No reason to try to avoid semantic search. Dead easy to implement, works across languages to some extent and the fuzziness is worth quite alot.
You're realistically going to need chunks of some kind anyway to feed the LLM, and once you got those it's just a few lines of code to get a basic persistant ChromaDB going.
You're realistically going to need chunks of some kind anyway to feed the LLM, and once you got those it's just a few lines of code to get a basic persistant ChromaDB going.