← Back to Glossary
Embedding Model
A specialized neural network designed to turn text strings into dense vector representations for similarity math.
Why it exists
Generative LLMs produce text. Embedding models (e.g. OpenAI text-embedding-3, BGE) produce float vectors optimized for search distance.
How it works
Passes text through encoder layers to output fixed-size float arrays (e.g. 768 or 1536 numbers) tuned for semantic retrieval.
Related terms
Where you'll use this
roadmap