Vector Database

A vector database stores embeddings and finds the closest matches to a query quickly. It's the storage layer behind semantic search and most RAG systems.

The options range from dedicated services (Pinecone, Weaviate, Qdrant) to extensions on databases you already run — pgvector on PostgreSQL being the common one. For most small and mid-sized businesses the extension is enough, and it avoids adding a system to operate and pay for.

Scale is usually misjudged in the same direction. A company's entire documentation, policies and product catalogue is often tens of thousands of chunks, which PostgreSQL handles without noticing. Dedicated vector infrastructure starts earning its keep in the millions.

Why it matters

Worth knowing so you can push back when a proposal includes a separate vector database for a knowledge base of two hundred documents.

Related terms

EmbeddingAn embedding is a list of numbers representing a piece of text's meaning, positioned so that texts with similar meanings sit close together. It lets s…RAG (Retrieval-Augmented Generation)RAG is the technique of searching your own documents for passages relevant to a question, then giving those passages to a language model along with th…

More in AI Automation & Agents

AI AgentWorkflow AutomationLarge Language Model (LLM)RAG (Retrieval-Augmented Generation)EmbeddingHallucinationHuman in the LoopGuardrailsTool Use (Function Calling)Model Context Protocol (MCP)PromptTokenEvalsIdempotencyWebhookAPI IntegrationAI Voice Agent

Need this built rather than explained?

We publish every price we charge, and you get a quote in writing before anything starts.

See every price
All terms