Embedding Model
A model whose job is to turn text (or images) into embedding vectors for search, clustering, and RAG.
An embedding model is a model specialized to convert inputs — text, images, code — into fixed-length embedding vectors that capture meaning, so similar inputs get nearby vectors. It is the encoder behind semantic search, clustering, recommendation, and the retrieval half of RAG.
Worked example: you embed every document once with an embedding model, store the vectors in a vector database, and at query time embed the query with the SAME model to find nearest neighbors — the model is what turns “meaning” into geometry. Gotcha: query and documents must be embedded by the same model (and often with the “query:” / “passage:” prefixes some models require), embedding dimension and domain-fit matter more than raw model size, and swapping embedding models means re-embedding your entire corpus — a real migration cost, not a config flip.