Azure AI Engineer Associate: Configuring and Using Azure AI Search

Getting the best out of Azure AI Search involves understanding full-text search in detail, but far more important these days is vector search. It is vector search that allows user queries to be matched with results that are similar in meaning – even if the results are in entirely different languages, and even in different modalities such as video or images. Begin this course by exploring the indexing and querying processes – this will involve provisioning an Azure AI Search resource, configuring the data source and indexer, editing the schema, and then querying the index once it is created. Learn about the Best Match 25 (BM25) algorithm and a powerful feature known as semantic reranking. Next, discover vector-search and vectorizing data using an embeddings model. Finally, learn about scaling Azure AI Search by balancing the number of replicas and partitions while meeting constraints on the number of search units, and mastering the use-cases of different search tiers.This course is part of a collection that prepares learners for the Designing and Implementing a Microsoft Azure AI Solution (AI-102) exam.