Brian Godsey

Overcoming the challenges of productionizing graph RAG Brian Godsey · Follow Published in Towards Data Science · 15 min read · 10 hours ago — Adventures in the Knowledge Graph: There is Value in the Knowledge Graph. Generated by Brian Godsey using DALL-E. When I read the recent article in VentureBeat about how Glean just secured over $260 million in its latest funding round, I had two immediate gut feelings. First, it was satisfying to

AI systems aren’t perfect (GASP!) and these are some of the reasons why. Brian Godsey · Follow Published in Towards Data Science · 17 min read · 22 hours ago — Created by the author using DALL-E. Some information loss was involved. As we bring enterprise AI systems into production, we shouldn’t expect them to function in the same way as search engines, or as databases of exact words and phrases. Yes, AI systems often

Document datasets already have structure. Take advantage of it. Brian Godsey · Follow Published in Towards Data Science · 13 min read · 2 hours ago — Photo by Jayne Harris on Unsplash There are layered challenges in building retrieval-augmented generation (RAG) applications. Document retrieval, a huge part of the RAG workflow, is itself a complex set of steps that can be approached in different ways depending on the use case. It is difficult for