Retrieval & ranking
Vector Embedding
A list of numbers that encodes meaning so related content sits close in vector space.
A vector embedding is a list of numbers that encodes the meaning of a piece of text, image or other content so that related items sit near each other in a high-dimensional space. Embeddings are the backbone of semantic retrieval: by turning meaning into geometry, they let systems measure how related two things are by how close their vectors are.
In AI search, your content is embedded, stored in a vector index, and matched against the embedding of each query. The closer your passage's vector is to the query's, the more likely it is retrieved. This is the mechanism underneath chunk retrieval, semantic similarity and RAG.
The practical takeaway is the same across this whole category: clear, specific expression of a single idea produces a clean embedding that matches the right queries.
Related terms
Passage Embedding
A numeric vector that captures a passage's meaning so similar passages sit near each other.
Semantic Similarity
How close two pieces of text are in meaning, measured by comparing their embeddings.
Cosine Similarity
A score from -1 to 1 measuring how closely two vectors point in the same direction.
Chunk Retrieval
Fetching the top few most relevant text passages from a vector index for a query.
Retrieval-Augmented Generation
Fetch relevant documents first, then have an LLM write an answer grounded in them.
Want to know where you stand in AI answers?
We’ll show you which engines cite you, and which don’t.
Get a free AI citation audit