Architecture Patterns for Enterprise Generative AI
Date:
By: Daniel Howard and Robin Bloor
Classification: White Paper
Generative AI, or just GAI, is the latest computing technology to take both the business world and the general public by storm. Standing on the shoulders of years of developments in data science, machine learning, and deep learning, GAI is a means to generate meaningful, easily digestible outputs from natural language prompts.
However, nothing in the applications world is built without architecture, and there are several forms a GAI (data) architecture can take. In this report, we enumerate these forms and offer advice as to which you may want to employ. We also provide a brief introduction to GAI, large language models (LLMs), and the use of vector databases in a GAI context.