Gemini in Looker overview

Gemini in Looker represents a series of features in the Gemini for Google Cloud portfolio that provides generative AI-powered assistance to help you analyze and gain valuable insights from your data.

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

For more information about the types of tasks that Gemini in Looker can assist with, see the Gemini in Looker overview documentation page.

Available features in Looker

When Gemini in Looker is enabled, Looker users can perform the following tasks in a Looker (Google Cloud core) instance or a Looker (original) instance:

  • Ask questions about and converse with your data by using Conversational Analytics: Gemini in Looker lets you ask questions about your data source by using natural language. Gemini returns Looker charts or data tables that are based on your query. You can learn more about how your response was generated and save your conversation for future reference. Conversational Analytics is available when the Conversational Analytics setting is enabled for your instance.
  • Generate custom Looker visualizations: Gemini in Looker lets you customize formatting options for Looker visualizations by using natural language. Gemini generates JSON formatting options from text-based prompts, which you can apply to your visualizations. You can also use prompts as a starting point for creating templates and patterns for more complex customizations and then manually update the visualization formatting options. This feature is available when the Looker Assistants setting is enabled for your instance.
  • Access advanced analytics with the Code Interpreter in Conversational Analytics to translate your natural language questions into Python code and execute that code to provide advanced analysis and visualizations. The Code Interpreter is available when the Code Interpreter and Conversational Analytics settings are enabled for your instance.
  • Generate LookML [Preview]: Gemini in Looker assists you in generating LookML parameters. Gemini suggests LookML parameters that are based on a natural language prompt, which you can add to your project files.
  • Generate a summary of an Explore [Preview]: Gemini in Looker generates a summary and an analysis of an Explore.

Enable features in Looker

To access these features in a Looker (original) instance, a Looker admin must enable Gemini in Looker in the Looker (original) instance settings. The instance must be on Looker 25.2 or later and be Looker-hosted. Conversational Analytics is available on Looker instances on 25.0 or later. A Looker admin can use the same instructions to subsequently disable features.

To access these features in a Looker (Google Cloud core) instance, a user with the Looker Admin (roles/looker.admin) IAM role must enable Gemini in Looker in the Looker (Google Cloud core) instance settings in the Google Cloud console. A user with the Looker Admin IAM role can use the same instructions to subsequently disable features.

Grant permissions to use Gemini in Looker features

To use any Gemini in Looker features, users must be granted a Looker role that contains permissions to perform the Gemini-assisted task. These permissions are summarized in the following list:

  • To query Looker data, or to create a data agent with Conversational Analytics or with the Conversational Analytics API, you must be assigned a Looker role that contains the access_data permission for the model that you're querying. Additional permissions are required to manage and use data agents with Conversational Analytics in Looker. Conversational Analytics is available when the Conversational Analytics setting is enabled.
  • To use the Visualization Assistant to create custom visualizations with Gemini assistance, you must be assigned a Looker role that contains the can_override_vis_config permission. The Visualization Assistant is available when the Looker Assistants setting is enabled.
  • To use the Code Interpreter in Conversational Analytics to translate your natural language questions into Python code and execute that code to provide advanced analysis and visualizations, you must be a assigned a role that has the same permissions that are required to use Conversational Analytics. The Code Interpreter is available when the Code Interpreter setting is enabled.
  • To write LookML with Gemini assistance, you must be assigned a Looker role that contains the develop permission for at least one model in a LookML project. This feature is available when the LookML Assistant setting is enabled.
  • To generate Explore summaries, including the suggested purpose of the Explore and the types of data that are used in the query, you must have a role that contains the develop permission for at least one model in the LookML project and the explore permission to view and interact with Explores. This feature is available when the Explore NL Summary setting is enabled.

Where to interact with Gemini in Looker features

After Gemini in Looker features are enabled, you can seek Gemini assistance to perform the following tasks in Looker:

Understand the compliance capabilities of Gemini in Looker features

Google Cloud Preview features are generally not in scope for formal compliance certification support and are not recommended for use with regulated workloads or sensitive data unless otherwise stated.

Conversational Analytics is not yet included in FedRAMP High or FedRAMP Medium authorization boundaries. Prior to enabling the Gemini in Looker setting for your Looker instance, discuss with your authorizing body whether Gemini for Google Cloud's compliance offerings meet the needs of your organization.

For Looker (Google Cloud core) instances, each Assured Workloads control package that becomes available will add Gemini in Looker features as default offerings as that package's change requirements and processes are met. Conversational Analytics in Looker respects the compliance capabilities of the associated Looker (Google Cloud core) instance, with the following exception:

Data Residency (DRZ) support, specifically for data-at-rest, is available to all Looker customers. All data-at-rest that is associated with Conversational Analytics resides strictly within the Looker instance and is confined to a single region. Data in transit may be processed using a global service.