easyAI Engineering

What is RAG and why use it instead of fine-tuning for knowledge?

Q: What is RAG and why use it instead of fine-tuning for knowledge?

**TL;DR.** **Retrieval-Augmented Generation**: retrieve relevant documents for the query and put them in the prompt so the model answers **from evidence**. For knowledge it beats fine-tuning on every axis that matters: **instantly updateable, auditable via citations, per-tenant scopable, cheaper**. Fine-tune for behaviour, RAG for facts. query embed index <text class='d-sub

600 views

Understand the problem

Retrieve-then-generate: fresh, cited, per-tenant knowledge without touching model weights.

ragretrievalfine-tuningarchitecture

Attempt it yourself

Sketch your approach before reading the solution — that's what interviews test.

Stuck? AI Nudge Available

Get a conceptual hint to guide your logic without spoiling the final implementation.

Study the solution

The solution is waiting

Give it an honest attempt first — then compare your thinking with the full walkthrough.

Read the code

Minimal RAG answer path

async function answer(question: string, tenantId: string) {
  const qVec = await embed(question);
  const chunks = await db.chunks.nearest(qVec, {
    where: { tenantId },            // access control lives HERE
    limit: 6,
  });
  const context = chunks.map((c, i) => "<doc id='" + i + "'>" + c.content + "</doc>").join("\n");
  return complete({
    system: "Answer only from the docs. Cite [doc-N]. Say so if not found.",
    user: context + "\n\nQuestion: " + question,
  });
}

Join the discussion

Discussion (0)

No responses yet. Be the first to share what you think.

What is a vector database and when do you actually need one?

What are tokens and why do they matter for cost and limits?