Dremio bets on generative AI and adds new tools to speed up data workflows

Join senior executives in San Francisco on July 11-12 to learn how leaders are integrating and optimizing AI investments for success. Learn more

Dremio, the open data lake provider that combines the capabilities of a data lake and a warehouse on a unified layer, is all about generative AI.

The company today announced two new next-generation AI features for its platform: a text-to-SQL experience for conversational querying of data and an autonomous semantic layer to help catalog and process data. .

The offerings will simplify working with data for Dremio users, allowing them to explore, discover and analyze their data assets quickly and easily. Similar efforts have also been made by other major players in the data ecosystem (including Snowflake and Informatica), signaling the rise of AI-based data processing.

How will the new features help you?

The task of unlocking data value has long depended on a number of manual and time-consuming steps. With the latest features, Dremio brings generative AI to fill some of these gaps.


Transform 2023

Join us in San Francisco on July 11-12, where senior executives will share how they integrated and optimized AI investments for success and avoided common pitfalls.

Register now

For example, with the new Text-to-SQL experience, instead of spending time writing complex SQL (Structured Query Language) queries, users can simply enter natural language input to get insights from their data. The offering relies on a semantic understanding of metadata and data and automatically converts the plain language query to SQL, delivering the desired results.

Similarly, the Autonomous Semantic Layer leverages generative AI to take the hassle out of manually cataloging data. It automatically learns the intricate details of user data and produces descriptions of datasets, columns, and relationships to establish taxonomies that facilitate data discovery and exploration.

According to Dremio, this layer also learns from user workloads and creates reflections (optimized materialization of source data or a query) to speed up data processing.

“By integrating generative AI capabilities into our platform, we’re accelerating data workflows and eliminating much of the manual work involved in SQL development, creating and curating data catalogs, and more,” said Tomer Shiran, co-founder and CPO of Dremio.

“Generative AI will transform data engineering, data science and analytics over the next few years, and we are excited to provide our users with the most powerful tools in the industry to discover the true potential of their data. “, he added.

Vector database capabilities

In addition to generational AI tools, Dremio also embeds vector database capabilities directly into its Lakehouse, allowing businesses to build AI-powered applications without creating additional data silos.

With this feature, users will be able to add a vector type column to store and search integrations for various data items.

For example, if a user has an array of Amazon reviews, they could store embeds that encode the meaning of each review along with other attributes. Then, if needed, they could use Dremio’s indexes and SQL functions to retrieve similar or related notices based on their meaning.

The text-to-SQL experience is now available for Dremio users, while the standalone semantic layer and vector database features will be rolled out later.

VentureBeat’s mission is to be a digital public square for technical decision makers to learn about transformative enterprise technology and conduct transactions. Discover our Briefings.

Leave a Comment