Innoworks Innoworks
Book an intro call

Glossary AI technique

Vector database

What is a vector database?

A vector database stores content as series of numbers that capture meaning, so AI can quickly find the passages that match a question.

Also known as vector databasevector storeembeddings database

Ordinary search looks for words. A vector database searches on meaning: a question about a notice period also finds the passage about the end of the agreement. For that, every passage is turned into an embedding, a series of numbers that represents its meaning.

Vector databases are the engine behind RAG: the system first retrieves the relevant passages and lets the language model turn them into an answer, with the source attached.

That is how you build a knowledge base on your own documents; see knowledge management with AI.

Last updated: 4 October 2026

Relatedterms

Read on in the glossary

All terms
AI techniqueRAG (Retrieval-Augmented Generation)RAG lets a language model first retrieve the right documents from your own sources and base its answer on those, so it draws on your knowledge instead of only its training.Strategy & implementationKnowledge managementKnowledge management is capturing, organising and making findable the knowledge in an organisation, so everyone can use the same, current information.AI techniqueLLM (Large Language Model)An LLM is a large language model trained on enormous amounts of text, which lets it understand and generate language; it is the engine under tools like ChatGPT, Claude and Gemini.AI techniqueAI agentAn AI agent is software that pursues a goal on its own: it plans the steps, uses tools or systems, checks the result and adjusts course, without a human directing every step.

You can feel it has to change,
we show you how.

You know where the friction is. We help you figure out how AI can genuinely fix it.

Book an intro call

Not ready for a conversation yet? Get honest AI advice first →

30 minutes. Online or in Enschede. You decide.