Class InvokeModelWithResponseStreamRequest
- All Implemented Interfaces:
SdkPojo,ToCopyableBuilder<InvokeModelWithResponseStreamRequest.Builder,InvokeModelWithResponseStreamRequest>
-
Nested Class Summary
Nested Classes -
Method Summary
Modifier and TypeMethodDescriptionfinal Stringaccept()The desired MIME type of the inference body in the response.final SdkBytesbody()The prompt and inference parameters in the format specified in thecontentTypein the header.builder()final StringThe MIME type of the input data in the request.final booleanfinal booleanequalsBySdkFields(Object obj) final <T> Optional<T>getValueForField(String fieldName, Class<T> clazz) final StringThe unique identifier of the guardrail that you want to use.final StringThe version number for the guardrail.final inthashCode()final StringmodelId()The unique identifier of the model to invoke to run inference.final PerformanceConfigLatencyModel performance settings for the request.final StringModel performance settings for the request.final StringKey-value pairs that you can use to filter invocation logs.static Class<? extends InvokeModelWithResponseStreamRequest.Builder>final ServiceTierTypeSpecifies the processing tier type used for serving the request.final StringSpecifies the processing tier type used for serving the request.final StringtoString()Returns a string representation of this object.final Tracetrace()Specifies whether to enable or disable the Bedrock trace.final StringSpecifies whether to enable or disable the Bedrock trace.Methods inherited from class software.amazon.awssdk.awscore.AwsRequest
overrideConfigurationMethods inherited from class java.lang.Object
clone, finalize, getClass, notify, notifyAll, wait, wait, waitMethods inherited from interface software.amazon.awssdk.utils.builder.ToCopyableBuilder
copy
-
Method Details
-
body
The prompt and inference parameters in the format specified in the
contentTypein the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to Inference parameters. For more information, see Run inference in the Bedrock User Guide.- Returns:
- The prompt and inference parameters in the format specified in the
contentTypein the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to Inference parameters. For more information, see Run inference in the Bedrock User Guide.
-
contentType
The MIME type of the input data in the request. You must specify
application/json.- Returns:
- The MIME type of the input data in the request. You must specify
application/json.
-
accept
The desired MIME type of the inference body in the response. The default value is
application/json.- Returns:
- The desired MIME type of the inference body in the response. The default value is
application/json.
-
modelId
The unique identifier of the model to invoke to run inference.
The
modelIdto provide depends on the type of model or throughput that you use:-
If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.
-
If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for cross-region inference in the Amazon Bedrock User Guide.
-
If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.
-
If you use a custom model, specify the ARN of the custom model deployment (for on-demand inference) or the ARN of your provisioned model (for Provisioned Throughput). For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.
-
If you use an imported model, specify the ARN of the imported model. You can get the model ARN from a successful call to CreateModelImportJob or from the Imported models page in the Amazon Bedrock console.
- Returns:
- The unique identifier of the model to invoke to run inference.
The
modelIdto provide depends on the type of model or throughput that you use:-
If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.
-
If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for cross-region inference in the Amazon Bedrock User Guide.
-
If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.
-
If you use a custom model, specify the ARN of the custom model deployment (for on-demand inference) or the ARN of your provisioned model (for Provisioned Throughput). For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.
-
If you use an imported model, specify the ARN of the imported model. You can get the model ARN from a successful call to CreateModelImportJob or from the Imported models page in the Amazon Bedrock console.
-
-
-
trace
Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
If the service returns an enum value that is not available in the current SDK version,
tracewill returnTrace.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available fromtraceAsString().- Returns:
- Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
- See Also:
-
traceAsString
Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
If the service returns an enum value that is not available in the current SDK version,
tracewill returnTrace.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available fromtraceAsString().- Returns:
- Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
- See Also:
-
guardrailIdentifier
The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.
An error is thrown in the following situations.
-
You don't provide a guardrail identifier but you specify the
amazon-bedrock-guardrailConfigfield in the request body. -
You enable the guardrail but the
contentTypeisn'tapplication/json. -
You provide a guardrail identifier, but
guardrailVersionisn't specified.
- Returns:
- The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail
is applied to the invocation.
An error is thrown in the following situations.
-
You don't provide a guardrail identifier but you specify the
amazon-bedrock-guardrailConfigfield in the request body. -
You enable the guardrail but the
contentTypeisn'tapplication/json. -
You provide a guardrail identifier, but
guardrailVersionisn't specified.
-
-
-
guardrailVersion
The version number for the guardrail. The value can also be
DRAFT.- Returns:
- The version number for the guardrail. The value can also be
DRAFT.
-
performanceConfigLatency
Model performance settings for the request.
If the service returns an enum value that is not available in the current SDK version,
performanceConfigLatencywill returnPerformanceConfigLatency.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available fromperformanceConfigLatencyAsString().- Returns:
- Model performance settings for the request.
- See Also:
-
performanceConfigLatencyAsString
Model performance settings for the request.
If the service returns an enum value that is not available in the current SDK version,
performanceConfigLatencywill returnPerformanceConfigLatency.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available fromperformanceConfigLatencyAsString().- Returns:
- Model performance settings for the request.
- See Also:
-
serviceTier
Specifies the processing tier type used for serving the request.
If the service returns an enum value that is not available in the current SDK version,
serviceTierwill returnServiceTierType.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available fromserviceTierAsString().- Returns:
- Specifies the processing tier type used for serving the request.
- See Also:
-
serviceTierAsString
Specifies the processing tier type used for serving the request.
If the service returns an enum value that is not available in the current SDK version,
serviceTierwill returnServiceTierType.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available fromserviceTierAsString().- Returns:
- Specifies the processing tier type used for serving the request.
- See Also:
-
requestMetadata
Key-value pairs that you can use to filter invocation logs.
- Returns:
- Key-value pairs that you can use to filter invocation logs.
-
toBuilder
- Specified by:
toBuilderin interfaceToCopyableBuilder<InvokeModelWithResponseStreamRequest.Builder,InvokeModelWithResponseStreamRequest> - Specified by:
toBuilderin classBedrockRuntimeRequest
-
builder
-
serializableBuilderClass
public static Class<? extends InvokeModelWithResponseStreamRequest.Builder> serializableBuilderClass() -
hashCode
public final int hashCode()- Overrides:
hashCodein classAwsRequest
-
equals
- Overrides:
equalsin classAwsRequest
-
equalsBySdkFields
- Specified by:
equalsBySdkFieldsin interfaceSdkPojo
-
toString
Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be redacted from this string using a placeholder value. -
getValueForField
- Overrides:
getValueForFieldin classSdkRequest
-
sdkFields
-
sdkFieldNameToField
- Specified by:
sdkFieldNameToFieldin interfaceSdkPojo
-