Vector Database
A database optimised for storing and querying high-dimensional vector embeddings using approximate nearest-neighbour algorithms, used as the retrieval layer in RAG systems and semantic search.
How it works
Vector databases (Qdrant, Weaviate, Milvus, pgvector on Postgres, and others) store millions or billions of embeddings and answer "find the k closest vectors to this query vector" in milliseconds. The underlying algorithms (HNSW, IVF, ScaNN) trade off recall against query latency at scale. For enterprise deployment, the architectural decision is whether to use a managed vector database service (which sends queries and embeddings to a third-party) or a self-hosted instance running inside the firm's own tenancy. Ayoob AI defaults to self-hosted for regulated UK clients, typically pgvector on Postgres or a Qdrant deployment on the client's own infrastructure, so no embeddings or query content leaves the firm.
Related terms
Vector Embedding
A high-dimensional numerical representation of text, image, or other content that places semantically similar items close together in vector space, enabling similarity search and clustering.
Retrieval-Augmented Generation (RAG)
An architecture pattern that grounds language model outputs in retrieved documents from a private corpus, reducing hallucination and enabling answers based on the firm's own data rather than the model's training set.
Semantic Search
Search that ranks results by meaning rather than exact keyword match, using vector embeddings to retrieve semantically-similar content even when no terms overlap.
Want to see this technology in action?
Book a Discovery Call