Vector
Expanded definition
Vectors are the storage format for embeddings. Index structures such as HNSW or IVF approximate nearest neighbors at scale. Distance metrics (cosine, L2, inner product) must match how the embedding model was trained. A vector is not a citation and not a guarantee of topical match; metadata filters and rerankers still matter. Do not confuse this with the unrelated sense of vector as in vector graphics.
Related terms
Explore adjacent ideas in the knowledge graph.
Vector FAQ
What is Vector?
In AI search, a vector is a list of numbers that locates an item in embedding space so nearby vectors can be retrieved as similar.
How is Vector used in AI systems?
Vectors are the storage format for embeddings. Index structures such as HNSW or IVF approximate nearest neighbors at scale. Distance metrics (cosine, L2, inner product) must match how the embedding model was trained. A vector is not a citation and not a guarantee of topical match; metadata filters and rerankers still matter.
Related
Comparisons, tools, and models that connect to this idea.