---
title: Vector Database
date: 2026-06-01T17:19:00+02:00
author: Hannes Heckel
canonical_url: "https://www.fast-lta.de//en/glossary/vector-database"
section: Glossar
---
Classic search systems (full-text search, SQL) find documents that contain exactly the searched terms. A vector database works differently: each document is converted into a high-dimensional numerical vector by an AI model (embedding). Similar content is geometrically close in vector space.

When a search query arrives, the query is also converted into a vector, and the system finds documents whose vectors are most similar to the query — regardless of whether exactly the same words are used. This enables semantic search: a question about ​‘vacation policy for remote work’ will also find documents using the terms ​‘home office’ and ​‘time off in lieu’.

In a RAG architecture, the vector database is the central component: it contains all indexed enterprise documents as embeddings and delivers the most relevant text passages to the language model when a question arrives. Silent AI includes an integrated vector database — no external system is required.

 

## Frequently asked questions

#### Do I need to set up a separate vector database for Silent AI?

No. Silent AI contains a fully integrated vector database. It is automatically populated when the connectors (SharePoint, Confluence, file servers, etc.) ingest documents. No external database product, no separate installation.

#### How current is the data in the vector database?

Connectors synchronize the dataset at configurable intervals. New or changed documents are automatically re-indexed. The degree of currency depends on the synchronization frequency and is configurable.