Vector Search

Vector search (also called vector similarity search or semantic search) is the technique of finding information by comparing embedding vectors rather than matching keywords. It represents a fundamental shift in how discovery works—from lexical matching to semantic understanding.

Traditional search engines match query terms against document terms. Vector search converts both queries and documents into high-dimensional vectors and finds the nearest neighbors in that space. A search for "affordable electric cars" would find content about "budget EVs" or "low-cost battery vehicles" even if those exact words never appear—because the concepts are close in embedding space.

The infrastructure supporting vector search has matured rapidly. Purpose-built vector databases—Pinecone, Weaviate, Qdrant, Milvus, Chroma—handle billions of vectors with millisecond query times. Traditional databases have added vector capabilities: PostgreSQL (via pgvector), MongoDB, Elasticsearch, and Redis all support vector indexing. Approximate nearest neighbor (ANN) algorithms like HNSW and IVF make high-dimensional search practical at scale.

Vector search is the enabling technology behind Retrieval-Augmented Generation (RAG)—the dominant architecture for grounding LLM responses in specific knowledge bases. It powers AI search engines like Perplexity, product recommendation systems, content similarity matching, and the GEO landscape where AI systems discover and cite relevant content. As the agentic web matures, vector search becomes the "memory layer" that gives AI agents access to relevant context from massive data stores.