A managed Google Cloud service for indexing embeddings and performing large-scale, low-latency similarity (nearest neighbor) searches, a core component of RAG architectures within Vertex AI.
In GENAI-L (Domain 3) it is combined with the Embeddings API in the RAG pipeline: documents are converted into vectors (Embeddings API) and indexed for similarity retrieval (Vector Search) before the context is passed to the generative model.
Vertex AI Vector Search is a concept that can show up on the exam. Check the full guide to see it in context.