We need RAG - buy a vector DB?

Same shelf, different job…

A2 · 420 × 594 mm · print-first

This poster separates two things that get sold as one: a vector database (infrastructure for similarity search) and RAG (a retrieve-then-generate pattern). Buying an index is not the same as grounding an answer.

The headline is the common mistake — “we need RAG, so buy a vector DB.” Sometimes you need the store without the generation loop; sometimes you need RAG with keyword or hybrid retrieval and no dedicated vector product.

The confusion

People name the pattern — and buy the store

Teams say they need RAG and immediately shortlist Pinecone, Weaviate, pgvector, Qdrant, and peers. That shopping list is about storage and approximate nearest-neighbour search.

A vector database is infrastructure. RAG is a loop: retrieve relevant material, put it in the prompt, generate. The loop may use a vector DB — or BM25, hybrid search, graphs, or plain SQL.

Vector DB = store · index · search
RAG = retrieve · ground · generate
They are not the same object

Vector database

Infrastructure — embeddings in, neighbours out

Documents (or rows) are chunked, embedded into vectors, and written into an index (HNSW, IVF, disk-backed variants, and filters). Queries return top-k ids, scores, and payloads.

The database owns storage, ANN search, metadata filters, and scale. It does not write the natural-language answer. An embedding model is required to get into vector space; a generative LLM is not required for search itself.

Documents → Embed → Vector index → Top-k hits
Output: ids · scores · payloads — not prose

RAG

Pattern — retrieve → ground the prompt → generate

Retrieval-Augmented Generation fetches relevant passages for a question, augments the prompt with them, then lets the model generate — ideally with citation paths back to the retrieved material.

RAG owns grounding and the “less invented facts” path. It needs a retriever behind it; that retriever is often a vector database, but it does not have to be.

Question → Retrieve → Augment → Generate → cite
Retriever may be vector, keyword, hybrid, or mixed

Differences

Store + scores vs retrieve → prompt → prose

Compact lens: vector DB is a store + ANN index (cities · scores · stop; no LLM). RAG is retrieve → prompt → LLM (prose answer · cite; needs LLM).

Worked example under each column — ask “spring city walks?” over Lisbon · Reykjavik · Tokyo. Left stops at ranked cities; right continues through retrieve → prompt → LLM to “Lisbon — mild spring walks” with cite.

Do not confuse your investor!

Same shelf, different job

Closing line only — no separate use-case cards. The travel example above already shows what each side returns: an id table of cities + scores, versus one written answer with cite id 01 Lisbon.

Read black and grey as emphasis on the sheet, not as Claude hooks. The thesis is one line: same shelf in the architecture diagram, different job in the system.

Sources

Lewis et al., Retrieval-Augmented Generation (RAG)
ANN indexes: HNSW / IVF family
happyoverlord.com research posters

Propose a topic

Suggest the next AI infographic. One topic, one glance — what should it make obvious?