GSP1274

Overview

In today's information-driven world, the volume of digital documents generated daily is staggering. From emails and reports to legal contracts and scientific papers, businesses and individuals alike are inundated with vast amounts of textual data. Extracting meaningful insights from these documents efficiently and accurately has become a paramount challenge.

Document processing involves a range of tasks, including text extraction, classification, summarization, and translation, among others. Traditional methods often rely on rule-based algorithms or statistical models, which may struggle with the nuances and complexities of natural language.

In this lab, you will learn how to use the Gemini API in Vertex AI with the Google Gen AI SDK to process PDF documents.

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:

• Install the Google Gen AI SDK for Python
• Extract structured entities from an unstructured document using Gemini
• Classify document types using Gemini
• Combine classification and entity extraction into a single workflow using Gemini
• Summarize documents using Gemini

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. Experiment with entity extraction and document classification

Named Entity Extraction is a technique of Natural Language Processing to identify specific fields and values from unstructured text. For example, you can find key-value pairs from a filled out form, or get all of the important data from an invoice categorized by the type.

Document classification is the process for identifying the type of document. For example, invoice, W-2, receipt, etc.

Entity extraction

In this section, you will see an example of how Gemini can be used to retrieve information from a document.

1. Run through the Entity Extraction section of the notebook.

Document classification

In this section, you see how Gemini can be used to review a document and specify its type from a specified list.

1. Run through the Document Classification section of the notebook.

Chaining classification and extraction

These techniques can also be chained together to extract any number of document types. For example, if you have multiple types of documents to process, you can send each document to Gemini with a classification prompt, then based on that output, you can write logic to decide which extraction prompt to use.

1. Run through the Chaining Classification and Extraction section of the notebook.

Click Check my progress to verify the objective. Experiment with entity extraction and document classification

Task 4. Experiment with document question answering and summarization

In this section, you will see how Gemini can be used to answer questions about a document and summarize its contents.

Document question answering

1. Run through the Document Question Answering section of the notebook.

Document summarization

In this section, you will see how Gemini can be used to summarize or paraphrase a document's contents.

1. Run through the Document Summarization section of the notebook.

Click Check my progress to verify the objective. Experiment with document question answering and summarization

Task 5. Experiment with table parsing from documents

In this section, you will see how Gemini can parse contents of a table and return it in a structured format, such as HTML or markdown.

1. Run through the Table parsing from documents section of the notebook.

Click Check my progress to verify the objective. Experiment with document question answering and summarization

Task 6. Experiment with document translation and comparison

In this section, you will see how Gemini can translate documents between languages.

Document translation

1. Run through the Document Translation section of the notebook.

Document comparison

In this section, you will see how Gemini can compare and contrast the contents of multiple documents.

Note: when working with multiple documents, the order can matter and should be specified in your prompt.

1. Run through the Document Comparison section of the notebook.

Click Check my progress to verify the objective. Experiment with document question answering and summarization

Congratulations!

You have now completed the lab! In this lab, you used the Gemini 2.0 Flash model with the Google Gen AI SDK to extract structured entities from an unstructured document.

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 19, 2025

Lab Last Tested May 19, 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.