RAG & Knowledge Systems

Building retrieval systems over your own documents, entirely locally.

Intermediate

Building a local RAG system

How to let a local model answer questions about your own documents, the pieces involved, and the two routes: an all-in-one app, or assembling it yourself.
Intermediate

Improving RAG retrieval quality

A RAG system is only as good as the passages it retrieves. The practical levers that most improve retrieval: chunking, hybrid search, reranking, and evaluation.
Intermediate

Adding a reranker to your RAG pipeline

A reranker is often the single biggest quality win for a local RAG system. What it does, how to add one, and which small models to use.