By the Variask team · Updated
Definition
Semantic search is search that understands the meaning and intent behind a query, not only its exact words, so it can return results that answer the question even when they use different wording.
Semantic search uses language models and embeddings to compare meaning. A query like how to keep my laptop cool can match a page about reducing CPU temperature. Google has used semantic understanding for years, and AI assistants rely on it heavily when they retrieve pages.
Questions
Vector search is a common way to build semantic search, but semantic search can also use other language understanding methods.
Related terms
How AI search works
Vector search
Vector search finds content by meaning instead of exact words. Text is turned into lists of numbers called embeddings, and the search returns the items whose numbers sit closest to the question's.
ReadHow AI search works
Embeddings
An embedding is a list of numbers that captures the meaning of a piece of text, so that texts with similar meaning get similar numbers. AI systems use embeddings to find, group and compare content.
ReadHow AI search works
Hybrid search
Hybrid search combines keyword search with vector search, so results match both the exact words in a query and its meaning. Many AI retrieval systems use it.
ReadEngines and surfaces
Conversational search
Conversational search is searching by asking questions in natural language and following up, as in a chat, instead of typing short keywords.
ReadDisciplines
Topical authority
Topical authority is how strongly a site is seen as an expert source on a subject, built by covering that subject in depth, accurately and consistently over time.
Read