Architecture
Embedding
A list of numbers (a vector) representing the meaning of text, an image or audio, so similar things have nearby vectors.
Embedding models turn documents into vectors that can be compared mathematically. They power semantic search, recommendations, clustering and the retrieval step of RAG. They are priced per million input tokens and are much cheaper than chat models.
Frequently asked questions
What does Embedding mean?
A list of numbers (a vector) representing the meaning of text, an image or audio, so similar things have nearby vectors. Embedding models turn documents into vectors that can be compared mathematically. They power semantic search, recommendations, clustering and the retrieval step of RAG. They are priced per million input tokens and are much cheaper than chat models.