What We're Building

Retrieval-Augmented Generation (RAG) is the pattern where an LLM answers questions using documents you provide, rather than relying only on what it learned during training. It's the foundation of most real-world AI apps: document Q&A, support bots, knowledge assistants.

This post builds a working RAG API …

Why This Matters

You build a RAG pipeline. Retrieval works: the right chunk is definitely in the top results. You send everything to the LLM, and it still gives a wrong or incomplete answer, as if it never saw the one piece of text that contained the answer.

Very often …

Why This Matters

If you've built even a basic RAG pipeline, you've probably run into "chunk overlap" as a setting — usually with some default value like 50 or 200 tokens — and wondered why you'd deliberately want the same text to appear in two different chunks. Doesn't that just waste storage …