Use the Conversational Analytics Looker connector

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.

With Conversational Analytics, you can create a data source directly from a specific Looker Explore. You can then use that data source to start a conversation, or you can configure a data agent that lets you ask questions about the Explore's data with natural language.

This page guides you through the following processes:

• Create a data source from a Looker Explore
• Converse with a Looker data source

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

Before you begin

To create a data source directly from a Looker and use it within Conversational Analytics, you must meet the following requirements:

• You must be a user under a Looker Studio Pro subscription. Looker Studio Pro licenses are available at no cost to Looker users.
• An administrator must have enabled Gemini in Looker for Looker Studio.
• The Looker connector must be enabled for the Looker instance that you are connecting to within Conversational Analytics. To enable the Looker connector, your Looker instance must meet the prerequisites that are described in Connecting to Looker Studio.

For more details about Looker instance requirements and limitations of the Looker connector, see Limits of the Looker connector.

Create a data source from a Looker Explore

To create a data source directly from a Looker Explore in Conversational Analytics, follow these steps:

1. Navigate to Conversational Analytics.
2. On the Chat with your data page, select the Data sources tab.
3. Select Connect to data, and then select Looker from the drop-down menu.

4. In the Connect to a Looker Instance section, in the Enter Looker Instance URL field, enter the URL for your Looker instance. If the instance URL is invalid or doesn't meet the Looker connector requirements, Conversational Analytics displays an error message.

   Note: If you've previously connected a Looker instance, you can select that instance from the Saved Looker Instance list.

5. If you're connecting to a Looker instance for the first time, click Connect Looker Account.

6. If Conversational Analytics displays the Link your Google Account and Looker window, review the information about how Looker Studio will access your Looker account. To link your accounts and proceed, select Agree and continue.

7. Once you have connected to a Looker instance, select an Explore from the list, and then click Connect to start a conversation.

Note: You can also create a data source directly from a Looker Explore when you create a new data agent.

Converse with a Looker data source

Once you create a data source, you can ask questions about your Looker data.

To ask a question, type your query in the send_spark Ask a question field at the bottom of the screen.

Caution: Field names in conversation results are displayed without labels or formatting.

Visualizations

Responses that include visualizations will have two results tabs: Chart and Table.

• Chart: Shows the rendered Looker visualization.
• Table: Shows the underlying data table. You can change the data table sort order by clicking on the arrow_downward arrow_upward Sort by arrows next to the column names. Changing the sort order of the Table columns will not alter the visualization.

Note: Certain visualization types may not be supported by Conversational Analytics.

Determine how an answer was calculated

To see how Conversational Analytics arrived at an answer or created a visualization, select How was this calculated? below the response. The How was this created? section includes the following tabs:

• Text: Provides a plain text explanation of the steps that were taken by Conversational Analytics to arrive at the given answer. This explanation includes the raw field names that were used, the calculations that were done, the filters that were applied, the sort order, and other details. explore Open in Explore opens the query in a Looker Explore in a new browser window.
• Code: Provides the JSON block of fields and filters that was sent to Looker. explore Open in Explore opens the query in a Looker Explore in a new browser window.

The Data panel

The collapsible storage Data panel shows the name of the Looker Explore that is being used by the conversation. You can view the Explore in Looker in a new browser window by clicking open_in_new View fields.

Supported questions

Conversational Analytics supports questions that can be answered by a single visualization, for example:

• Metric trends over time
• Breakdown or distribution of a metric by dimension
• Unique values for one or more dimensions
• Single metric values
• The top dimension values by metric

Conversational Analytics doesn't yet support questions that can only be answered with the following types of complicated visualizations:

• Percent change of a metric over time, including period-over-period analysis
• Prediction and forecasting
• Advanced statistical analysis, including correlation and anomaly detection