Homegrown LLMs and Retrieval Augmented Generation (RAG) technologies

26/02/2025 1h 10min Episodio 3
Homegrown LLMs and Retrieval Augmented Generation (RAG) technologies

Listen "Homegrown LLMs and Retrieval Augmented Generation (RAG) technologies"

Episode Synopsis

In today’s conversation Ruben Puentedura acknowledges the limitations of “AI”, shares his research and experience with Retrieval Augmented Generation (RAG) technologies, and talks about the affordances of home grown LLMs (Large Language Models) combined with external resources. We are joined by Bryan Alexander and Tom Haymes.
Dr. Puentedura is the Founder and President of Hippasus, a consulting practice focusing on transformative applications of information technologies to education.
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
https://arxiv.org/pdf/2404.16130
Code a simple RAG from scratch
https://huggingface.co/blog/ngxson/make-your-own-rag
More from Ruben Puentedura https://www.linkedin.com/in/rubenpuentedura/
Tom Haymes: https://www.linkedin.com/in/tomhaymes/
Bryan Alexander: https://bryanalexander.org/
Mark Corbett Wilson: https://www.linkedin.com/in/markcorbettwilson/
Talking with machines by Mark Corbett Wilson @mcorbettwilson on social media