@Generated(value="com.amazonaws:aws-java-sdk-code-generator") public class InvokeEndpointRequest extends AmazonWebServiceRequest implements Serializable, Cloneable
NOOP
Constructor and Description |
---|
InvokeEndpointRequest() |
Modifier and Type | Method and Description |
---|---|
InvokeEndpointRequest |
clone()
Creates a shallow clone of this object for all fields except the handler context.
|
boolean |
equals(Object obj) |
String |
getAccept()
The desired MIME type of the inference response from the model container.
|
ByteBuffer |
getBody()
Provides input data, in the format specified in the
ContentType request header. |
String |
getContentType()
The MIME type of the input data in the request body.
|
String |
getCustomAttributes()
Provides additional information about a request for an inference submitted to a model hosted at an Amazon
SageMaker endpoint.
|
String |
getEnableExplanations()
An optional JMESPath expression used to override the
EnableExplanations parameter of the
ClarifyExplainerConfig API. |
String |
getEndpointName()
The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.
|
String |
getInferenceComponentName()
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component
to invoke.
|
String |
getInferenceId()
If you provide a value, it is added to the captured data when you enable data capture on the endpoint.
|
String |
getTargetContainerHostname()
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies
the host name of the container to invoke.
|
String |
getTargetModel()
The model to request for inference when invoking a multi-model endpoint.
|
String |
getTargetVariant()
Specify the production variant to send the inference request to when invoking an endpoint that is running two or
more variants.
|
int |
hashCode() |
void |
setAccept(String accept)
The desired MIME type of the inference response from the model container.
|
void |
setBody(ByteBuffer body)
Provides input data, in the format specified in the
ContentType request header. |
void |
setContentType(String contentType)
The MIME type of the input data in the request body.
|
void |
setCustomAttributes(String customAttributes)
Provides additional information about a request for an inference submitted to a model hosted at an Amazon
SageMaker endpoint.
|
void |
setEnableExplanations(String enableExplanations)
An optional JMESPath expression used to override the
EnableExplanations parameter of the
ClarifyExplainerConfig API. |
void |
setEndpointName(String endpointName)
The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.
|
void |
setInferenceComponentName(String inferenceComponentName)
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component
to invoke.
|
void |
setInferenceId(String inferenceId)
If you provide a value, it is added to the captured data when you enable data capture on the endpoint.
|
void |
setTargetContainerHostname(String targetContainerHostname)
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies
the host name of the container to invoke.
|
void |
setTargetModel(String targetModel)
The model to request for inference when invoking a multi-model endpoint.
|
void |
setTargetVariant(String targetVariant)
Specify the production variant to send the inference request to when invoking an endpoint that is running two or
more variants.
|
String |
toString()
Returns a string representation of this object.
|
InvokeEndpointRequest |
withAccept(String accept)
The desired MIME type of the inference response from the model container.
|
InvokeEndpointRequest |
withBody(ByteBuffer body)
Provides input data, in the format specified in the
ContentType request header. |
InvokeEndpointRequest |
withContentType(String contentType)
The MIME type of the input data in the request body.
|
InvokeEndpointRequest |
withCustomAttributes(String customAttributes)
Provides additional information about a request for an inference submitted to a model hosted at an Amazon
SageMaker endpoint.
|
InvokeEndpointRequest |
withEnableExplanations(String enableExplanations)
An optional JMESPath expression used to override the
EnableExplanations parameter of the
ClarifyExplainerConfig API. |
InvokeEndpointRequest |
withEndpointName(String endpointName)
The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.
|
InvokeEndpointRequest |
withInferenceComponentName(String inferenceComponentName)
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component
to invoke.
|
InvokeEndpointRequest |
withInferenceId(String inferenceId)
If you provide a value, it is added to the captured data when you enable data capture on the endpoint.
|
InvokeEndpointRequest |
withTargetContainerHostname(String targetContainerHostname)
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies
the host name of the container to invoke.
|
InvokeEndpointRequest |
withTargetModel(String targetModel)
The model to request for inference when invoking a multi-model endpoint.
|
InvokeEndpointRequest |
withTargetVariant(String targetVariant)
Specify the production variant to send the inference request to when invoking an endpoint that is running two or
more variants.
|
addHandlerContext, getCloneRoot, getCloneSource, getCustomQueryParameters, getCustomRequestHeaders, getGeneralProgressListener, getHandlerContext, getReadLimit, getRequestClientOptions, getRequestCredentials, getRequestCredentialsProvider, getRequestMetricCollector, getSdkClientExecutionTimeout, getSdkRequestTimeout, putCustomQueryParameter, putCustomRequestHeader, setGeneralProgressListener, setRequestCredentials, setRequestCredentialsProvider, setRequestMetricCollector, setSdkClientExecutionTimeout, setSdkRequestTimeout, withGeneralProgressListener, withRequestCredentialsProvider, withRequestMetricCollector, withSdkClientExecutionTimeout, withSdkRequestTimeout
public void setEndpointName(String endpointName)
The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.
endpointName
- The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.public String getEndpointName()
The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.
public InvokeEndpointRequest withEndpointName(String endpointName)
The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.
endpointName
- The name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.public void setBody(ByteBuffer body)
Provides input data, in the format specified in the ContentType
request header. Amazon SageMaker
passes all of the data in the body to the model.
For information about the format of the request body, see Common Data Formats-Inference.
The AWS SDK for Java performs a Base64 encoding on this field before sending this request to the AWS service. Users of the SDK should not perform Base64 encoding on this field.
Warning: ByteBuffers returned by the SDK are mutable. Changes to the content or position of the byte buffer will be seen by all objects that have a reference to this object. It is recommended to call ByteBuffer.duplicate() or ByteBuffer.asReadOnlyBuffer() before using or reading from the buffer. This behavior will be changed in a future major version of the SDK.
body
- Provides input data, in the format specified in the ContentType
request header. Amazon
SageMaker passes all of the data in the body to the model.
For information about the format of the request body, see Common Data Formats-Inference.
public ByteBuffer getBody()
Provides input data, in the format specified in the ContentType
request header. Amazon SageMaker
passes all of the data in the body to the model.
For information about the format of the request body, see Common Data Formats-Inference.
ByteBuffer
s are stateful. Calling their get
methods changes their position
. We recommend
using ByteBuffer.asReadOnlyBuffer()
to create a read-only view of the buffer with an independent
position
, and calling get
methods on this rather than directly on the returned ByteBuffer
.
Doing so will ensure that anyone else using the ByteBuffer
will not be affected by changes to the
position
.
ContentType
request header. Amazon
SageMaker passes all of the data in the body to the model.
For information about the format of the request body, see Common Data Formats-Inference.
public InvokeEndpointRequest withBody(ByteBuffer body)
Provides input data, in the format specified in the ContentType
request header. Amazon SageMaker
passes all of the data in the body to the model.
For information about the format of the request body, see Common Data Formats-Inference.
The AWS SDK for Java performs a Base64 encoding on this field before sending this request to the AWS service. Users of the SDK should not perform Base64 encoding on this field.
Warning: ByteBuffers returned by the SDK are mutable. Changes to the content or position of the byte buffer will be seen by all objects that have a reference to this object. It is recommended to call ByteBuffer.duplicate() or ByteBuffer.asReadOnlyBuffer() before using or reading from the buffer. This behavior will be changed in a future major version of the SDK.
body
- Provides input data, in the format specified in the ContentType
request header. Amazon
SageMaker passes all of the data in the body to the model.
For information about the format of the request body, see Common Data Formats-Inference.
public void setContentType(String contentType)
The MIME type of the input data in the request body.
contentType
- The MIME type of the input data in the request body.public String getContentType()
The MIME type of the input data in the request body.
public InvokeEndpointRequest withContentType(String contentType)
The MIME type of the input data in the request body.
contentType
- The MIME type of the input data in the request body.public void setAccept(String accept)
The desired MIME type of the inference response from the model container.
accept
- The desired MIME type of the inference response from the model container.public String getAccept()
The desired MIME type of the inference response from the model container.
public InvokeEndpointRequest withAccept(String accept)
The desired MIME type of the inference response from the model container.
accept
- The desired MIME type of the inference response from the model container.public void setCustomAttributes(String customAttributes)
Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1).
The code in your model is responsible for setting or updating any custom attributes in the response. If your code
does not set this value in the response, an empty value is returned. For example, if a custom attribute
represents the trace ID, your model can prepend the custom attribute with Trace ID:
in your
post-processing function.
This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
customAttributes
- Provides additional information about a request for an inference submitted to a model hosted at an Amazon
SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this
value, for example, to provide an ID that you can use to track a request or to provide other metadata that
a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII
characters as specified in Section
3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1).
The code in your model is responsible for setting or updating any custom attributes in the response. If
your code does not set this value in the response, an empty value is returned. For example, if a custom
attribute represents the trace ID, your model can prepend the custom attribute with Trace ID:
in your post-processing function.
This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
public String getCustomAttributes()
Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1).
The code in your model is responsible for setting or updating any custom attributes in the response. If your code
does not set this value in the response, an empty value is returned. For example, if a custom attribute
represents the trace ID, your model can prepend the custom attribute with Trace ID:
in your
post-processing function.
This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
The code in your model is responsible for setting or updating any custom attributes in the response. If
your code does not set this value in the response, an empty value is returned. For example, if a custom
attribute represents the trace ID, your model can prepend the custom attribute with
Trace ID:
in your post-processing function.
This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
public InvokeEndpointRequest withCustomAttributes(String customAttributes)
Provides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this value, for example, to provide an ID that you can use to track a request or to provide other metadata that a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII characters as specified in Section 3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1).
The code in your model is responsible for setting or updating any custom attributes in the response. If your code
does not set this value in the response, an empty value is returned. For example, if a custom attribute
represents the trace ID, your model can prepend the custom attribute with Trace ID:
in your
post-processing function.
This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
customAttributes
- Provides additional information about a request for an inference submitted to a model hosted at an Amazon
SageMaker endpoint. The information is an opaque value that is forwarded verbatim. You could use this
value, for example, to provide an ID that you can use to track a request or to provide other metadata that
a service endpoint was programmed to process. The value must consist of no more than 1024 visible US-ASCII
characters as specified in Section
3.3.6. Field Value Components of the Hypertext Transfer Protocol (HTTP/1.1).
The code in your model is responsible for setting or updating any custom attributes in the response. If
your code does not set this value in the response, an empty value is returned. For example, if a custom
attribute represents the trace ID, your model can prepend the custom attribute with Trace ID:
in your post-processing function.
This feature is currently supported in the Amazon Web Services SDKs but not in the Amazon SageMaker Python SDK.
public void setTargetModel(String targetModel)
The model to request for inference when invoking a multi-model endpoint.
targetModel
- The model to request for inference when invoking a multi-model endpoint.public String getTargetModel()
The model to request for inference when invoking a multi-model endpoint.
public InvokeEndpointRequest withTargetModel(String targetModel)
The model to request for inference when invoking a multi-model endpoint.
targetModel
- The model to request for inference when invoking a multi-model endpoint.public void setTargetVariant(String targetVariant)
Specify the production variant to send the inference request to when invoking an endpoint that is running two or more variants. Note that this parameter overrides the default behavior for the endpoint, which is to distribute the invocation traffic based on the variant weights.
For information about how to use variant targeting to perform a/b testing, see Test models in production
targetVariant
- Specify the production variant to send the inference request to when invoking an endpoint that is running
two or more variants. Note that this parameter overrides the default behavior for the endpoint, which is
to distribute the invocation traffic based on the variant weights.
For information about how to use variant targeting to perform a/b testing, see Test models in production
public String getTargetVariant()
Specify the production variant to send the inference request to when invoking an endpoint that is running two or more variants. Note that this parameter overrides the default behavior for the endpoint, which is to distribute the invocation traffic based on the variant weights.
For information about how to use variant targeting to perform a/b testing, see Test models in production
For information about how to use variant targeting to perform a/b testing, see Test models in production
public InvokeEndpointRequest withTargetVariant(String targetVariant)
Specify the production variant to send the inference request to when invoking an endpoint that is running two or more variants. Note that this parameter overrides the default behavior for the endpoint, which is to distribute the invocation traffic based on the variant weights.
For information about how to use variant targeting to perform a/b testing, see Test models in production
targetVariant
- Specify the production variant to send the inference request to when invoking an endpoint that is running
two or more variants. Note that this parameter overrides the default behavior for the endpoint, which is
to distribute the invocation traffic based on the variant weights.
For information about how to use variant targeting to perform a/b testing, see Test models in production
public void setTargetContainerHostname(String targetContainerHostname)
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.
targetContainerHostname
- If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter
specifies the host name of the container to invoke.public String getTargetContainerHostname()
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.
public InvokeEndpointRequest withTargetContainerHostname(String targetContainerHostname)
If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.
targetContainerHostname
- If the endpoint hosts multiple containers and is configured to use direct invocation, this parameter
specifies the host name of the container to invoke.public void setInferenceId(String inferenceId)
If you provide a value, it is added to the captured data when you enable data capture on the endpoint. For information about data capture, see Capture Data.
inferenceId
- If you provide a value, it is added to the captured data when you enable data capture on the endpoint. For
information about data capture, see Capture Data.public String getInferenceId()
If you provide a value, it is added to the captured data when you enable data capture on the endpoint. For information about data capture, see Capture Data.
public InvokeEndpointRequest withInferenceId(String inferenceId)
If you provide a value, it is added to the captured data when you enable data capture on the endpoint. For information about data capture, see Capture Data.
inferenceId
- If you provide a value, it is added to the captured data when you enable data capture on the endpoint. For
information about data capture, see Capture Data.public void setEnableExplanations(String enableExplanations)
An optional JMESPath expression used to override the EnableExplanations
parameter of the
ClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.
enableExplanations
- An optional JMESPath expression used to override the EnableExplanations
parameter of the
ClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.public String getEnableExplanations()
An optional JMESPath expression used to override the EnableExplanations
parameter of the
ClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.
EnableExplanations
parameter of the
ClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.public InvokeEndpointRequest withEnableExplanations(String enableExplanations)
An optional JMESPath expression used to override the EnableExplanations
parameter of the
ClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.
enableExplanations
- An optional JMESPath expression used to override the EnableExplanations
parameter of the
ClarifyExplainerConfig
API. See the EnableExplanations section in the developer guide for more information.public void setInferenceComponentName(String inferenceComponentName)
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke.
inferenceComponentName
- If the endpoint hosts one or more inference components, this parameter specifies the name of inference
component to invoke.public String getInferenceComponentName()
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke.
public InvokeEndpointRequest withInferenceComponentName(String inferenceComponentName)
If the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke.
inferenceComponentName
- If the endpoint hosts one or more inference components, this parameter specifies the name of inference
component to invoke.public String toString()
toString
in class Object
Object.toString()
public InvokeEndpointRequest clone()
AmazonWebServiceRequest
clone
in class AmazonWebServiceRequest
Object.clone()