GSP1210

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. This lab focuses on demonstrates a variety of multimodal use cases that Gemini can be used for. In this lab, you will learn how to use the Vertex AI Gemini API to generate text from text and image(s), and video prompts.

Multimodality

Compared to text-only LLMs, Gemini Pro Vision's multimodality can be used for many new use-cases:

Example use cases with text and image(s) as input:

• Detecting objects in photos
• Understanding screens and interfaces
• Understanding of drawing and abstraction
• Understanding charts and diagrams
• Recommendation of images based on user preferences
• Comparing images for similarities, anomalies, or differences

Example use cases with text and video as input:

• Generating a video description
• Extracting tags of objects throughout a video
• Extracting highlights/messaging of a video

Objectives

In this lab, you will:

• Use the Vertex AI Gemini API to generate text from text, image(s), and video prompts.

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.

Enable All Recommended APIs

1. In the Google Cloud Console, on the Navigation menu, click Vertex AI.

2. Click Enable All Recommended APIs.

Task 1. Open the notebook in Vertex AI Workbench

1. In the Google Cloud Console, on the Navigation menu, click Vertex AI > Workbench.

2. On the User-Managed Notebooks page, find the generative-ai-jupyterlab notebook and click on the Open JupyterLab button.

The JupyterLab interface opens in a new browser tab.

Task 2. Open the generative-ai folder

1. Navigate to the generative-ai folder on the left hand side of the notebook.

2. Navigate to the /gemini/use-cases/ folder.

3. Click on the intro_multimodal_use_cases.ipynb file

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

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

Note: you can skip any notebook cells that are noted Colab only.

In the following sections, you will run through the notebook cells to see how to use the Vertex AI Gemini API with the Vertex AI SDK for Python.

Task 3. Use the Gemini Pro Vision model

Gemini Pro Vision (gemini-pro-vision) is a multimodal model that supports multimodal prompts. You can include text, image(s), and video in your prompt requests and get text or code responses.

In this task, run through the notebook cells to see how to use the Gemini Pro Vision model. Return here to check your progress as you complete the objectives.

Image understanding across multiple images

One of the capabilities of Gemini is being able to reason across multiple images. In this example, you will use Gemini to calculate the total cost of groceries using an image of fruits and a price list.

Run through the Image understanding across multiple images section of the notebook.

Click Check my progress to verify the objective. Image understanding across multiple images

Understanding Screens and Interfaces

Gemini can also extract information from appliance screens, UIs, screenshots, icons, and layouts. In this example, you will use Gemini to extract information from a stove to help a user navigate the UI and respond in different languages:

Run through the Understanding Screens and Interfaces section of the notebook.

Click Check my progress to verify the objective. Understanding Screens and Interfaces

Understanding entity relationships in technical diagrams

Gemini has multimodal capabilities that enable it to understand diagrams and take actionable steps, such as optimization or code generation. In this example, you will see how Gemini can decipher an entity relationship (ER) diagram, understand the relationships between tables, identify requirements for optimization in a specific environment like BigQuery, and even generate corresponding code.

Run through the Understanding entity relationships in technical diagrams section of the notebook.

Click Check my progress to verify the objective. Understanding entity relationships in technical diagrams

Recommendations based on multiple images

Gemini is capable of image comparison and providing recommendations. This may be useful in industries like e-commerce and retail. In this example, you will use Gemini to recommend which pair of glasses would be better suited to an oval-shaped face.

Run through the Recommendations based on multiple images section of the notebook.

Click Check my progress to verify the objective. Recommendations based on multiple images

Similarity/Differences

Gemini can compare images and identify similarities or differences between objects. In this example, you will use Gemini to compare two images of the same location and identify the differences between them.

Run through the Similarity/Differences section of the notebook.

Click Check my progress to verify the objective. Similarity/Differences

Generating a video description

Gemini can generate a description of a video. In this example, you will use Gemini to generate a description of a video of a video of a Mediterranean sea coast.

Run through the Generating a video description section of the notebook.

Extracting tags of objects throughout the video

Gemini can also extract tags throughout a video. In this example, you will use Gemini to extract tags of objects throughout a video of a photo shoot and generate hashtags.

Run through the Extracting tags of objects throughout the video section of the notebook.

Asking more questions about a video

Gemini can answer questions about a video. In this example, you will use Gemini to answer questions about the video and return a JSON response.

Run through the Asking more questions about a video section of the notebook.

Retrieving extra information beyond the video

Gemini can also retrieve extra information beyond the video. In this example, you will use Gemini to retrieve extra information about the video, such as asking specific questions about a train route.

Run through the Retrieving extra information beyond the video section of the notebook.

Congratulations!

You have now completed the lab! In this lab, you learned how to use the Vertex AI Gemini API to generate text from text and image(s) prompts.

Next steps / learn more

• Check out the Generative AI on Vertex AI documentation.
• Learn more about Generative AI on the Google Cloud Tech YouTube channel.
• Google Cloud 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 March 07, 2024

Lab Last Tested March 07, 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.