GSP1293

Overview

In this lab, you will explore the code execution capabilities of , one of Google DeepMind's new multimodal Gemini models. This model provides significant improvements in speed, quality, and advanced reasoning, including enhanced understanding, coding, and instruction following.

A key feature of this model is code execution, which is the ability to generate and execute Python code directly within the API. If you want the API to generate and run Python code and return the results, you can use code execution as demonstrated in this lab.

This code execution capability enables the model to generate code, execute and observe the results, correct the code if needed, and learn iteratively from the results until it produces a final output. This is particularly useful for applications that involve code-based reasoning such as solving mathematical equations or processing text.

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 generate and execute code using the Gemini API in Vertex AI and the Google Gen AI SDK for Python with the model.

You will complete the following tasks:

• Generating and running sample Python code from text prompts
• Exploring data using code execution in multi-turn chats
• Using code execution in streaming sessions

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 are made available to you.

This hands-on lab lets you do the lab activities in a real cloud environment, not in a simulation or demo environment. It does so by giving you new, temporary credentials 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).

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

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 dialog opens for you to select your payment method. On the left is the Lab Details pane 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 pane.

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 pane.

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 access Google Cloud products and services, click the Navigation menu or type the service or product name in the Search field.

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 section of the notebook. The Project ID and Location are pre-configured for you.

Click Check my progress to verify the objective. Set up the notebook.

Task 3. Working with code execution in Gemini

In this section, you will use the Gemini API to generate and execute Python code.

Load the Gemini model

The following code in the notebook loads the model. You can learn about all Gemini models on Vertex AI by visiting the documentation.

1. Run the Load the Gemini model section of the notebook.

Define the code execution tool

The following code in the notebook initializes the code execution tool by passing code_execution in a Tool definition. Later you'll register this tool with the model so it can use it to generate and run Python code.

1. Run the Define the code execution tool section of the notebook.

Generate and execute code

The following code in the notebook sends a prompt to the Gemini model, asking it to generate and execute Python code to calculate the sum of the first 50 prime numbers. The code execution tool is passed in so the model can generate and run the code.

1. Run the Generate and execute code section of the notebook.

View the generated code

The following code in the notebook iterates through the response and displays any generated Python code by checking for part.executable_code in the response parts.

1. Run the View the generated code section of the notebook.

View the code execution results

The following code in the notebook iterates through the response and displays the execution result and outcome by checking for part.code_execution_result in the response parts.

1. Run the View the code execution results section of the notebook.

Click Check my progress to verify the objective. Working with code execution in Gemini.

Task 4. Code execution in a chat session

This section shows how to use code execution in an interactive chat with history using the Gemini API. You can create a chat session, enabling the model to generate and run Python code. You'll start by asking the model to generate sample time series data with noise and output a sample of 10 data points.

You can then iterate through the response to display any generated code and execution results. Next, you'll ask the model to add a smoothed data series to the time series data and display the results. Finally, you'll ask the model to generate descriptive statistics for the time series data and display the results.

1. Run the Code execution in a chat session section of the notebook.

Click Check my progress to verify the objective. Code execution in a chat session.

Task 5. Code execution in a streaming session

You can also use the code execution functionality with streaming output from the Gemini API. The following code demonstrates how the Gemini API can generate and execute code while streaming the results.

1. Run the Code execution in a streaming session section of the notebook.

Click Check my progress to verify the objective. Code execution in a streaming session.

Congratulations!

Congratulations! You have successfully learned how to generate and execute Python code with , including how to stream the output. This capability allows you to create more dynamic and interactive applications. You can now leverage these skills to build innovative solutions and streamline your workflows. Keep exploring the possibilities of and discover how it can empower your projects!

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
• Explore the Vertex AI Cookbook for a curated, searchable gallery of notebooks for Generative AI.
• Explore other notebooks and samples in the Google Cloud Generative AI repository.

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 October 28, 2025

Lab Last Tested October 28, 2025

Copyright 2025 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.