Easy Embeddings Question 10 of 223

What is semantic search?

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

Mean3.25average

Median2middle

Mode2most often

Semantic search ranks documents by meaning rather than exact keyword overlap.

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

Embeddings 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.

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

1
Semantic search ranks documents
by meaning rather than exact keyword overlap.
2
A query and a
passage can match if their embeddings are close.
3
It is the retrieval
style most RAG systems start with.
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.

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

Input text

“A query and a passage can match if their embeddings are close.”

Tokenized output

Aqueryandapassagecan

Token IDs (example)

2987408337471632900

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

Semantic search ranks documents by meaning rather than exact keyword overlap. A query and a passage can match if their embeddings are close.