Use Case Documentation
NLP Powered Search

Choose this use case if you wish to develop a model that can extract meaningful and relevant information from a large amount of unstructured text data when offered natural language queries. NLP powered search may be useful in E-commerce search, customer support, document search, or knowledge base search. Given a dataset containing large amounts of text data and an optional secondary dataset of query-response pairs, you can generate a model that responds accurately and comprehensively to natural language queries.

Dataset and Feature Group Requirements

This section specifies the Datasets / Feature Groups requirements to successfully train a NLP Powered Search model. Feature requirements include recommendations on additional datasets that might enhance model performance.

Training Models - Training Options and Metrics

This section describes all the available model training options that can be used to create a NLP Powered Search model. You can utilize the metric explanations to better understand how they measure the performance of the model you trained.

Prediction API

This section discusses the prediction API method so that you could properly generate predictions from the model you deployed.