Retrieval
Vector Search (Semantic Search)
Also known as semantic search, similarity search
Vector search finds the nearest matches to a query by comparing embeddings, not exact keywords.
It lets a RAG pipeline surface a passage about "cancel my plan" for a user who typed "stop billing me."
In production it is usually paired with metadata filters and a reranker.
Raw nearest-neighbor results alone are rarely precise enough to hand straight to the model.
← Back to the full glossaryRelated terms
Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) retrieves relevant passages at query time and feeds them into an LLM's context. Embeddings Embeddings are numeric vectors that place similar content close together in vector space. Chunking Chunking splits source documents into smaller passages before embedding, so retrieval returns focused text.