Thank you both. I will do more digging on pg_description as you suggested.
Also looking forward to optimizations. I was actually working on the similar project on the semantic data layer for llm context, but I think your project already solves this issue. Will report back as I try to integrate ktx more in our agentic flows.
some observations:
setup (without openai embeddings) was pretty easy. Nice!
Not sure why it took ~19 minutes for a postgres database with 20sh tables.
Also the data from pg_desc did not get into the wiki
I am going to try to embed it in our agentic flow and see how it fits. Very cool project though.