GSP1279

Overview

This lab guides you through building a multimodal question answering system from the ground up using Google's Vertex AI and the powerful Gemini family of models. You'll gain a deep understanding of how such systems work by constructing one yourself, without relying on pre-built tools or libraries. This hands-on experience demystifies the process and equips you with the knowledge to customize and optimize your own question answering systems in the future. You'll also explore the advantages of multimodal Retrieval Augmented Generation (RAG) over traditional text-based RAG, discovering how incorporating visual information enhances knowledge access and reasoning capabilities.

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 build a document search engine using multimodal retrieval augmented generation (RAG):

• Extract and store metadata of documents containing both text and images, and generate embeddings the documents
• Search the metadata with text queries to find similar text or images
• Search the metadata with image queries to find similar images
• Using a text query as input, search for contextual answers using both text and images

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.

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

Task 3. Building metadata of documents containing text and images

In this section, you will import helper functions to build metadata, load pre-computed metadata of text and images from a source document, and inspect the processed text and image data.

1. Run through the Building metadata of documents containing text and images section of the notebook.

Click Check my progress to verify the objective. Import helper functions to build metadata

Load pre-computed metadata of text and images Inspect the processed text and image data

Task 4. Text search

In this section, you will use the Gemini model to search with a simple question and see if the simple text search using text embeddings can answer it. You will also use the multimodal capability of the Gemini model to search for an image similar to the text query.

1. Run through the Text search sections of the notebook.

Click Check my progress to verify the objective. Text search

Task 5. Image search

Imagine searching for images, but instead of typing words, you use an actual image as the clue. Think of it like searching with a mini-map instead of a written address. It's a different way to ask, "Show me more stuff like this". So, instead of typing "various example of Gemini 2.0 long context", you show a picture of that image and say, "Find me more like this"

In this section, you will only be finding similar images that show the various features of Gemini in a single document. However, you can scale this design pattern to match (find relevant images) across multiple documents.

1. Run through the Image search sections of the notebook.

Click Check my progress to verify the objective. Image search

Task 6. Building Multimodal QA System with retrieval augmented generation (mRAG)

In this last task, you will bring everything together to implement multimodal RAG. To implement multimodal RAG, the user provides a text query related to information present in both text and images within the document. Text chunks similar to the query are retrieved from document pages using a text search method. Simultaneously, an image search identifies images with descriptions matching the query.

The combined relevant text and images serve as context for Gemini, which generates an answer to the query, potentially referencing specific instructions. Finally, citations indicate the text and images used to formulate the response.

1. Run through the Building Multimodal QA System with retrieval augmented generation (mRAG) sections of the notebook.

Click Check my progress to verify the objective. Building Multimodal QA System with retrieval augmented generation (mRAG)

Congratulations!

Congratulations! In this lab, you learned how to build a multimodal question answering system using the Gemini API in Vertex AI. You built a document search engine that can search for text and images using text and image queries. You also built a multimodal question answering system that can answer questions using both text and images.

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 May 22, 2025

Lab Last Tested May 22, 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.