Really fascinating article. Im also working my way into understanding how to create a real world, practical ontology. In my case I struggle with a normalized data mindset but this is a whole different game, we have to be able to tolerate ambiguity first and then let patterns emerge. Kind of like the stages of data pipeline architecture.
Yes, exactly! Building AI applications is strange because it's extremely iterative. You rarely have a perfect product in the first go, and you want to design for iterations.
Nice explanation Paul. I am also exploring Ontology based solution that will work in my project. It was a good walk-through. Where can I find a bit more technical details around this?
I am going through your course on Agentic AI Engineering. It is very good. Looking forward your book as well.
I just tried to build my own Ontology extraction logic today using a hybrid approach of LLM and Determinitistic process. This is purely built using Cursor and Replit. So far working as I had envisioned it. Now I will go through Neo4j now to check on how can I improve it further. For sure, I will be very keen to gain your expert knowledge on the same once you publish your book.
That sounds like a solid plan. Ask Cursor to extract in more depth the strategy from this article into a plan of attack for your repo. It will do wonders!
Would you be open to providing more feedback on the course? As a testimonial/review or just a simple DM message
Really fascinating article. Im also working my way into understanding how to create a real world, practical ontology. In my case I struggle with a normalized data mindset but this is a whole different game, we have to be able to tolerate ambiguity first and then let patterns emerge. Kind of like the stages of data pipeline architecture.
Yes, exactly! Building AI applications is strange because it's extremely iterative. You rarely have a perfect product in the first go, and you want to design for iterations.
Ontologies are useless but ontologizing is essential
Haha. Nice one!
Nice explanation Paul. I am also exploring Ontology based solution that will work in my project. It was a good walk-through. Where can I find a bit more technical details around this?
Thanks! I found them directly within Neo4j's repository. I suggest trying out their code.
P.S. Also, I am working on a book about creating your personal assistant from scratch, covering this topic in depth. But it's not out yet!
I am going through your course on Agentic AI Engineering. It is very good. Looking forward your book as well.
I just tried to build my own Ontology extraction logic today using a hybrid approach of LLM and Determinitistic process. This is purely built using Cursor and Replit. So far working as I had envisioned it. Now I will go through Neo4j now to check on how can I improve it further. For sure, I will be very keen to gain your expert knowledge on the same once you publish your book.
Thanks, man! Appreciate your support.
That sounds like a solid plan. Ask Cursor to extract in more depth the strategy from this article into a plan of attack for your repo. It will do wonders!
Would you be open to providing more feedback on the course? As a testimonial/review or just a simple DM message
For sure, Paul. I will be glad to provide a feedback and a testimonial both.
Thanks, man! I DMed you