CONCEPT

Vector Search

Authoritative Definition

Retrieval mechanism based on calculating mathematical distances between high-dimensional vector embeddings of queries and documents.

Overview & Technical Description

Vector search is the foundational infrastructure powering modern semantic retrieval. It operates by converting unstructured data—text, images, or audio—into dense, high-dimensional arrays of floating-point numbers known as embeddings. These embeddings are generated by neural networks trained to position conceptually similar items close together in the vector space. When a search query is issued, it is embedded using the same model, and the system retrieves the nearest document vectors using mathematical distance metrics such as cosine similarity, Euclidean distance (L2), or dot product. This paradigm shifts search from brittle, exact-keyword matching to fluid, natural-language understanding. It is widely utilized as the primary retrieval engine in RAG architectures, providing contextual memory for large language models. To scale efficiently across millions or billions of embeddings, vector search engines implement Approximate Nearest Neighbor (ANN) algorithms, such as Hierarchical Navigable Small World (HNSW) or Inverted File Index (IVF). These algorithms trade a negligible amount of accuracy for massive gains in query speed and computational efficiency. Beyond simple retrieval, production-grade vector search systems integrate seamlessly with traditional database capabilities. They support metadata filtering, allowing users to constrain similarity searches to specific dates, tags, or tenant IDs. This combination of dense semantic retrieval and hard deterministic filtering ensures that AI agents can quickly surface contextually relevant, permissions-safe data from massive enterprise repositories.

Editorial Notes

While cosine similarity is the standard default, dot product is often preferred for normalized embeddings due to its computational efficiency. Effective metadata filtering typically requires vector databases that support Single-Stage Filtering to prevent "missing recall" issues.

Related Concepts

Companies Implementing Vector Search

18 listed
Chroma
Open-source AI-native embedding database designed for developer simplicity.
ClickHouse
Columnar database management system supporting fast vector indexing and analytics.
Databricks
Data intelligence platform offering Databricks Vector Search and governance for AI context.
DuckDB
In-process analytical database system supporting fast local vector indexing and SQL querying.
LanceDB
Developer-friendly, embedded vector database for AI applications built on Lance columnar format.
Marqo
Vector search engine providing end-to-end vector generation, storage, and retrieval.
MongoDB
Developer document database offering Atlas Vector Search for operational context data.
Neon
Serverless Postgres database platform supporting pgvector for scalable AI context storage.
Pinecone
Fully managed vector database built for high-throughput semantic search and RAG.
Qdrant
Vector similarity search engine with extended filtering support and cloud deployment.
Redis
In-memory data store providing vector search and RedisVL for semantic caching.
SingleStore
Distributed SQL database optimized for high-speed vector search and transactional context.
Snowflake
Cloud data warehouse featuring Cortex Search and vector functions for enterprise data context.
Supabase
Open-source Firebase alternative with integrated Postgres and pgvector search.
Turbopuffer
Stateless vector database service built on object storage for ultra-low-cost vector indexing.
Vespa.ai
Big data serving engine for vector search, lexical search, and structured queries at scale.
Weaviate
Open-source vector database for AI application data with hybrid search and vector index modularity.
Zilliz / Milvus
Cloud-native distributed vector database built to handle billion-scale vector embeddings.

Products & Tools