On the Q-Question global configuration page, you can configure large models and manage settings for speech Q&A, Q-Interpretation, and sample dataset display. This topic describes these configurations.
This feature is currently available only in the China (Hong Kong) and Malaysia sites. It will be rolled out to other sites soon.
Limits
Only organization administrators and users with a custom role that includes the Q-Question-Centralized Management permission can manage global configurations.
Configuration entry
Navigate to Intelligent Q > Q-Question > Global configuration.
Speech Q&A switch configuration
When this feature is enabled, users can ask questions using speech input in Q-Question.
Q-Interpretation
When this feature is enabled, users can use the configured large model to analyze data and generate insights. For more information, see Dashboard Q-Interpretation.
Display sample dataset
When you enable this feature, the system displays sample datasets.
A dataset with the Sample flag in the upper-left corner is a sample dataset. You can select a sample dataset to perform data queries. For more information, see Preview and select datasets.
Auto-focus on dataset
When you enable this option, if a user's first question hits a single dataset, Q-Question automatically focuses all subsequent questions on that dataset. This removes the need for repeated selections. If you disable this option, the system intelligently selects the most relevant dataset for each new question.
You can select the Query based on all available data and Query based on analysis subjects options as needed.
Query based on all available data
When enabled, if a question hits a single dataset while you query all available data, subsequent questions are automatically focused on that dataset. You do not need to select it again.
When disabled, Q-Question does not automatically focus on a dataset. Instead, the system intelligently selects the most relevant dataset for each question.
Query based on analysis subjects
When enabled, if a question hits a single dataset while you query based on analysis subjects, subsequent questions are automatically focused on that dataset. You do not need to select it again.
When disabled, Q-Question does not automatically focus on a dataset. Instead, the system intelligently selects the most relevant dataset for each question.
Interactive dataset selection
When you enable this option, if a question hits multiple datasets, Q-Question provides a selection UI for you to manually select the dataset. If you disable this option, the system automatically selects the most relevant datasets to provide an answer.
You can select the Query based on all available data and Query based on analysis subjects options as needed.
Query based on all available data
Enabled: On the [All] datasets page, if a question hits multiple highly relevant datasets, the system lists the candidate datasets. Manually select one or more datasets to continue.
Disabled: The system automatically selects the most relevant dataset to provide an answer. No manual selection is required.
Query based on analysis subjects
Enabled: On the [Analysis Subject] datasets page, if a question hits multiple datasets under the current analysis subject, the system lists the candidate datasets. Manually select one or more datasets to continue.
Disabled: The system automatically selects the most relevant dataset in the current subject to provide an answer. No manual selection is required.