Infrastructure Updated 2026-04

Vector Database

Definition

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

See also in the glossary

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 that use vector database

P
Pinecone
The leading vector database for AI applications
4.6/5
P
Perplexity
The AI answer engine that cites its sources
4.5/5
C
Consensus
The AI search engine for scientific literature
4.7/5
N
NotebookLM
Google's AI that turns your docs into an expert assistant
4.5/5

Frequently Asked Questions

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.