Infrastructure Aktualisiert 2026-04

Vector Database

Definition

A vector database stores embeddings for semantic search and RAG at scale.

Siehe auch im Glossar

E
Embedding
An embedding is a numerical representation (vector) of text or data, capturing its semantic meaning.
R
RAG (Retrieval-Augmented Generation)
RAG is a technique that connects an LLM to external data sources to generate more accurate and up-to-date answers.
L
LLM (Large Language Model)
An LLM is an AI model trained on billions of texts, capable of understanding and generating human language.
A
AI API
An AI API allows developers to integrate artificial intelligence capabilities into their applications.

Tools, die vector database verwenden

P
Pinecone
Die führende Vektor-Datenbank für KI-Anwendungen
4.6/5
P
Perplexity
Die KI-Antwortmaschine, die ihre Quellen zitiert
4.5/5
C
Consensus
Die KI-Suchmaschine für wissenschaftliche Literatur
4.7/5
N
NotebookLM
Googles KI, die Ihre Dokumente in einen Experten-Assistenten verwandelt
4.5/5

Häufig gestellte Fragen

Why not a regular SQL database?
SQL searches for exact matches. A vector database finds semantically similar content, even with different words.
Is Pinecone the only option?
No. Weaviate, Qdrant, Chroma and pgvector (PostgreSQL) are popular alternatives.