Skip to main content

Generative AI Preview

To help you manage and query data in your Dremio Sonar project, Generative AI is an artificial intelligence capable of generating labels, wikis, and SQL statements.

Opting into and enabling Generative AI provides you access to the Text-to-SQL experience, generated labels and wikis, and other Generative AI features as they become available. See Dremio Preferences for the steps on how to enable Generative AI for each project that you want to use it in.

Text-to-SQL Experience

Using Text-to-SQL allows you to effortlessly convert natural language queries into SQL directly within the SQL Runner. The Text-to-SQL translation is based on a semantic understanding of metadata and data, resulting in the industry’s most accurate SQL generation. The image below is an example of a generated SQL statement:

This is a screenshot showing the generated SQL using Text-to-SQL.

To try out this feature, see the Analyzing Data Using Text-to-SQL tutorial.

Generating Labels and Wikis

By generating labels and wikis for your datasets, you can minimize the need for manual profiling and cataloging.

In order to generate a label, Generative AI bases its understanding on your schema by considering other labels that have been previously generated and those that have been created by other users. The image below is an example of a dataset with generated labels:

This screenshot is showing the labels generated.

In order to generate a wiki for a dataset, Generative AI takes your data into account by determining how the columns within the dataset relate to each other and to the dataset as a whole. The image below is an example of a generated wiki:

This screenshot is showing a generated wiki.

To try out these features, see the Generating Labels and Wikis tutorial.

Data Privacy

  • Neither Dremio nor our trained model partner (OpenAI) trains models using customer data, which reduces the risk of IP leakage through passed context information.
  • Dremio sends sample data to the model, and this data is secured with the user's credentials.
  • Dremio uses schema information and dataset tags/wikis as model context. This means that any sensitive information in your table or column names, or in the dataset tags/wikis, could be passed to a model. Neither Dremio nor our trained model partner (Open AI) persists this context.
  • Generative AI features are built on Dremio's existing, secure data platform. These features are audited by the same practices and policies, including SOC 2 Type II. For more information, see Dremio Cloud Terms of Service.