Paul Moxon
In recent years, Generative AI (GenAI) has garnered significant attention for its potential to revolutionize various industries, from creative arts to data analysis. Research by Accenture has found that 98% of business leaders think that AI foundation models will be essential to their operations over the next three to five years and Goldman Sachs Research estimated that GenAI could add more than $7 Trillion to the global economy. The potential is huge.
However, the realization of this potential requires more than simply using ChatGPT to answer a few questions. Organizations must think through how they can use GenAI in practice and integrate this with their own systems and data to provide GenAI tools and solutions that are specific to the needs of the organization. Enter Retrieval Augmented Generation, or RAG. RAG is a pattern by which the GenAI LLMs are augmented with data extracted from the organization's internal (and external) systems and databases to provide better, more meaningful, responses.
This session will examine why RAG is critical to successful GenAI initiatives - whether these are internal tools to augment and enhance decision making or externally facing tools for customers, such as intelligent chatbots - and the different options for implementing RAG.
- Learn why GenAI needs context - and contextual data - to be truly effective
- Learn how Retrieval Augmented Generation (RAG) delivers this contextual data to the GenAI LLMs
- Understand the different RAG models and why a Data Fabric approach accelerates your GenAI initiatives
