Graph-Driven RAG AI Powered by DITA

Can generative AI benefit from structured content? What role play knowledge graphs in this? And what does all of that have to do with DITA? After they discovered the shortcomings of vector-based RAG there is a buzz in the industry around knowledge graph-driven retrieval-augmented generation (Graph RAG). This session will examine whether and how DITA fits into that equation. Michael Iantosca will demonstrate a full-scale implementation of a graph-driven RAG based on intelligent structured content. Presented by Iantosca as graph AI theory, just as generative AI blasted into the mainstream, this session explains how DITA was used to automate the construction and maintenance of a scalable knowledge graph to drive generative AI applications along with a fully functional advanced neuro-symbolic chatbot that supports what other models lack: the ability to do inferencing and reasoning. Not a show-and-tell session but an in-depth review of how the model and solution were built, the theory behind it, and how other teams can replicate it. Several years ago, some audacious Markdown maven declared that DITA was getting “long in the tooth”. Now, at the dawn of neuro-symbolic generative AI, it turns out that DITA was, indeed, the future. This educational presentation is brought to you by The Content Wrangler and is sponsored by Heretto, a powerful component content management system (CCMS) platform to deploy help and API documentation in a single portal designed to delight your customers.