Serverless NLP Inference via HTTP API on AWS

How to set up an API for your serverless endpoint using Boto3

What is this about?

In a previous blog post I described how we can deploy NLP models on Amazon SageMaker for serverless inference. As a next step we would like to measure the performance of this serverless endpoint. To do that we need to invoke the endpoint with some test data. This can easily be done using the Boto3 sagemaker-runtime client:

api aws nlp sagemaker serverless serverless-architecture