Jump go di content
Glossary

Vector Search

Vector search find content by meaning instead of exact words. Text dey converted into high-dimensional embeddings, and similarity metric like cosine distance rank stored vectors by how close dem dey to query vector, returning related passages even when no keywords match.

Synonym dem: semantic search, similarity search, nearest-neighbor search, embedding search

Vector search power semantic retrieval: instead of matching strings, e match meaning. Query dey embedded into di same vector space as indexed content, and index return nearest vectors by distance metric. To stay fast at scale, production systems use approximate nearest-neighbor indexes wey accept tiny accuracy trade-offs for major latency wins. Vector search most effective when paired with keyword search in hybrid retriever, so exact identifiers no lost to pure semantic matching.

Question dem wey people dey ask well-well

Wetin be embedding for vector search?
Embedding na numeric vector wey represent meaning of piece of text, produced by embedding model. Texts with similar meaning land close together in vector space.
Wetin be approximate nearest neighbor (ANN) search?
ANN search trade small amount of accuracy for big speed gains, using index structures so similarity lookups stay fast as stored vectors grow into millions.