Embedding
A dense numerical vector that encodes the semantic meaning of text.
Embeddings map text into high-dimensional vector space where semantically similar passages cluster together. They are produced by specialized embedding models and used to power semantic search, retrieval-augmented generation, and clustering. Embedding APIs are priced separately from generation — typically much cheaper, at fractions of a cent per million tokens.
Termes Associés
A database optimized for storing and searching high-dimensional embedding vectors.
Enhancing model responses by fetching relevant documents from an external knowledge base at query time.
Search that retrieves results based on meaning rather than exact keyword matching.
The algorithm that converts raw text into a sequence of tokens for a language model.