Building Knowledge Graphs with Gemini

1. Overview

In this lab, you will explore the following tasks:

• 1️⃣ Extract knowledge from raw, unstructured documents
• 2️⃣ Generate and visualize knowledge graphs for book narratives
• 3️⃣ Generalize building knowledge graphs to other domains

Here is an example of what you'll achieve:

What you'll learn

• How to prototype with open prompts to develop intuition
• How to craft increasingly specific prompts using a tabular-extraction strategy
• How to structure inputs to move towards production-ready and generalizable code
• How to structure and optimize outputs for faster and cheaper generations
• How to add data visualization for easier interpretation of responses
• How to generalize to other domains

What you'll need

• Familiarity running Python in a notebook (in Colab or any other Jupyter environment)
• A Google Cloud project or a Gemini API key with billing enabled

ℹ️ The total cost to run the lab from start to finish is less than 1 USD.

Let's get started...

2. Before you begin

To use the Gemini API, you have two main options:

1. Via Agent Platform (formerly Vertex AI) with a Google Cloud project
2. Via Google AI Studio with a Gemini API key

🛠️ Option 1 - Gemini API via Agent Platform

Requirements:

• A Google Cloud project
• The Agent Platform API must be enabled for this project

Enable the Agent Platform API

🛠️ Option 2 - Gemini API via Google AI Studio

Requirement:

• A Gemini API key

Learn more about getting a Gemini API key from Google AI Studio.

3. Run the notebook

Choose your preferred tool to open the notebook:

🧰 Tool A - Open the notebook in Colab

Open in Colab

💡 This is the most straightforward tool to run the notebook directly from your browser (zero configuration required). It also allows you to easily save and manage it in your Google Drive.

🧰 Tool B - Open the notebook in Colab Enterprise or Workbench

Open in Colab Enterprise Open in Workbench

💡 This might be preferred if you already have a Google Cloud project configured with a Colab Enterprise or Workbench instance.

🧰 Tool C - Get the notebook from GitHub and run it in your own environment

Get the notebook

⚠️ You will need to get the notebook from GitHub (or clone the repository) and run it in your own Jupyter environment.

🗺️ Notebook table of contents

For easier navigation, make sure to expand and use the table of contents. Example:

🏁 Run the notebook

You are ready. You can now follow and run the notebook. Have fun!...

4. Congratulations!

Congratulations on completing the codelab!

Learn more

• Complete the Multimodal Video Transcription with Gemini codelab.
• Explore additional use cases in the Agent Platform Prompt Gallery.
• Stay updated with the Agent Platform Release Notes.