Vector search
Retrieval by nearest-neighbour similarity between embedding vectors rather than by keyword matching, usually implemented with approximate…
GEO AIVector embedding
Embedding
A numerical vector representing the meaning of text, an image or another item, positioned so that semantically similar items lie close together in the vector space.
In full
Embeddings let systems compare meaning rather than matching strings, which is what allows a query and a passage with no shared vocabulary to be recognised as related. They power vector search, clustering, deduplication, recommendation and the retrieval half of RAG. In SEO workflows, embeddings are used practically for detecting cannibalisation, clustering keywords by intent, mapping internal link opportunities, and measuring how close a page is to the topic it targets.
Example
Embedding 4,000 URLs and clustering them reveals nine pairs of pages whose vectors are nearly identical — clear cannibalisation candidates.
Related terms
Retrieval-augmented generation
An architecture where a system retrieves relevant documents or passages first and then has a language model generate an answer conditioned…
Semantic search
Retrieval based on the meaning of a query and documents rather than literal keyword matching, using entities, context and learned…
Keyword cannibalisation
Multiple pages on a site competing for the same query, so search engines alternate between them and none establishes a strong position.
Chunk retrieval
Retrieving individual segments of a document rather than whole pages, which is how most AI search and RAG systems select what to feed a…
Where to read more
- Dense Passage Retrieval for Open-Domain Question Answering · Landmark Post · arxiv.org