Last updated: April 5, 2026 · Model Architecture · by Daniel Ashford

What is Embeddings?

QUICK ANSWER

Numerical representations of text that capture semantic meaning — used in search and RAG systems.

Definition

Embeddings are dense numerical vectors that represent text in a way that captures semantic meaning. Texts with similar meanings have embeddings that are close together in vector space, while dissimilar texts are far apart.

How It Works

Modern embedding models produce vectors with 768 to 3,072 dimensions. They are the foundation of semantic search and RAG pipelines. Major embedding models include OpenAI text-embedding-3, Cohere embed-v4, and open-source models like BGE and E5.

Example

If you embed "How do I reset my password?" and "I forgot my login credentials," these would have very similar embedding vectors despite using different words.

Related Terms

RAG (Retrieval-Augmented Generation)
A technique that gives LLMs access to external documents to improve accuracy and reduce hallucination.
Vector Database
A specialized database for storing and searching embeddings — the backbone of RAG systems.
Tokens
The basic units of text that LLMs process — roughly 3/4 of a word.

See How Models Compare

Understanding embeddings is important when choosing the right AI model. See how 12 models compare on our leaderboard.

View Leaderboard →Our Methodology
← Browse all 47 glossary terms
DA
Daniel Ashford
Founder & Lead Evaluator · 200+ models evaluated