aws sagemaker-runtime invoke-endpoint-with-response-stream

Invokes a model at the specified endpoint to return the inference response as a stream. AWS CLI reference

11 options Its page in the AWS CLI reference

Options

11 in the AWS CLI reference

--acceptThe desired MIME type of the inference response from the model container.

--bodyProvides input data, in the format specified in the ContentType request header.

--content-typeThe MIME type of the input data in the request body.

--custom-attributesProvides additional information about a request for an inference submitted to a model hosted at an Amazon SageMaker AI endpoint.

--endpoint-nameThe name of the endpoint that you specified when you created the endpoint using the CreateEndpoint API.

--inference-component-nameIf the endpoint hosts one or more inference components, this parameter specifies the name of inference component to invoke for a streaming response.

--inference-idAn identifier that you assign to your request.

--prefix-aware-idAn optional, stable identifier that serves as a routing hint for prefix-aware routing.

--session-idThe ID of a stateful session to handle your request.

--target-container-hostnameIf the endpoint hosts multiple containers and is configured to use direct invocation, this parameter specifies the host name of the container to invoke.

--target-variantSpecify the production variant to send the inference request to when invoking an endpoint that is running two or more variants.