How to use a TfidfVectorizer model in real-time with endpoints

Question

During training, I created a TfidfVectorizer model and trained it to generate features from a database. How can I reuse this model to generate the representation of new texts, which will be classified by the endpoint?

Answer

You can try [SageMaker Inference Pipeline](https://docs.aws.amazon.com/sagemaker/latest/dg/inference-pipelines.html), and add the TfidfVectorizer as a preprocessing step. Also take a look at this step-by-step [blog example](https://aws.amazon.com/blogs/machine-learning/preprocess-input-data-before-making-predictions-using-amazon-sagemaker-inference-pipelines-and-scikit-learn/).

How to use a TfidfVectorizer model in real-time with endpoints

Conteúdo relevante