Easy Vector DB Question 38 of 223

What is approximate nearest neighbor search?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: AN LLM TURN

Text inTokens

TransformerAttention

Text outNext token

Simple meaning

ANN search returns vectors that are very close to the query without guaranteeing the exact closest set.

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

Vector DB questions separate

people who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

STEPS — What happens with tokens?

Before the model can read a sentence, it goes through these steps:

1
ANN search returns vectors
that are very close to the query without guaranteeing the exact closest set.
2
Exact search is too
slow at millions of embeddings.
3
Production RAG almost always
uses ANN.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

EXAMPLE — See it in action

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“Exact search is too slow at millions of embeddings.”

Tokenized output

Exactsearchistooslowat

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Key takeaway

ANN search returns vectors that are very close to the query without guaranteeing the exact closest set. Exact search is too slow at millions of embeddings.