Graph-Driven RAG AI Powered by DITA

  • Presentation
  • AI and New Technologies in TC
  • 02. April
  • 17:00 - 17:40 PM (CEST)
  • 15:00 - 15:40 PM (UTC) | 11:00 - 11:40 AM (EDT)
  • Find your local time here: Time Converter
  • finished
  •  Michael Iantosca

    Michael Iantosca

    • Avalara Inc
  •  Harald Stadlbauer

    Harald Stadlbauer

    • NINEFEB

Contents

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 put the question of whether and how DITA fits into that equation.  Michael Iantosca, Senior Direct of Knowledge Platforms and Engineering at Avalara, and Helmut Nagy, Chief Product Officer of Semantic Web Company will demonstrate a full-scale implementation of a graph-driven RAG based on intelligent structured content.  Presented by Iantosca as graph AI theory at CIDM and in Best Practices newsletters just as generative AI blasted into the mainstream, this session will explain 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 deterministic reasoning and inference. This isn’t your typical 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 the same.  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.

Takeaways

Learn about the full story of a GraphRAG integration on top of DITA:

•              Learn how the model was built

•              Learn how the content graph as generated

•              Get an idea about the integration in a GraphRAG solution        

•              Learn the theory behind it

Speakers

 Michael Iantosca

Michael Iantosca

  • Avalara Inc
Biography

Michael Iantosca is the Senior Director of Content Platforms at Avalara Inc. Michael spent 38 of his 43years at IBM as a content pioneer – leading the design and development of advanced content management systems and technology that began at the very dawn of the structured content revolution in the early 80s. Dual trained as a content professional and systems engineer, he led the charge building some of the earliest content platforms based SGML and DITA and formed the team at IBM that invented DITA.

 Harald Stadlbauer

Harald Stadlbauer

  • NINEFEB
Biography

Harald Stadlbauer is General Manager of the NINEFEB Group of companies, dedicated to the advancement of Technical Communication, like Technical Documentation as well as eLearning, the intelligent context-related delivery of it.

Harald has a track record of Project and Product Management in Robotics and Automation technology up to his role as Vice President Business Development in Telecommunications

He is actively engaged in developing iiRDS further as well as contributing to the AAS (Asset Administration Shell) submodels of the IDTA (Industrial Digital Twin Association). He was the owner of the AAS Submodel “Intelligent Information for Use”, working now in synchronizing other Submodels with the metadata of the Intelligent Information for Use.