With Conversational Analytics, you can use a Looker Explore 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:
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 use Conversational Analytics in Looker Studio, 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.
To use Conversation Analytics within a Looker instance, you and your Looker instance must meet the following requirements:
- A Looker admin must enable Gemini in Looker for the Looker instance.
- A Looker admin must grant you the Gemini role in the Looker instance. You must also have a role that contains the
access_data
permission for the model that you are querying.
To use a Looker Explore as a data source for Conversational Analytics, you must meet the following requirements:
- 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.
Use a Looker Explore as a data source
Looker Explores appear in the list of available data sources on the Chat with your data page. To use a new Looker Explore as a data source in Conversational Analytics, follow these steps:
- Navigate to Conversational Analytics.
- On the Chat with your data page, select the Data sources tab.
- Select Connect to data, and then select Looker from the drop-down menu.
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.
If you're connecting to a Looker instance for the first time, click Connect Looker Account.
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.
Once you have linked to a Looker instance, select an Explore from the list, and then click Connect to start a conversation.
Converse with a Looker data source
Once you complete the steps to use a Looker Explore as a data source, you can ask questions about your Looker data.
When you converse with your data, the collapsible
Data panel shows the name of the Looker Explore that is being used by the conversation. The Data panel panel also provides the following options:- View fields: View the Explore in Looker in a new browser window by clicking View fields.
- New conversation: Start a new conversation with the Looker Explore that the current conversation is using.
Ask a question
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
Visualizations
If the response to your query includes a visualization, the result shows the following tabs:
- Chart: Shows the rendered Looker visualization.
- Table: Shows the underlying data table. You can change the data table sort order by clicking on the Sort by arrows next to the column names. Changing the sort order of the Table columns will not alter the visualization.
Limitations on visualizations
Conversational Analytics leverages Vega-lite for conversation chart generation. The following Vega chart types are fully supported:
- Line chart (one or more series)
- Area chart
- Bar chart (horizontal, vertical, stacked)
- Scatter plot (one or more groups)
- Pie chart
The following Vega chart types are supported, but you may encounter unexpected behavior when rendering them:
- Maps
- Heatmaps
- Charts with tooltips
Chart types that exist outside the Vega catalog are not supported. Any charts that are not specified in this section are considered unsupported.
Determine how an answer was calculated
To see how Conversational Analytics arrived at an answer or created a visualization, click
How was this calculated? below the response.When you click How was this calculated?, Conversational Analytics displays a Text section. The Text section provides a plain text explanation of the steps that Conversational Analytics took 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.
Open in a Looker Explore
To open the query results as an Explore within the connected Looker instance, click
Open in Explore within the query results.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
Manage queries within a conversation
When you converse with data, you can manage the conversation by stopping an active query response while it is running or by deleting the most recent question and its response.
Stop a query response
To stop running a query after you've sent a message, click
The query was cancelled.
Delete the most recent question
To delete the most recent question and its response, follow these steps:
- Hold your cursor over the most recent question, and then click Delete message.
- In the Permanently delete message? dialog, click Delete to permanently delete the question and its response.