DevConf.US 2025

Major Hayden

Major works on all kinds of technology at Red Hat, including artificial intelligence, Linux on public clouds, and automated kernel testing. He's served in various leadership roles in the Fedora project and he maintains several Fedora packages. Before Red Hat, he worked in the OpenStack community as part of his role at Rackspace.

Away from work, Major enjoys getting on the air via amateur radio (W5WUT), running, and learning more about financial markets. He also maintains a technical blog at major.io.


Job title

Senior Principal Software Engineer

Company or affiliation

Red Hat


Session

09-20
15:30
15min
Don't tell me RAG is easy
Major Hayden

Take all of the documentation and throw it into the database and we're done, right? Not so fast.

Large language models (LLMs) don't know everything and retrieval-augmented generation, or RAG, fills in the knowledge gaps with just-in-time retrieval of data from a database. Technical limitations and challenges loom large here, but there are plenty of difficulties brought over from the world of humans into the world of LLMs.

Come on a RAG journey with me as I recount some of the roadblocks my team faced as we built a product with RAG as a core component. Learn about the available technologies, how to build out a RAG stack, and how to avoid bringing human complexity into an already complex technical system.

Artificial Intelligence and Data Science
Ladd Room (Capacity 96)