Set up Amazon Q Developer for your users - Amazon SageMaker
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Set up Amazon Q Developer for your users

Amazon Q Developer is a generative AI conversational assistant. With Amazon Q Developer, your users can:

  • Receive step-by-step guidance on using SageMaker features independently or in combination with other Amazon services.

  • Get sample code to get started on your ML tasks such as data preparation, training, inference, and MLOps.

  • Receive troubleshooting assistance to debug and resolve errors encountered while running code in JupyterLab.

Important

Prerequisites:

To set up Amazon Q within JupyterLab, you must have:

  • An Amazon SageMaker domain set up for your organization with IAM Identity Center configured as the means of access.

  • An Amazon Q Developer Pro subscription.

The Set up for organizations is an advanced setup for the Amazon SageMaker domain that lets you use IAM Identity Center. For information about how you can set up the domain and information about setting up IAM Identity Center, see Custom setup to Amazon SageMaker.

Amazon Q Developer Pro is a paid subscription service. For information about subscribing to Amazon Q Developer Pro, see Subscribing to Amazon Q Developer Pro.

You can set up Amazon Q Developer within a new domain or an existing domain. Use the following information to set up Amazon Q Developer.

Set up in an existing domain

If you're updating a domain that you've already set up for your organization, you need to update it to use Amazon Q Developer. To update the domain to use Amazon Q Developer, use the following Amazon Command Line Interface command from your local machine:


aws --region Amazon Web Services Region sagemaker update-domain --domain-id domain-id --domain-settings-for-update "AmazonQSettings={Status=ENABLED,QProfileArn=Q-Profile-ARN}"

You can find the Q Profile ARN on the Q Developer Settings Page.

Set up in a new domain

When setting up Amazon Q Developer in a new domain, you can either use the Amazon Web Services Management Console or the following Amazon Command Line Interfacecommand from your local machine:


aws --region Amazon Web Services Region sagemaker create-domain --domain-id domain-id --domain-name "example-domain-name" --vpc-id example-vpc-id --subnet-ids example-subnet-ids --auth-mode SSO --default-user-settings "ExecutionRole=arn:aws:iam::111122223333:role/IAM-role,--domain-settings "AmazonQSettings={status=ENABLED,qProfileArn=Q-profile-ARN" --query example-domain-ARN --output text

You can find the Q Profile ARN on the Q Developer Settings Page.

You can use the following Amazon CLI to disable Amazon Q Developer:


aws --region Amazon Web Services Region sagemaker update-domain --domain-id domain-id --domain-settings-for-update "AmazonQSettings={Status=DISABLED,QProfileArn=Q-Profile-ARN}"

We recommend using the latest version of the Amazon Command Line Interface. For information about updating the Amazon CLI, see Install or update to the latest version of the Amazon Command Line Interface.

If you need to establish a connection between Amazon Q Developer and your VPC, see Creating an interface VPC endpoint for Amazon Q .

Note

Amazon Q Developer has the following limitations:

  • It doesn't support shared spaces.

  • The inline code suggestions of Amazon Q Developer in JupyterLab detects whether a code suggestion might be too similar to publicly available code. The reference tracker can flag such suggestions with a repository URL and project license information or optionally filter them out. You can then more easily find and review the referenced code and see how it is used in the context of another project before deciding to use it. All references are logged for you to review later to ensure that your code flow is not disturbed, and you can keep coding without interruption.

    The chat feature of Amazon Q Developer in JupyterLab currently doesn’t make suggestions that include references to known licensed open source code. The feature currently filters out suggestions that include references to known licensed open source code.

    For more information about code references, see Using code references - Amazon Q Developer and AI Coding Assistant - Amazon Q Developer FAQs.

  • Amazon Q processes all user interaction data within the US East (N. Virginia) Amazon Web Services Region. For more information about how Amazon Q processes data and the Amazon Web Services Regions it supports, see Supported Regions for Amazon Q Developer.