Troubleshooting Gemini in Looker issues

Preview

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

Note: Gemini in Looker features are available at no additional cost during Preview for a limited time only. At the end of this Preview period, you may be required to purchase Gemini in Looker features for an additional fee.

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.

This page describes the following topics as they relate to Gemini in Looker features:

• Known limitations, troubleshooting, and tips for writing better prompts for each task that is supported by Gemini in Looker
• Troubleshooting that is related to Gemini in Looker enablement
• How to submit in-product feedback about Gemini in Looker tasks
• How to get support
• Related resources

Troubleshooting resources

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

Gemini in Looker resources and troubleshooting

Task performed with Gemini assistance	Available platforms	Limitations of Gemini assistance	Troubleshooting Gemini in Looker tasks	Sample Gemini prompts
Query data in natural language with Conversational Analytics	Looker (original) Looker (Google Cloud core)	Limitations on visualizations Data source-specific limitations Supported questions	User and platform requirements Setting up a data source
Write LookML using natural language	Looker (original) Looker (Google Cloud core)		Tips for using Gemini in the Looker IDE User and platform requirements	Sample prompt: Create a dimension based on longitude or latitude Sample prompt: Create a measure for today's total sales
Create custom Looker visualizations using natural language	Looker (original) Looker (Google Cloud core)	Visualization Assistant is available only for HighCharts-based visualizations.	Creating successful prompts User and platform requirements	Sample prompts

Gemini in Looker enablement troubleshooting

Platform	Platform requirements to enable Gemini in Looker	Permissions required to enable Gemini in Looker	Troubleshooting
Looker (original)	The instance must be Looker-hosted. The instance must be on Looker 25.0 or later to enable Gemini in Looker. The instance must be on Looker 25.6 or later to use Conversational Analytics. The instance must be on Looker 25.16 or later to manage and use Conversational Analytics data agents that use a Looker Explore as a data source. We recommend that instances participating in Extended Support Release Program are on Looker 25.6 or later to use Conversational Analytics.	Looker Admin role	Gemini in Looker supports English-language prompts and responses only. Make sure that the required permissions are assigned to the appropriate users. Only the Gemini in Looker roles and permissions that apply to the Conversational Analytics API can be assigned to embed users.
Looker (Google Cloud core)	Conversational Analytics doesn't support Looker (Google Cloud core) instances that use CMEK or VPC Service Controls. Connecting Conversational Analytics in Looker Studio Pro to a private connections Looker (Google Cloud core) instance that is within a VPC Service Controls perimeter isn't supported and doesn't meet VPC Service Controls compliance requirements.	Looker Admin (roles/looker.admin) IAM role on the project in which the instance resides	Make sure that the Trusted Testers settings are enabled. Gemini in Looker supports English-language prompts and responses only. Make sure that the required permissions are assigned to the appropriate users. Only the Gemini in Looker roles and permissions that apply to the Conversational Analytics API can be assigned to embed users or users of an Embed Looker (Google Cloud core) edition instance.

How to submit in-product feedback

Submit in-product feedback to rate the quality and accuracy of Gemini in Looker previews.

You can submit in-product feedback about each Gemini in Looker task by using the thumb_up thumbs-up and thumb_down thumbs-down icons.

How to get support

Reach out to Support if you encounter any of the following issues:

• Gemini in Looker features are slow to respond or generate content.
• Gemini in Looker features return blank or empty responses.
• The instance, report, or chart returns a timeout error.
• The instance or page returns an internal server error.

Be sure to include a clear description of the problem and the expected behavior, the steps that you took prior to encountering the issue, and any additional relevant details.

For details on how to contact Support, see the documentation for your Looker platform type:

• Looker (original)
• Looker (Google Cloud core)

Related resources

• Write better prompts for Gemini for Google Cloud
• Gemini for Google Cloud limitations