SageMakerGatewayRuntime¶
Client¶
- class SageMakerGatewayRuntime.Client¶
A low-level client representing Amazon SageMaker Gateway Runtime
Use the Amazon SageMaker Gateway Runtime API to run inference through a Global Inference Gateway. A Global Inference Gateway routes each request to an inference gateway that serves the model named in the request.
The request body is an OpenAI-compatible JSON object, sent with
Content-Type: application/json, and the model is selected by themodelkey in that body. The content of the body is passed to the model server unchanged, except for thestreamflag, which each operation sets.Requests are signed with Signature Version 4 under the
sagemakersigning name. IAM actions are in thesagemakernamespace, for examplesagemaker:InvokeGlobalInferenceGateway. The default regional endpoint isgateway-runtime.sagemaker.{region}.amazonaws.com.rproxy.govskope.ca.client = session.create_client('sagemaker-gateway-runtime')
These are the available methods:
Client Exceptions¶
Client exceptions are available on a client instance via the exceptions property. For more detailed instructions and examples on the exact usage of client exceptions, see the error handling user guide.
The available client exceptions are: