Package software.amazon.awssdk.services.bedrockruntime

Interface BedrockRuntimeAsyncClient

  • All Superinterfaces:
    AutoCloseable, AwsClient, SdkAutoCloseable, SdkClient
    @Generated("software.amazon.awssdk:codegen")
@ThreadSafe
public interface BedrockRuntimeAsyncClient
extends AwsClient
    Service client for accessing Amazon Bedrock Runtime asynchronously. This can be created using the static builder() method.The asynchronous client performs non-blocking I/O when configured with any SdkAsyncHttpClient supported in the SDK. However, full non-blocking is not guaranteed as the async client may perform blocking calls in some cases such as credentials retrieval and endpoint discovery as part of the async API call.

    Describes the API operations for running inference using Amazon Bedrock models.

    • Method Detail

      • applyGuardrail

        default CompletableFuture<ApplyGuardrailResponse> applyGuardrail​(ApplyGuardrailRequest applyGuardrailRequest)

        The action to apply a guardrail.

        Parameters:
        applyGuardrailRequest -
        Returns:
        A Java Future containing the result of the ApplyGuardrail operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ServiceQuotaExceededException The number of requests exceeds the service quota. Resubmit your request later.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • applyGuardrail

        default CompletableFuture<ApplyGuardrailResponse> applyGuardrail​(Consumer<ApplyGuardrailRequest.Builder> applyGuardrailRequest)

        The action to apply a guardrail.


        This is a convenience which creates an instance of the ApplyGuardrailRequest.Builder avoiding the need to create one manually via ApplyGuardrailRequest.builder()

        Parameters:
        applyGuardrailRequest - A Consumer that will call methods on ApplyGuardrailRequest.Builder to create a request.
        Returns:
        A Java Future containing the result of the ApplyGuardrail operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ServiceQuotaExceededException The number of requests exceeds the service quota. Resubmit your request later.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • converse

        default CompletableFuture<ConverseResponse> converse​(ConverseRequest converseRequest)

        Sends messages to the specified Amazon Bedrock model. Converse provides a consistent interface that works with all models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model.

        For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

        For example code, see Converse API examples in the Amazon Bedrock User Guide.

        This operation requires permission for the bedrock:InvokeModel action.

        Parameters:
        converseRequest -
        Returns:
        A Java Future containing the result of the Converse operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • converse

        default CompletableFuture<ConverseResponse> converse​(Consumer<ConverseRequest.Builder> converseRequest)

        Sends messages to the specified Amazon Bedrock model. Converse provides a consistent interface that works with all models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model.

        For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

        For example code, see Converse API examples in the Amazon Bedrock User Guide.

        This operation requires permission for the bedrock:InvokeModel action.


        This is a convenience which creates an instance of the ConverseRequest.Builder avoiding the need to create one manually via ConverseRequest.builder()

        Parameters:
        converseRequest - A Consumer that will call methods on ConverseRequest.Builder to create a request.
        Returns:
        A Java Future containing the result of the Converse operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • converseStream

        default CompletableFuture<Void> converseStream​(ConverseStreamRequest converseStreamRequest,
                                               ConverseStreamResponseHandler asyncResponseHandler)

        Sends messages to the specified Amazon Bedrock model and returns the response in a stream. ConverseStream provides a consistent API that works with all Amazon Bedrock models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model.

        To find out if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

        For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

        For example code, see Conversation streaming example in the Amazon Bedrock User Guide.

        This operation requires permission for the bedrock:InvokeModelWithResponseStream action.

        Parameters:
        converseStreamRequest -
        Returns:
        A Java Future containing the result of the ConverseStream operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • converseStream

        default CompletableFuture<Void> converseStream​(Consumer<ConverseStreamRequest.Builder> converseStreamRequest,
                                               ConverseStreamResponseHandler asyncResponseHandler)

        Sends messages to the specified Amazon Bedrock model and returns the response in a stream. ConverseStream provides a consistent API that works with all Amazon Bedrock models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model.

        To find out if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

        For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

        For example code, see Conversation streaming example in the Amazon Bedrock User Guide.

        This operation requires permission for the bedrock:InvokeModelWithResponseStream action.


        This is a convenience which creates an instance of the ConverseStreamRequest.Builder avoiding the need to create one manually via ConverseStreamRequest.builder()

        Parameters:
        converseStreamRequest - A Consumer that will call methods on ConverseStreamRequest.Builder to create a request.
        Returns:
        A Java Future containing the result of the ConverseStream operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • invokeModel

        default CompletableFuture<InvokeModelResponse> invokeModel​(InvokeModelRequest invokeModelRequest)

        Invokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. You use model inference to generate text, images, and embeddings.

        For example code, see Invoke model code examples in the Amazon Bedrock User Guide.

        This operation requires permission for the bedrock:InvokeModel action.

        Parameters:
        invokeModelRequest -
        Returns:
        A Java Future containing the result of the InvokeModel operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ServiceQuotaExceededException The number of requests exceeds the service quota. Resubmit your request later.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • invokeModel

        default CompletableFuture<InvokeModelResponse> invokeModel​(Consumer<InvokeModelRequest.Builder> invokeModelRequest)

        Invokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. You use model inference to generate text, images, and embeddings.

        For example code, see Invoke model code examples in the Amazon Bedrock User Guide.

        This operation requires permission for the bedrock:InvokeModel action.


        This is a convenience which creates an instance of the InvokeModelRequest.Builder avoiding the need to create one manually via InvokeModelRequest.builder()

        Parameters:
        invokeModelRequest - A Consumer that will call methods on InvokeModelRequest.Builder to create a request.
        Returns:
        A Java Future containing the result of the InvokeModel operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ServiceQuotaExceededException The number of requests exceeds the service quota. Resubmit your request later.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • invokeModelWithResponseStream

        default CompletableFuture<Void> invokeModelWithResponseStream​(InvokeModelWithResponseStreamRequest invokeModelWithResponseStreamRequest,
                                                              InvokeModelWithResponseStreamResponseHandler asyncResponseHandler)

        Invoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a stream.

        To see if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

        The CLI doesn't support InvokeModelWithResponseStream.

        For example code, see Invoke model with streaming code example in the Amazon Bedrock User Guide.

        This operation requires permissions to perform the bedrock:InvokeModelWithResponseStream action.

        Parameters:
        invokeModelWithResponseStreamRequest -
        Returns:
        A Java Future containing the result of the InvokeModelWithResponseStream operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ModelStreamErrorException An error occurred while streaming the response. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ServiceQuotaExceededException The number of requests exceeds the service quota. Resubmit your request later.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation

      • invokeModelWithResponseStream

        default CompletableFuture<Void> invokeModelWithResponseStream​(Consumer<InvokeModelWithResponseStreamRequest.Builder> invokeModelWithResponseStreamRequest,
                                                              InvokeModelWithResponseStreamResponseHandler asyncResponseHandler)

        Invoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a stream.

        To see if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

        The CLI doesn't support InvokeModelWithResponseStream.

        For example code, see Invoke model with streaming code example in the Amazon Bedrock User Guide.

        This operation requires permissions to perform the bedrock:InvokeModelWithResponseStream action.


        This is a convenience which creates an instance of the InvokeModelWithResponseStreamRequest.Builder avoiding the need to create one manually via InvokeModelWithResponseStreamRequest.builder()

        Parameters:
        invokeModelWithResponseStreamRequest - A Consumer that will call methods on InvokeModelWithResponseStreamRequest.Builder to create a request.
        Returns:
        A Java Future containing the result of the InvokeModelWithResponseStream operation returned by the service.
        The CompletableFuture returned by this method can be completed exceptionally with the following exceptions. The exception returned is wrapped with CompletionException, so you need to invoke Throwable.getCause() to retrieve the underlying exception.
        • AccessDeniedException The request is denied because of missing access permissions.
        • ResourceNotFoundException The specified resource ARN was not found. Check the ARN and try your request again.
        • ThrottlingException The number of requests exceeds the limit. Resubmit your request later.
        • ModelTimeoutException The request took too long to process. Processing time exceeded the model timeout length.
        • InternalServerException An internal server error occurred. Retry your request.
        • ModelStreamErrorException An error occurred while streaming the response. Retry your request.
        • ValidationException Input validation failed. Check your request parameters and retry the request.
        • ModelNotReadyException The model specified in the request is not ready to serve inference requests.
        • ServiceQuotaExceededException The number of requests exceeds the service quota. Resubmit your request later.
        • ModelErrorException The request failed due to an error while processing the model.
        • SdkException Base class for all exceptions that can be thrown by the SDK (both service and client). Can be used for catch all scenarios.
        • SdkClientException If any client side error occurs such as an IO related failure, failure to get credentials, etc.
        • BedrockRuntimeException Base class for all service exceptions. Unknown exceptions will be thrown as an instance of this type.
        See Also:
        AWS API Documentation