Kinetica announced the availability of a Quick Start for deploying
natural language to SQL on enterprise data.
This Quick Start is for organizations that want to experience ad-hoc data analysis on real-time, structured data
using an LLM that accurately and securely converts natural language to SQL and
returns quick, conversational
answers. This offering makes it fast and easy to load structured
data, optimize the SQL-GPT Large Language Model (LLM), and begin asking
questions of the data using natural language. This announcement follows a
series of GenAI innovations which began last May with Kinetica becoming
the first analytic database to incorporate
natural language into SQL.
Here is how it works:
- Second, simply load
files into Kinetica;
- Third, create context
for those tables that will help the LLM associate the words and terminology
with the names of fields and columns;
- Finally, use the prompt
to ask explicit questions and get near instantaneous answers.
"We're thrilled to introduce Kinetica's
groundbreaking Quick Start for SQL-GPT, enabling organizations to seamlessly
harness the power of Language to SQL on their enterprise data in just one
hour," said Phil Darringer, VP of Product, Kinetica. "With our fine-tuned LLM
tailored to each customer's data and our commitment to guaranteed accuracy and
speed, we're revolutionizing enterprise data analytics with generative
AI."
The Kinetica database converts natural language
queries to SQL, and returns answers within seconds, even for complex and
unknown questions. Further, Kinetica converges multiple modes of analytics such
as time series, spatial, graph, and machine learning that broadens the types of
questions that can be answered. What makes it possible for Kinetica to deliver
on conversational query is the use of native vectorization that leverages
NVIDIA GPUs and modern CPUs. NVIDIA GPUs are the compute paradigm behind every
major AI breakthrough this century, and are now extending into data management
and ad-hoc analytics. In a vectorized query engine, data is stored in
fixed-size blocks called vectors, and query operations are performed on these
vectors in parallel, rather than on individual data elements. This allows the
query engine to process multiple data elements simultaneously, resulting in
radically faster query execution on a smaller compute footprint.
Availability and
Pricing
The Kinetica Quick Start for
SQL-GPT is available now. Step by step instructions are available here. Users can
sign up for free for Kinetica Cloud to try it out today.