GSP1230

Overview

Gemini is a family of generative AI models developed by Google DeepMind that is designed for multimodal use cases.

For retail companies, recommendation systems improve customer experience and thus can increase sales. In this lab, you will learn how to use the Gemini 1.5 Pro model to rapidly create a multimodal recommendation system. The Gemini 1.5 Pro 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 1.5 Pro model to perform visual understanding. You will also investigate how the Gemini 1.5 Pro model can be used to recommend an item (e.g. a chair) from a list of furniture items as input.

Gemini

Gemini is a family of powerful generative AI models developed by Google DeepMind, capable of understanding and generating various forms of content, including text, code, images, audio, and video.

Gemini API in Vertex AI

The Gemini API in Vertex AI provides a unified interface for interacting with Gemini models. This allows developers to easily integrate these powerful AI capabilities into their applications. For the most up-to-date details and specific features of the latest versions, please refer to the official Gemini documentation.

Gemini Models

• Gemini Pro: Designed for complex reasoning, including:
  • Analyzing and summarizing large amounts of information.
  • Sophisticated cross-modal reasoning (across text, code, images, etc.).
  • Effective problem-solving with complex codebases.
• Gemini Flash: Optimized for speed and efficiency, offering:
  • Sub-second response times and high throughput.
  • High quality at a lower cost for a wide range of tasks.
  • Enhanced multimodal capabilities, including improved spatial understanding, new output modalities (text, audio, images), and native tool use (Google Search, code execution, and third-party functions).

Prerequisites

Before starting this lab, you should be familiar with:

• Basic Python programming.
• General API concepts.
• Running Python code in a Jupyter notebook on Vertex AI Workbench.

Objectives

In this lab, you will learn how to:

• Use the Gemini 1.5 Pro model (gemini-1.5-pro) to perform visual understanding
• Take multimodality into consideration in prompting for the Gemini 1.5 Pro model
• Create a retail recommendation application using the Gemini 1.5 Pro model

Setup and requirements

Before you click the Start Lab button

Read these instructions. Labs are timed and you cannot pause them. The timer, which starts when you click Start Lab, shows how long Google Cloud resources will be made available to you.

This hands-on lab lets you do the lab activities yourself in a real cloud environment, not in a simulation or demo environment. It does so by giving you new, temporary credentials that you use to sign in and access Google Cloud for the duration of the lab.

To complete this lab, you need:

• Access to a standard internet browser (Chrome browser recommended).

Note: Use an Incognito or private browser window to run this lab. This prevents any conflicts between your personal account and the Student account, which may cause extra charges incurred to your personal account.

• Time to complete the lab---remember, once you start, you cannot pause a lab.

Note: If you already have your own personal Google Cloud account or project, do not use it for this lab to avoid extra charges to your account.

How to start your lab and sign in to the Google Cloud console

1. Click the Start Lab button. If you need to pay for the lab, a pop-up opens for you to select your payment method. On the left is the Lab Details panel with the following:

   • The Open Google Cloud console button
   • Time remaining
   • The temporary credentials that you must use for this lab
   • Other information, if needed, to step through this lab

2. Click Open Google Cloud console (or right-click and select Open Link in Incognito Window if you are running the Chrome browser).

   The lab spins up resources, and then opens another tab that shows the Sign in page.

   Tip: Arrange the tabs in separate windows, side-by-side.

   Note: If you see the Choose an account dialog, click Use Another Account.

3. If necessary, copy the Username below and paste it into the Sign in dialog.

   {{{user_0.username | "Username"}}}

   You can also find the Username in the Lab Details panel.

4. Click Next.

5. Copy the Password below and paste it into the Welcome dialog.

   {{{user_0.password | "Password"}}}

   You can also find the Password in the Lab Details panel.

6. Click Next.

   Important: You must use the credentials the lab provides you. Do not use your Google Cloud account credentials. Note: Using your own Google Cloud account for this lab may incur extra charges.

7. Click through the subsequent pages:

   • Accept the terms and conditions.
   • Do not add recovery options or two-factor authentication (because this is a temporary account).
   • Do not sign up for free trials.

After a few moments, the Google Cloud console opens in this tab.

Note: To view a menu with a list of Google Cloud products and services, click the Navigation menu at the top-left.

Task 1. Open the notebook in Vertex AI Workbench

1. In the Google Cloud console, on the Navigation menu (), click Vertex AI > Workbench.

2. Find the instance and click on the Open JupyterLab button.

The JupyterLab interface for your Workbench instance opens in a new browser tab.

Task 2. Set up the notebook

1. Open the file.

2. In the Select Kernel dialog, choose Python 3 from the list of available kernels.

3. Run through the Getting Started and the Import libraries sections of the notebook.

   • For Project ID, use , and for Location, use .

Note: You can skip any notebook cells that are noted Colab only. If you experience a 429 response from any of the notebook cell executions, wait 1 minute before running the cell again to proceed.

Click Check my progress to verify the objective. Install Vertex AI SDK for Python and import libraries

In the following sections, you will run through the notebook cells to see how to use the multimodal capabilities of the Gemini 1.5 Pro model.

Task 3. Use the Gemini 1.5 Pro model

The Gemini 1.5 Pro model (gemini-1.5-pro) is a multimodal model that supports adding image and video in text or chat prompts for a text response.

1. In this task, run through the notebook cells to see how to use the Gemini 1.5 Pro model to describe a room in details from its image, combining text and image in a single prompt.

Click Check my progress to verify the objective. Use Gemini 1.5 Pro model to describe a room

Task 4. Generate open recommendations based on built-in knowledge

Using the same image, you can ask the model to recommend a piece of furniture that would fit in it alongside with the description of the room. Note that the model can choose any furniture to recommend in this case, and can do so from its only built-in knowledge.

1. Using the same image, run through the notebook cells to see how to use the Gemini 1.5 Pro model to recommend a piece of furniture that would fit in the room, alongside with the description of the room.

Click Check my progress to verify the objective. Use Gemini 1.5 Pro model to recommend a piece of furniture

Task 5. Generate recommendations based on provided images

Instead of keeping the recommendation open, you can also provide a list of items for the model to choose from. In this section, you will download a few chair images and set them as options for the Gemini model to recommend from. This is particularly useful for retail companies who want to provide recommendations to users based on the kind of room they have, and the available items that the store offers.

1. In this task, run through the notebook cells to see how to use the Gemini 1.5 Pro model to recommend a piece of furniture from a list of items.

Click Check my progress to verify the objective. Use Gemini 1.5 Pro model to recommend an item from a selection

Congratulations!

Congratulations! In this lab, you have successfully explored how to build a multimodal recommendation system using Gemini for furniture. You have learned how to use the Gemini 1.5 Pro model to perform visual understanding and how to take multimodality into consideration in prompting for the Gemini 1.5 Pro model. This lab showed how you can easily build a multimodal recommendation system using Gemini for furniture, but you can also use the similar approach in:

• Recommending clothes based on an occasion or an image of the venue
• Recommending wallpaper based on the room and settings

Next steps / learn more

Check out the following resources to learn more about Gemini:

• Gemini Overview
• Generative AI on Vertex AI Documentation
• Generative AI on YouTube
• Generative AI Official Repo
• Example Gemini Notebooks

Google Cloud training and certification

...helps you make the most of Google Cloud technologies. Our classes include technical skills and best practices to help you get up to speed quickly and continue your learning journey. We offer fundamental to advanced level training, with on-demand, live, and virtual options to suit your busy schedule. Certifications help you validate and prove your skill and expertise in Google Cloud technologies.

Manual Last Updated December 12, 2024

Lab Last Tested December 12, 2024

Copyright 2024 Google LLC All rights reserved. Google and the Google logo are trademarks of Google LLC. All other company and product names may be trademarks of the respective companies with which they are associated.