
            return completeResponseTextBuffer.toString();

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

    public static void main(String[] args) throws ExecutionException, InterruptedException {
        invokeModelWithResponseStream();
    }
}

Bedrock의 Converse API를 사용하여 Cohere Command로 텍스트 메시지를 보냅니다.

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

import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
import software.amazon.awssdk.services.bedrockruntime.model.ContentBlock;
import software.amazon.awssdk.services.bedrockruntime.model.ConversationRole;
import software.amazon.awssdk.services.bedrockruntime.model.ConverseResponse;
import software.amazon.awssdk.services.bedrockruntime.model.Message;

public class Converse {

    public static String converse() {

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

        // Set the model ID, e.g., Command R.
        var modelId = "cohere.command-r-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();


        try {
            // Send the message with a basic inference configuration.
            ConverseResponse response = client.converse(request -> request
                    .modelId(modelId)
                    .messages(message)
                    .inferenceConfig(config -> config
                            .maxTokens(512)
                            .temperature(0.5F)
                            .topP(0.9F)));

            // Retrieve the generated text from Bedrock's response object.
            var responseText = response.output().message().content().get(0).text();
            System.out.println(responseText);

            return responseText;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        converse();
    }
}

Bedrock의 Converse API를 비동기 Java 클라이언트와 함께 사용하여 Cohere Command에 텍스트 메시지를 보냅니다.

// Use the Converse API to send a text message to Cohere Command
// with the async Java client.

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.Message;

import java.util.concurrent.CompletableFuture;
import java.util.concurrent.ExecutionException;

public class ConverseAsync {

    public static String converseAsync() {

        // 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., Command R.
        var modelId = "cohere.command-r-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();

        // Send the message with a basic inference configuration.
        var request = client.converse(params -> params
                .modelId(modelId)
                .messages(message)
                .inferenceConfig(config -> config
                        .maxTokens(512)
                        .temperature(0.5F)
                        .topP(0.9F))
        );

        // Prepare a future object to handle the asynchronous response.
        CompletableFuture<String> future = new CompletableFuture<>();

        // Handle the response or error using the future object.
        request.whenComplete((response, error) -> {
            if (error == null) {
                // Extract the generated text from Bedrock's response object.
                String responseText = response.output().message().content().get(0).text();
                future.complete(responseText);
            } else {
                future.completeExceptionally(error);
            }
        });

        try {
            // Wait for the future object to complete and retrieve the generated text.
            String responseText = future.get();
            System.out.println(responseText);

            return responseText;

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

    public static void main(String[] args) {
        converseAsync();
    }
}

Bedrock의 Converse API를 사용하여 Cohere Command에 문자 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the Converse API to send a text message to Cohere Command
// 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., Command R.
        var modelId = "cohere.command-r-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());
        }
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보냅니다.

// Use the native inference API to send a text message to Cohere Command R.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class Command_R_InvokeModel {

    public static String invokeModel() {

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

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

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command-r-plus.html
        var nativeRequestTemplate = "{ \"message\": \"{{prompt}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/text").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보냅니다.

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

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class Command_InvokeModel {

    public static String invokeModel() {

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

        // Set the model ID, e.g., Command Light.
        var modelId = "cohere.command-light-text-v14";

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{prompt}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/generations/0/text").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the native inference API to send a text message to Cohere Command R
// and print the response stream.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeAsyncClient;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamRequest;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler;

import java.util.concurrent.ExecutionException;

import static software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler.Visitor;

public class Command_R_InvokeModelWithResponseStream {

    public static String invokeModelWithResponseStream() throws ExecutionException, InterruptedException {

        // 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., Command R.
        var modelId = "cohere.command-r-v1:0";

        // The InvokeModelWithResponseStream API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command-r-plus.html
        var nativeRequestTemplate = "{ \"message\": \"{{prompt}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        // Create a request with the model ID and the model's native request payload.
        var request = InvokeModelWithResponseStreamRequest.builder()
                .body(SdkBytes.fromUtf8String(nativeRequest))
                .modelId(modelId)
                .build();

        // Prepare a buffer to accumulate the generated response text.
        var completeResponseTextBuffer = new StringBuilder();

        // Prepare a handler to extract, accumulate, and print the response text in real-time.
        var responseStreamHandler = InvokeModelWithResponseStreamResponseHandler.builder()
                .subscriber(Visitor.builder().onChunk(chunk -> {
                    // Extract and print the text from the model's native response.
                    var response = new JSONObject(chunk.bytes().asUtf8String());
                    var text = new JSONPointer("/text").queryFrom(response);
                    System.out.print(text);

                    // Append the text to the response text buffer.
                    completeResponseTextBuffer.append(text);
                }).build()).build();

        try {
            // Send the request and wait for the handler to process the response.
            client.invokeModelWithResponseStream(request, responseStreamHandler).get();

            // Return the complete response text.
            return completeResponseTextBuffer.toString();

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

    public static void main(String[] args) throws ExecutionException, InterruptedException {
        invokeModelWithResponseStream();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the native inference API to send a text message to Cohere Command
// and print the response stream.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeAsyncClient;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamRequest;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler;

import java.util.concurrent.ExecutionException;

import static software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler.Visitor;

public class Command_InvokeModelWithResponseStream {

    public static String invokeModelWithResponseStream() throws ExecutionException, InterruptedException {

        // 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., Command Light.
        var modelId = "cohere.command-light-text-v14";

        // The InvokeModelWithResponseStream API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{prompt}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in the model's native request payload.
        String nativeRequest = nativeRequestTemplate.replace("{{prompt}}", prompt);

        // Create a request with the model ID and the model's native request payload.
        var request = InvokeModelWithResponseStreamRequest.builder()
                .body(SdkBytes.fromUtf8String(nativeRequest))
                .modelId(modelId)
                .build();

        // Prepare a buffer to accumulate the generated response text.
        var completeResponseTextBuffer = new StringBuilder();

        // Prepare a handler to extract, accumulate, and print the response text in real-time.
        var responseStreamHandler = InvokeModelWithResponseStreamResponseHandler.builder()
                .subscriber(Visitor.builder().onChunk(chunk -> {
                    // Extract and print the text from the model's native response.
                    var response = new JSONObject(chunk.bytes().asUtf8String());
                    var text = new JSONPointer("/generations/0/text").queryFrom(response);
                    System.out.print(text);

                    // Append the text to the response text buffer.
                    completeResponseTextBuffer.append(text);
                }).build()).build();

        try {
            // Send the request and wait for the handler to process the response.
            client.invokeModelWithResponseStream(request, responseStreamHandler).get();

            // Return the complete response text.
            return completeResponseTextBuffer.toString();

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

    public static void main(String[] args) throws ExecutionException, InterruptedException {
        invokeModelWithResponseStream();
    }
}

Bedrock의 Converse API를 사용하여 Meta Llama에 문자 메시지를 보냅니다.

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

import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
import software.amazon.awssdk.services.bedrockruntime.model.ContentBlock;
import software.amazon.awssdk.services.bedrockruntime.model.ConversationRole;
import software.amazon.awssdk.services.bedrockruntime.model.ConverseResponse;
import software.amazon.awssdk.services.bedrockruntime.model.Message;

public class Converse {

    public static String converse() {

        // Create a Bedrock Runtime client in the AWS Region you want to use.
        // Replace the DefaultCredentialsProvider with your preferred credentials provider.
        var client = BedrockRuntimeClient.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();


        try {
            // Send the message with a basic inference configuration.
            ConverseResponse response = client.converse(request -> request
                    .modelId(modelId)
                    .messages(message)
                    .inferenceConfig(config -> config
                            .maxTokens(512)
                            .temperature(0.5F)
                            .topP(0.9F)));

            // Retrieve the generated text from Bedrock's response object.
            var responseText = response.output().message().content().get(0).text();
            System.out.println(responseText);

            return responseText;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        converse();
    }
}

비동기 Java 클라이언트와 함께 Bedrock의 Converse API를 사용하여 Meta Llama에 텍스트 메시지를 보냅니다.

// Use the Converse API to send a text message to Meta Llama
// with the async Java client.

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.Message;

import java.util.concurrent.CompletableFuture;
import java.util.concurrent.ExecutionException;

public class ConverseAsync {

    public static String converseAsync() {

        // 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();

        // Send the message with a basic inference configuration.
        var request = client.converse(params -> params
                .modelId(modelId)
                .messages(message)
                .inferenceConfig(config -> config
                        .maxTokens(512)
                        .temperature(0.5F)
                        .topP(0.9F))
        );

        // Prepare a future object to handle the asynchronous response.
        CompletableFuture<String> future = new CompletableFuture<>();

        // Handle the response or error using the future object.
        request.whenComplete((response, error) -> {
            if (error == null) {
                // Extract the generated text from Bedrock's response object.
                String responseText = response.output().message().content().get(0).text();
                future.complete(responseText);
            } else {
                future.completeExceptionally(error);
            }
        });

        try {
            // Wait for the future object to complete and retrieve the generated text.
            String responseText = future.get();
            System.out.println(responseText);

            return responseText;

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

    public static void main(String[] args) {
        converseAsync();
    }
}

Bedrock의 Converse API를 사용하여 Meta Llama에 문자 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// 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());
        }
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보냅니다.

// Use the native inference API to send a text message to Meta Llama 3.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class Llama3_InvokeModel {

    public static String invokeModel() {

        // Create a Bedrock Runtime client in the AWS Region you want to use.
        // Replace the DefaultCredentialsProvider with your preferred credentials provider.
        var client = BedrockRuntimeClient.builder()
                .credentialsProvider(DefaultCredentialsProvider.create())
                .region(Region.US_WEST_2)
                .build();

        // Set the model ID, e.g., Llama 3 70b Instruct.
        var modelId = "meta.llama3-70b-instruct-v1:0";

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{instruction}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in Llama 3's instruction format.
        var instruction = (
                "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\\n" +
                "{{prompt}} <|eot_id|>\\n" +
                "<|start_header_id|>assistant<|end_header_id|>\\n"
        ).replace("{{prompt}}", prompt);

        // Embed the instruction in the the native request payload.
        var nativeRequest = nativeRequestTemplate.replace("{{instruction}}", instruction);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/generation").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the native inference API to send a text message to Meta Llama 3
// and print the response stream.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeAsyncClient;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamRequest;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler;

import java.util.concurrent.ExecutionException;

import static software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler.Visitor;

public class Llama3_InvokeModelWithResponseStream {

    public static String invokeModelWithResponseStream() {

        // 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_WEST_2)
                .build();

        // Set the model ID, e.g., Llama 3 70b Instruct.
        var modelId = "meta.llama3-70b-instruct-v1:0";

        // The InvokeModelWithResponseStream API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{instruction}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in Llama 3's instruction format.
        var instruction = (
                "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\\n" +
                "{{prompt}} <|eot_id|>\\n" +
                "<|start_header_id|>assistant<|end_header_id|>\\n"
        ).replace("{{prompt}}", prompt);

        // Embed the instruction in the the native request payload.
        var nativeRequest = nativeRequestTemplate.replace("{{instruction}}", instruction);

        // Create a request with the model ID and the model's native request payload.
        var request = InvokeModelWithResponseStreamRequest.builder()
                .body(SdkBytes.fromUtf8String(nativeRequest))
                .modelId(modelId)
                .build();

        // Prepare a buffer to accumulate the generated response text.
        var completeResponseTextBuffer = new StringBuilder();

        // Prepare a handler to extract, accumulate, and print the response text in real-time.
        var responseStreamHandler = InvokeModelWithResponseStreamResponseHandler.builder()
                .subscriber(Visitor.builder().onChunk(chunk -> {
                    // Extract and print the text from the model's native response.
                    var response = new JSONObject(chunk.bytes().asUtf8String());
                    var text = new JSONPointer("/generation").queryFrom(response);
                    System.out.print(text);

                    // Append the text to the response text buffer.
                    completeResponseTextBuffer.append(text);
                }).build()).build();

        try {
            // Send the request and wait for the handler to process the response.
            client.invokeModelWithResponseStream(request, responseStreamHandler).get();

            // Return the complete response text.
            return completeResponseTextBuffer.toString();

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

    public static void main(String[] args) throws ExecutionException, InterruptedException {
        invokeModelWithResponseStream();
    }
}

Bedrock의 Converse API를 사용하여 Mistral에 문자 메시지를 보냅니다.

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

import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
import software.amazon.awssdk.services.bedrockruntime.model.ContentBlock;
import software.amazon.awssdk.services.bedrockruntime.model.ConversationRole;
import software.amazon.awssdk.services.bedrockruntime.model.ConverseResponse;
import software.amazon.awssdk.services.bedrockruntime.model.Message;

public class Converse {

    public static String converse() {

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

        // Set the model ID, e.g., Mistral Large.
        var modelId = "mistral.mistral-large-2402-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();


        try {
            // Send the message with a basic inference configuration.
            ConverseResponse response = client.converse(request -> request
                    .modelId(modelId)
                    .messages(message)
                    .inferenceConfig(config -> config
                            .maxTokens(512)
                            .temperature(0.5F)
                            .topP(0.9F)));

            // Retrieve the generated text from Bedrock's response object.
            var responseText = response.output().message().content().get(0).text();
            System.out.println(responseText);

            return responseText;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }

    }

    public static void main(String[] args) {
        converse();
    }
}

비동기 Java 클라이언트와 함께 Bedrock의 Converse API를 사용하여 Mistral에 텍스트 메시지를 보냅니다.

// Use the Converse API to send a text message to Mistral
// with the async Java client.

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.Message;

import java.util.concurrent.CompletableFuture;
import java.util.concurrent.ExecutionException;

public class ConverseAsync {

    public static String converseAsync() {

        // 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., Mistral Large.
        var modelId = "mistral.mistral-large-2402-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();

        // Send the message with a basic inference configuration.
        var request = client.converse(params -> params
                .modelId(modelId)
                .messages(message)
                .inferenceConfig(config -> config
                        .maxTokens(512)
                        .temperature(0.5F)
                        .topP(0.9F))
        );

        // Prepare a future object to handle the asynchronous response.
        CompletableFuture<String> future = new CompletableFuture<>();

        // Handle the response or error using the future object.
        request.whenComplete((response, error) -> {
            if (error == null) {
                // Extract the generated text from Bedrock's response object.
                String responseText = response.output().message().content().get(0).text();
                future.complete(responseText);
            } else {
                future.completeExceptionally(error);
            }
        });

        try {
            // Wait for the future object to complete and retrieve the generated text.
            String responseText = future.get();
            System.out.println(responseText);

            return responseText;

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

    public static void main(String[] args) {
        converseAsync();
    }
}

Bedrock의 Converse API를 사용하여 Mistral에 문자 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the Converse API to send a text message to Mistral
// 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., Mistral Large.
        var modelId = "mistral.mistral-large-2402-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());
        }
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보냅니다.

// Use the native inference API to send a text message to Mistral.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class InvokeModel {

    public static String invokeModel() {

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

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

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-mistral-text-completion.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{instruction}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in Mistral's instruction format.
        var instruction = "<s>[INST] {{prompt}} [/INST]\\n".replace("{{prompt}}", prompt);

        // Embed the instruction in the the native request payload.
        var nativeRequest = nativeRequestTemplate.replace("{{instruction}}", instruction);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/outputs/0/text").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

모델 API 호출을 사용하여 텍스트 메시지를 보내고 응답 스트림을 실시간으로 처리합니다.

// Use the native inference API to send a text message to Mistral
// and print the response stream.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeAsyncClient;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamRequest;
import software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler;

import java.util.concurrent.ExecutionException;

import static software.amazon.awssdk.services.bedrockruntime.model.InvokeModelWithResponseStreamResponseHandler.Visitor;

public class InvokeModelWithResponseStream {

    public static String invokeModelWithResponseStream() throws ExecutionException, InterruptedException {

        // 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., Mistral Large.
        var modelId = "mistral.mistral-large-2402-v1:0";

        // The InvokeModelWithResponseStream API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-mistral-text-completion.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{instruction}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in Mistral's instruction format.
        var instruction = "<s>[INST] {{prompt}} [/INST]\\n".replace("{{prompt}}", prompt);

        // Embed the instruction in the the native request payload.
        var nativeRequest = nativeRequestTemplate.replace("{{instruction}}", instruction);

        // Create a request with the model ID and the model's native request payload.
        var request = InvokeModelWithResponseStreamRequest.builder()
                .body(SdkBytes.fromUtf8String(nativeRequest))
                .modelId(modelId)
                .build();

        // Prepare a buffer to accumulate the generated response text.
        var completeResponseTextBuffer = new StringBuilder();

        // Prepare a handler to extract, accumulate, and print the response text in real-time.
        var responseStreamHandler = InvokeModelWithResponseStreamResponseHandler.builder()
                .subscriber(Visitor.builder().onChunk(chunk -> {
                    // Extract and print the text from the model's native response.
                    var response = new JSONObject(chunk.bytes().asUtf8String());
                    var text = new JSONPointer("/outputs/0/text").queryFrom(response);
                    System.out.print(text);

                    // Append the text to the response text buffer.
                    completeResponseTextBuffer.append(text);
                }).build()).build();

        try {
            // Send the request and wait for the handler to process the response.
            client.invokeModelWithResponseStream(request, responseStreamHandler).get();

            // Return the complete response text.
            return completeResponseTextBuffer.toString();

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

    public static void main(String[] args) throws ExecutionException, InterruptedException {
        invokeModelWithResponseStream();
    }
}

안정적인 확산을 사용하여 이미지를 생성합니다.

// Create an image with Stable Diffusion.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

import java.math.BigInteger;
import java.security.SecureRandom;

import static com.example.bedrockruntime.libs.ImageTools.displayImage;

public class InvokeModel {

    public static String invokeModel() {

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

        // Set the model ID, e.g., Stable Diffusion XL v1.
        var modelId = "stability.stable-diffusion-xl-v1";

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-diffusion-1-0-text-image.html
        var nativeRequestTemplate = """
                {
                    "text_prompts": [{ "text": "{{prompt}}" }],
                    "style_preset": "{{style}}",
                    "seed": {{seed}}
                }""";

        // Define the prompt for the image generation.
        var prompt = "A stylized picture of a cute old steampunk robot";

        // Get a random 32-bit seed for the image generation (max. 4,294,967,295).
        var seed = new BigInteger(31, new SecureRandom());

        // Choose a style preset.
        var style = "cinematic";

        // Embed the prompt, seed, and style in the model's native request payload.
        String nativeRequest = nativeRequestTemplate
                .replace("{{prompt}}", prompt)
                .replace("{{seed}}", seed.toString())
                .replace("{{style}}", style);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

            // Decode the response body.
            var responseBody = new JSONObject(response.body().asUtf8String());

            // Retrieve the generated image data from the model's response.
            var base64ImageData = new JSONPointer("/artifacts/0/base64")
                    .queryFrom(responseBody)
                    .toString();

            return base64ImageData;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        System.out.println("Generating image. This may take a few seconds...");

        String base64ImageData = invokeModel();

        displayImage(base64ImageData);
    }


}