Large Language Model (LLM) | MichaelDeBellis

Communicating knowledge from an OWL ontology to 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

May 129 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 an LLM to help build ontologies: The Basic Formal Ontology (BFO) Assistant

Using the Open AI Assistant tool to create an LLM enabled assistant to using the Basic Formal Ontology (BFO)

Michael DeBellis

Feb 1, 20241 min read