Local RAG starts with retrieval, not infrastructure

RAG projects have a way of collecting infrastructure before they collect evidence.

A database gets provisioned. A vector store appears. Then Redis, object storage, a parser service, a queue worker, and a few dashboards. By the time the first PDF is imported, there are enough moving parts that a bad search result can mean almost anything.

Was the parser wrong? Did chunking lose the useful context? Was the vector index empty? Did the query just not match the document?

For early work, I would rather make the problem smaller. Use a handful of documents people already depend on. Ask questions they have actually asked before. Look at the passages returned by search and decide whether they are useful.

That is what I mean by starting local.

Local RAG starts with retrieval, not infrastructure

Related reading

Building a RAG Data Feed: The Ingestion Problems Nobody Warns You About

Chat with your documents: agentic RAG in a few lines

Building a Production RAG Pipeline: Document Processing, Chunking, and Metadata…

RAG isn't an AI problem. It's a data engineering problem wearing an AI hat.

Why RAG gives wrong answers (and how to fix retrieval failures)

Anatomy of a Full RAG Application: Every Concept, One Self-Hosted Stack