← All explainers
AI in 3 · 3 min read

What actually happens inside a RAG pipeline

Chunk, embed, retrieve, re-rank, generate — and the three places it quietly goes wrong in production.

AI in 3Foundational

Retrieval-augmented generation is a search problem wearing an AI costume. You split your documents into chunks, turn each chunk into a vector, store the vectors, and at question time find the chunks nearest to the question and paste them into the prompt.

Because it is a search problem, it fails like one. If the right chunk is never retrieved, no model on earth will answer correctly — it will answer confidently instead, from whatever it did receive.

Instrument retrieval separately from generation. Log the retrieved chunk IDs for every answer. When a user reports a bad answer you need to know whether retrieval missed or the model ignored what it was given, and those have completely different fixes.

The shape of it

  1. 01

    Chunk

    Split on structure, not character count. Bad chunking is the most common root cause.

  2. 02

    Embed

    Same model for documents and queries, always. Re-embed everything when you change it.

  3. 03

    Retrieve

    Hybrid — vector plus keyword. Pure vector search misses exact IDs and product names.

  4. 04

    Re-rank

    A cross-encoder over the top 50 beats a bigger top-k every time.

  5. 05

    Generate

    Instruct the model to answer only from context and to say when it can't.

Want this applied to your situation?

Sessions are direct and specific — you leave with a decision, not a reading list.

Book a session
More in AI in 3