Write code in a Colab Enterprise notebook with Gemini assistance

Write code in a Colab Enterprise notebook with Gemini assistance

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

As an early-stage technology, Gemini can generate output that seems plausible but is factually incorrect. We recommend that you validate all output from Gemini before you use it. For more information, see Gemini for Google Cloud and responsible AI.

This document describes how you can use Gemini in Colab Enterprise, which is a product in the Gemini for Google Cloud portfolio, to help you write code in a Colab Enterprise notebook.

Learn how and when Gemini for Google Cloud uses your data.

This document is intended for data analysts, data scientists, and data developers who work with Colab Enterprise. It assumes you have knowledge of how to write code in a notebook environment.

Before you begin

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

3. Make sure that billing is enabled for your Google Cloud project.

4. Enable the Vertex AI, Cloud AI Companion, Dataform, and Compute Engine APIs.

   Enable the APIs

5. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

6. Make sure that billing is enabled for your Google Cloud project.

7. Enable the Vertex AI, Cloud AI Companion, Dataform, and Compute Engine APIs.

   Enable the APIs

Required roles

To ensure that your user account has the necessary permissions to write code with Gemini assistance in a Colab Enterprise notebook, ask your administrator to grant your user account the following IAM roles on the project:

• Colab Enterprise User (roles/aiplatform.colabEnterpriseUser)
• Cloud AI Companion User (roles/cloudaicompanion.user)

For more information about granting roles, see Manage access.

Your administrator might also be able to give your user account the required permissions through custom roles or other predefined roles.

One or more of the required roles includes the dataform.repositories.list permission. Users who are granted the dataform.repositories.list permission or the Code Creator (roles/dataform.codeCreator) role in a project can list the names of code assets in that project by using the Dataform API or the Dataform command-line interface (CLI). Non-administrators using BigQuery Studio can only see code assets that they created or that were shared with them.

Set up Gemini in Colab Enterprise

To use Gemini features:

1. Complete the steps to set up Gemini in Colab Enterprise your Google Cloud project. Gemini features aren't visible until setup is complete.

2. In the Google Cloud console, go to the Colab Enterprise Notebooks page.

   Go to Notebooks

3. If you haven't enabled the required APIs yet, click Enable and complete the dialog to enable them.

   

4. In the toolbar, click the pen_spark Help me code button and select the features that you want to use.

   

Use code generation

To generate code using Gemini for Google Cloud:

1. In the Google Cloud console, go to the Colab Enterprise Notebooks page.

   Go to Notebooks

2. In the Region menu, select the region that contains your notebook.

3. On the My notebooks tab, click the notebook that you want to open.

4. In the toolbar, click the pen_spark Help me code button and select Code generation if it isn't already selected.

5. In a blank code cell of your notebook, click generate.

6. In the pen_spark Generate field, type a description of the code that you want to generate, and then press Enter.

7. To close the Generate panel, click Close.

Use code completion

To use code completion in a Colab Enterprise notebook, do the following:

1. In the Google Cloud console, go to the Colab Enterprise Notebooks page.

   Go to Notebooks

2. In the Region menu, select the region that contains your notebook.

3. On the My notebooks tab, click the notebook that you want to open.

4. In the toolbar, click the pen_spark Help me code button and select Code completion if it isn't already selected.

5. In a code cell of your notebook, start entering code. Colab Enterprise suggests a potential way to complete your code in gray italic text.

   For example, if you enter import p, Colab Enterprise might suggest a code completion that imports pandas as pd followed by a line that reads a CSV file and stores the contents in a pandas dataframe.
   

6. To accept the suggested code completion, press Tab.

Turn off Gemini features

To turn off Gemini features in Colab Enterprise, do the following:

1. In the Colab Enterprise toolbar, click the pen_spark Help me code button.

2. Clear the Gemini features that you want to turn off.

Troubleshoot

This section shows you how to resolve issues with using Gemini in Colab Enterprise.

Gemini features not working

When you type in a Colab Enterprise notebook, code completion suggestions don't appear. Or, the pen_spark Help me code button doesn't appear above a code cell.

In your Colab Enterprise settings, you might have turned off the Automatically trigger code completions setting.

To resolve this issue, do the following:

1. Click  Toggle header visibility.
2. On the Tools menu, click Settings.
3. Click Editor.
4. Select Automatically trigger code completions.
5. Click Save.

What's next

• Learn more about the types of generative AI assistance available in Gemini for Google Cloud.

• Learn how Gemini for Google Cloud uses your data.