Using Gemini for Multimodal Retail Recommendations GSP1230

Overview
Gemini is a family of generative AI models developed by Google DeepMind that is designed for multimodal use cases. The Gemini API gives you access to the Gemini Pro Vision and Gemini Pro models.

For retail companies, recommendation systems improve customer experience and thus can increase sales. In this lab, you will learn how to use the Gemini Pro Vision model to rapidly create a multimodal recommendation system. The Gemini Pro Vision model can provide both recommendations and explanations using a multimodal model.

In this lab, you will begin with a scene (e.g. a living room) and use the Gemini Pro Vision model to perform visual understanding. You will also investigate how the Gemini Pro Vision model can be used to recommend an item (e.g. a chair) from a list of furniture items as input.

Vertex AI Gemini API
The Vertex AI Gemini API provides a unified interface for interacting with Gemini models. There are currently two models available in the Gemini API:

1. Gemini Pro model (gemini-pro): Designed to handle natural language tasks, multiturn text and code chat, and code generation.
2. Gemini Pro Vision model (gemini-pro-vision): Supports multimodal prompts. You can include text, images, and video in your prompt requests and get text or code responses.
You can interact with the Gemini API using the following methods:
- Use the Vertex AI Studio for quick testing and command generation
- Use cURL commands
- Use the Vertex AI SDK
This lab focuses on the multimodal capabilities of the Gemini Pro Vision model.

For more information, see the Generative AI on Vertex A documentation.

Objectives
In this lab, you will learn how to:
- Use the Gemini Pro Vision model (gemini-pro-vision) to perform visual understanding
- Take multimodality into consideration in prompting for the Gemini Pro Vision model
- Create a retail recommendation application using the Gemini Pro Vision model
#gcp #googlecloud #qwiklabs #learntoearn