There's nothing about RAG that requires embeddings.

The retrieval part can be grep if you don't care about semantic search.

I believe Multimodal KB+Agentic RAG is a suitable solution for personal KB. Imagine you have tons of office docs and want to dig some complex topics within it. You could try https://github.com/JetXu-LLM/DocMason

Fully retrieve all diagram or charts info from ppt and excels, and then leverage Native AI agents(e.g. Codex) to conduct Agentic Rad

eh i'd push back on "just RAG". like yes the retrieval-generation loop is RAG shaped, no ones arguing that. but the interesting bit here is the write loop - the LLM is authoring and maintaining the wiki itself, building backlinks, filing its own outputs back in. thats not retrieval thats knowledge synthesis. in vanilla RAG your corpus is static, here it isnt

also the linting pass is doing something genuinely different - auditing inconsistencies, imputing missing data, suggesting connections. thats closer to assistant maintaining a zettelkasten than a search engine returning top-k chunks

cool project btw will check it out

You should have started your comment with “ I have a few qualms with this app”.

I’ve been thinking something along the lines of a LLM-WIKI for a while now which could truely act as a wingman-executive-assistant-second-brain, but OP has gone deeper than my ADHD thoughts could have possibly gone.

Looking forward to seeing this turn into fruition

> This is just RAG.

More to the point, this is how LLM assistants like GitHub Copilot use their custom instructions file, aka copilot-instructions.md

https://docs.github.com/en/copilot/how-tos/configure-custom-...