A vector embedding is a numerical representation of a piece of content — text, image, or video — as a list of numbers (a vector) in a high-dimensional space. AI models generate embeddings so that semantically similar content ends up close together in that space, enabling fast similarity search. Search engines and AI retrieval systems use embeddings to match a query to relevant documents even when the exact words differ. Understanding embeddings helps explain how modern search goes beyond keyword matching to grasp meaning and [Search Intent](/glossary/search-intent).