RESEARCH · RETRIEVAL
Three kinds
of RAG.
Retrieval-augmented generation connects a model to your data, so it answers from what is true for you and not just what it memorized. There is not one way to do it. There are at least three, they fail in different places, and picking the wrong one is how a promising demo dies in production.
THE SHAPE OF IT
Same goal, three architectures.
Every kind of RAG does the same job: fetch relevant context, put it in the prompt, and let the model answer grounded in it. The difference is how it decides what is relevant, and how many chances it gets to decide.
CLASSIC RAG
Embed and fetch.
Turn the query into a vector, return the top matching chunks, answer. One retrieval, one shot.
GRAPH RAG
Follow the links.
Walk a knowledge graph, return a connected subgraph. Sees relationships a flat vector search misses.
AGENTIC RAG
Retrieve, then decide.
An agent plans, retrieves, checks the result, and retrieves again until it has what the answer needs.
Three retrieval architectures, one goal
THE TRADEOFFS
When each one wins.
| Classic RAG | Graph RAG | Agentic RAG | |
|---|---|---|---|
| Best for | Lookup, FAQ, single-fact answers | Relationships, multi-hop questions | Open-ended, multi-step research |
| How it retrieves | Embed the query, return top-k similar chunks | Traverse a knowledge graph, return a subgraph | Plan, retrieve, check, retrieve again |
| Strength | Simple, fast, cheap | Follows connections vectors miss | Adapts when one retrieval is not enough |
| Fails when | The answer spans many documents | The graph is stale or badly built | Loops run long; cost and latency climb |
| Cost | $ | $$ · graph build + storage | $$$ · many model calls |
HOW TO CHOOSE
Cheapest thing that works.
Start with classic RAG. Most real questions are lookups, and it answers them at a fraction of the cost of anything fancier. Adding architecture you do not need is not sophistication, it is latency and spend.
Reach for Graph RAG when the questions are about relationships: which contracts reference this clause, which customers touch this account, how these entities connect. Reach for Agentic RAG when a single retrieval genuinely cannot know what to fetch until it has read something first. Complexity is a cost you pay only when the question demands it.
HOW MILLIE MEASURES THIS
We do not benchmark RAG in the abstract. We take your questions and your corpus, run each architecture against the same task packet, and report accuracy against cost.
Often the finding is that classic RAG wins on the routine majority of questions and Agentic RAG earns its cost only on the hard minority. Knowing where that line sits, for your data, is the design. See what we measure.