GSP1268

Overview

Agent Engine (formerly known as LangChain on Vertex AI or Vertex AI Reasoning Engine) is a fully managed Google Cloud service enabling developers to deploy, manage, and scale AI agents in production. Agent Engine handles the infrastructure to scale agents in production so you can focus on creating intelligent and impactful applications.

You can define Python functions that get used as tools via Gemini Function Calling. Agent Engine integrates closely with the Gen AI SDK for the Gemini model in Vertex AI, and it can manage prompts, agents, and examples in a modular way. Agent Engine is compatible with LangChain, LlamaIndex, or other Python frameworks.

In this lab, you will learn how to build and deploy an agent (model, tools, and reasoning) using the Gen AI SDK for Python. You'll build and deploy an agent that uses the Gemini Pro model, Python functions as tools, and LangChain for orchestration.

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:

• Install the Gen AI SDK for Python
• Use the Gen AI SDK to build components of a simple agent
• Test your agent locally before deploying
• Deploy and test your agent on Vertex AI
• Customize each layer of your agent (model, tools, orchestration)

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).

Note: Use an Incognito (recommended) or private browser window to run this lab. This prevents 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: Use only the student account for this lab. If you use a different Google Cloud account, you may incur charges to that 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 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 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. Note: If a pip package error occurs during the installation of the pip dependencies, please rerun the cell in the notebook.

4. Set the STAGING_BUCKET variable to your Project ID: . Make sure to include the gs:// before the Project ID.

Click Check my progress to verify the objective. Import libraries and set up the notebook.

Task 3. Build and deploy an agent

In this section, you will build and deploy an agent using the Gen AI SDK for Python. The agent consists of three components:

• Model: The Gemini Pro model
• Tools: Python functions that can be called by the model
• Orchestration: LangChain for orchestrating the reasoning

You will define the model, tools, and orchestration in the notebook, test the agent locally, and then deploy the agent to Vertex AI.

1. Run the Build and deploy an agent section of the notebook.

Click Check my progress to verify the objective. Load the Gemini Pro Model.

Click Check my progress to verify the objective. Define Python functions (tools).

Click Check my progress to verify the objective. Deploy your agent on Vertex AI.

Task 4. Customizing your agent

The example you just ran through includes the minimal amount of configuration required for each component within the agent to help you get started.

But what if you want to swap to a different Gemini model version, change the generative model parameters or safety filters, or perform additional customizations to the agent? The following example in the notebook shows some of the most common parameters that you'll want to customize in your agent. Agent Engine in Vertex AI works with Gemini model versions that support Function Calling and LangChain agents.

In this section, you will learn how to customize the model and agent components to suit your needs.

1. Run the Customizing your agent section of the notebook.

Click Check my progress to verify the objective. Model configuration.

Click Check my progress to verify the objective. Agent configuration.

Congratulations!

Congratulations! In this lab, you learned how to build and deploy an agent with Agent Engine in Vertex AI. You built and deployed an agent that uses the Gemini Pro model, Python functions as tools, and LangChain for orchestration. You also learned how to customize different layer of your agent.

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 April 28, 2025

Lab Last Tested April 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.