Concept· 2 min
What is an embedding?
An embedding turns text, images or audio into a list of numbers that capture meaning — the currency of semantic search and RAG.
Key idea
Similar meanings end up close together in vector space, so cosine similarity gives you a 'how related' score for free.
Example
'king - man + woman ≈ queen' — a classic word-embedding demo that showed vectors encode real relationships.
What to remember
- Foundation of vector search, recommendation and clustering
- Model choice matters — text-embedding-3-large ≠ ada-002
- Store in a vector DB (pgvector, Pinecone, Weaviate)