ChatGPT

Communicating Ontology Knowledge with an LLM in Graph RAG: The power of simplicity and standards

One of the biggest challenges in Graph Retrieval Augmented Generation (RAG) systems is how to communicate knowledge from the ontology (e.g., subclasses, types, property values) to the LLM. The approach described in this post is very simple and easy to reuse but surprisingly effective.

Michael DeBellis

4 days ago9 min read

Keeping ChatGPT on Track: How “Seeds” Prevent Context Loss in Long Conversations

Seeds and Projects are easy and powerful tools to help ChatGPT retain context over long threads

Michael DeBellis

Dec 11, 20254 min read

Using Retrieval Augmented Generation (RAG) and Knowledge Graphs to build a Climate Obstruction Portal

Description of a system developed using Retrieval Augmented Generation (RAG) and a knowledge graph as a portal for Climate Obstruction researchers

Michael DeBellis

Oct 9, 20251 min read

Using ChatGPT to Generate English Labels for a Spanish Ontology

I've been using ChatGPT to help with various kinds of analysis and coding tasks. Today I had the problem of generating English labels for...

Michael DeBellis

Nov 2, 20245 min read