Kinetica Adds Conversational Query Capabilities To Its Analytical Database With ChatGPT

With its ability to convert natural language questions into SQL queries, the addition of ChatGPT to the high-performance, real-time Kinetica database makes it possible for business users to obtain analytical insights on the fly.

Kinetica has integrated its high-performance analytics database with ChatGPT, making it among the first to use the popular AI technology for “conversational querying” that converts natural language questions into Structured Query Language (SQL).

Kinetica, a rising company in the crowded market of next-generation databases, says the use of ChatGPT makes it possible for users to ask complex questions of proprietary, complex data sets in the Kinetica system and receive answers in seconds.

“The world of [database] query is going to go from being all controlled to much more ad hoc query. And that’s where we have a distinct advantage because Kinetica [has] that kind of ability to use brute force compute better than other databases,” Nima Negahban, Kinetica co-founder and CEO, said in an interview with CRN.

“We don’t need to have a whole bunch of pre-planning done. We can take on a very complex query against large datasets, on the fly, and deliver [analytical results] in a way that’s performant and conducive to this kind of conversational experience that I think is going to be expected in the years to come as you look across the users in an enterprise,” Negahban said.

[Related: The Big Data 100The Big Data 100 20232023]

Kinetica develops a real-time, vectorized database for analyzing and observing huge volumes of streaming time series, spatial and graph data. The distributed, OLAP, Postgres-compatible database supports standard queries and works with popular business intelligence tools.

The Kinetica database uses native vectorization where data is stored in fixed-size blocks called vectors. Queries are performed against vectors in parallel rather than individual data elements, allowing the database to provide “radically faster” query execution, according to the company. The database also relies on GPUs and advanced CPUs to perform simultaneous calculations on multiple data elements.

“It’s the combination of ChatGPT and that vectorized architecture, ask any question and get a fast answer, that we think is going to be a killer app,” said Chad Meley, Kinetica’s chief marketing officer, in the CRN interview. “We think this is going to just fundamentally change the way enterprises interact with data.”

Tuesday Kinetica said it is the industry’s first analytic database to integrate with ChatGPT, ushering in “conversational querying” that makes querying more interactive and making data query capabilities available to a wider audience of users.

SQL is the standard development tool for building queries for retrieving data in relational databases. But with the exception of some “power users” who can develop their own SQL queries, SQL-based queries are largely developed by programmers and data engineers either for pre-built queries and reports or in response to business users’ requests – which means delays in getting data and insights to decision makers.

A New Approach To NLP

Developing AI-based natural language processing (NLP) tools to help non-technical executives and information workers analyze data using conversational texts has been a long-time big data industry goal. With a front-end interface that converts natural language to SQL, ChatGPT has the potential to greatly advance those capabilities.

Rather than writing complex SQL queries or navigating complex user interfaces, the ChatGPT interface provides a way for users to ask ad-hoc questions of proprietary data in a database system – even complex queries not previously developed – and receive answers in seconds without the need to pre-engineer data.

The new conversational querying capabilities improves the ease-of-use of the Kinetica database by allowing users to ask questions using their own words and phrasing, according to the company. The new capabilities also boost productivity by providing real-time access to information and offers the ability to more quickly identify patterns and insights within the data.

With the new query capability, business users with a question will “just type that in and then the query gets generated,” CEO Negahban said. “That’s going to be a fundamental change in how your business is done and also a fundamental change in what is expected of a database to be able to power that kind of workflow.”

ChatGPT Integration

Kinetica, headquartered in Arlington, VA., has integrated ChatGPT with its Workbench user interface and in time will also provide the ability to invoke ChatGPT through SQL. “This is part of what we’re doing in a multi-phase approach on how we’re going to be supporting the generative AI stack,” Negahban said.

The executives said Kinetica’s solution provider and ISV partners will benefit from the new ChatGPT capabilities by building applications and solutions that offer higher productivity to their customers and the ability to engage a wider audience of users for business intelligence tasks.

“Growing the channel is a big focus for us at this point in the company’s evolution,” CMO Meley said, noting that in February Kinetica hired former Chief Revenue Officer Robert DeMartino, previously at database developer TigerGraph, as Kinetica’s new CRO. “The channel partners are very excited about this innovation.”