RAGs to Riches? The Realities of RAG and text-to-SQL

Logo
Presented by

Andy Hayler, Practice Leader: Data as an Asset, Bloor Research & Iris Zarecki, Product Marketing Director K2view

About this talk

In the age of Generative AI and retrieval augmented generation (RAG) the spotlight is on enterprise data. The data can reside in operational systems, data lakes / data warehouses, or on a data management platform, and it is an essential piece required for GenAI app to provide much more personalized and accurate information. Large Language Models (LLMs) can access structured enterprise data via RAG and SQL statements. For all the undeniable advantages of using an LLM to generate SQL queries, there are also a number of issues that accompany this approach. Join 2 industry leaders as they discuss:  * What is retrieval augmented generation (RAG) and how does it work? * The pros and cons of generating SQL with AI * Considerations for ensuring your enterprise data is GenAI-Ready * Closing the GenAI data gap
Related topics:

More from this channel

Upcoming talks (0)
On-demand talks (27)
Subscribers (7869)
At K2View, we believe that every company should be able to liberate and elevate its data to deliver the most personalized and profitable customer experience in its industry, while being innovative and radically agile. With K2View, companies manage data in a whole new way, using a business lens: they create data products that continually sync, transform, and serve data from siloed source systems – delivering a real-time, holistic view of any business entity to any data consumer. Our Data Product Platform fuels operational and analytical workloads, at enterprise scale. It deploys as a data fabric, data mesh, or data hub - in an on-premises, cloud, or a hybrid architecture - in a matter of weeks, and adapts to change on the fly. The most data-intensive companies in the world, including AT&T, Verizon, American Express, Vodafone, and Hertz trust K2View Data Product Platform for their operational use cases - spanning Customer 360, cloud migration, test data management, data tokenization, and legacy application modernization.