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.

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

Describes SPARQL queries to separate TBox entities from ABox.

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...