SEO

Embedding

Also called vector, text embedding

A numeric representation of a piece of text that lets software compare meaning instead of matching exact words.

Quick facts: Embedding

Category
SEO
Also called
vector, text embedding
Level
Advanced
Affects
Semantic search, AI retrieval, chatbot accuracy, related content
Where to see it
Embedding APIs from major model providers, vector databases, and most retrieval frameworks
In this article4
  1. How an embedding works
  2. Why embeddings matter
  3. Where embeddings go wrong
  4. How to act on it

How an embedding works

A model reads a piece of text — a sentence, a paragraph, a product description — and outputs a long list of numbers that represents what the text is about. Texts with similar meaning produce similar lists, so the machine can measure how close two pieces of writing are without either one containing the other’s words. “Cheap flights to Kathmandu” and “low-cost airfare to Nepal’s capital” land near each other; “flight simulator review” does not.

That closeness is all an embedding gives you. It carries no facts, no dates and no truth, and it cannot tell you whether the text it represents is accurate. It is a position, and everything built on top of it — semantic search, recommendation, retrieval for AI answers — is some form of asking which stored positions sit nearest to the question.

Why embeddings matter

They are the reason exact-match keyword thinking has faded. When a system compares meaning rather than strings, repeating a phrase gains you nothing, while covering the actual concept clearly gains you a lot. Related vocabulary, the questions around a topic and the specifics of your offer all shift the position of your text towards the questions you want to be found for.

They are also the layer underneath most AI retrieval. A passage from your site is embedded, stored, and later compared against a user’s prompt; if it sits close enough, it is fetched and can be quoted. This is what semantic search means in practice, and it is why writing plainly about one subject beats writing loosely around several.

Where embeddings go wrong

The first misunderstanding is treating them as a store of knowledge. They are not a database of facts, and asking an embedding whether something is true is a category error — that is why retrieval systems keep the original text beside the numbers and quote from the text, not from the position.

The second is vagueness. Marketing prose that avoids naming what it sells embeds towards a general fog rather than a specific topic, so it matches nothing sharply. Mixing several unrelated subjects into one passage does the same damage from the other direction: the position lands between the topics and near none of them. Stale content adds a quieter failure — an embedding reflects the text as it was when it was created, so a rewritten page that is never re-processed keeps competing on its old meaning.

How to act on it

For a website, nothing exotic is required. Say plainly what a page is about, in the words your customers use, near the top. Keep one subject per section and name it rather than referring back to “it”. Cover the specifics — the service, the place, the constraint, the price model — because specifics are what pull a passage towards a real question rather than a general theme.

If you are building something of your own, such as an internal assistant over your documents, then embeddings become an operational concern: choose one model and stay with it, since positions from different models are not comparable, re-embed whenever a document changes, and store the source and date beside each entry. That store is a vector database, and its usefulness rises and falls with how clean the text going into it is.

Do and do not

Do

  • Name the subject of a section explicitly and early
  • Keep one topic per passage, in customer vocabulary
  • Re-process your own documents whenever they change

Do not

  • Repeat a phrase hoping to strengthen a match
  • Treat an embedding as a store of facts
  • Mix embeddings from different models in one store

Questions people ask about this

Do I need to do anything about embeddings on my website?

Not technically. Search engines and assistants create their own embeddings from your pages, and you cannot supply or adjust them. What you influence is the text they are made from, so the practical work is ordinary writing: one clear subject per section, specific vocabulary, named services and places, and no filler that blurs what the page is about.

Are embeddings the same as keywords?

No, and the difference matters. A keyword is a string that either appears or does not. An embedding is a position that represents meaning, so a page can match a query it never contains word for word. Repetition of a phrase adds little, whereas covering the concept and its surrounding vocabulary clearly moves the text closer to the questions people ask.

Why would an embedding need updating?

Because it is a snapshot of the text at the moment it was processed. If you rewrite a page, the stored numbers still describe the old wording until the content is embedded again. On the open web the search engines handle that on their own schedule; in a system you built yourself, re-embedding after every content change is your job.

Related terms

Found this useful?

Share it, or ask an AI to summarise it

Back to the glossary

Knowing the term is the easy part

Applying it to your own site and budget is the work. Book a call and I will tell you what actually applies to you.