Use Vertex AI Vector Search to Recommend Similar Products

Vector Search can explore billions of items that are semantically similar or related. This service, which matches vector similarities, finds application in various scenarios, including recommendation engines, search engines, chat bots, and text classification. Vertex AI Vector Search is the foundation of Google products such as Google Search, YouTube, and Play.

This lab is based on a retail use case, where you will use Vertex AI Vector Search to index and search for vector representations of products created by Vertex AI's Embedding for Text. You will see how this can efficiently provide product recommendations to users.

Learning Objectives

Upon completion of this intermediate-level lab, you will be able to:

• Understand Vector Search terminology and concepts
• Create a Vertex AI Vector Search index and index endpoints
• Use the Vertex AI Vector Search API to search for similar items or nearest neighbors in the index

Intended Audience

This lab is intended for:

• AI Practitioners
• Data scientists
• Machine learning engineers
• Google Professional Cloud Machine Learning exam candidates

Prerequisites

You should possess:

• A basic understanding of the following:

  • Vertex AI
  • Python

The following content can fulfill the prerequisites:

• Introduction to Google Vertex AI
• Python for Beginners