Vector Database

Definition

A vector database is a specialized data store that indexes and retrieves high-dimensional numerical embeddings by similarity rather than by exact match. Vector databases power retrieval-augmented generation (RAG) systems by finding the documents most semantically relevant to a user query in milliseconds, even across millions of stored records.

Traditional databases find rows by exact or pattern-matched values. Vector databases find rows by meaning -- the embedding of "invoice late payment" is close to "overdue bill" even though no words match. This semantic search capability is what makes RAG and AI assistants possible over large document sets.

Common vector database options

pgvector -- Postgres extension; easiest to operate if you already use Postgres
Pinecone -- managed, serverless; fastest to production
Weaviate -- open-source; strong hybrid search (vector + keyword)
Qdrant -- open-source; good for on-premises GovCon deployments

When to choose which

For most enterprise AI projects, pgvector on an existing Postgres instance is the lowest-friction starting point. Migrate to a dedicated vector database if you exceed 10 million vectors or need sub-10ms p99 retrieval at scale.

Related terms

AI Implementation

AI implementation is the end-to-end process of integrating artificial intelligence into a business's existing workflows, systems, and software -- from identifying high-ROI automation opportunities through deploying production-ready AI systems. Done well, it replaces manual, repetitive processes and can reduce operational labor cost by 30-60% within the first year.

RAG (Retrieval-Augmented Generation)

Retrieval-augmented generation (RAG) is an AI architecture that supplements a large language model's static training knowledge with real-time retrieval from a private or external knowledge base. RAG reduces hallucinations by grounding LLM responses in verified source documents, making it the standard pattern for enterprise AI assistants built on proprietary data.

LLM (Large Language Model)

A large language model (LLM) is a deep-learning model trained on billions of text tokens to predict and generate human-readable language. LLMs such as GPT-4, Claude, and Gemini power chatbots, document summarization, code generation, and AI workflow automation -- and serve as the reasoning engine inside RAG systems and AI agents.

Embeddings

Embeddings are dense numerical vectors -- typically 768 to 3,072 floating-point numbers -- that represent the semantic meaning of a piece of text, image, or other data. Documents with similar meaning produce embeddings that are close together in vector space, enabling AI systems to find relevant content by meaning rather than keyword matching.

← Back to full glossary

Need help implementing this in your business?

Code and Trust translates AI concepts like vector database into working implementations — starting with a workflow audit that shows exactly where it creates ROI.

Schedule AI Audit →