Voyage AI

Vector embeddings (or embeddings) are mathematical representations of text or other unstructured data created by translating words or sentences into numbers—a language that computers can understand. They bridge the rich, nuanced world of human language (text, images, audio, and video) and the precise environment of machine learning models (numbers) by representing data points numerically.

Embedding models are neural network models (e.g., transformers) that convert unstructured and complex data—such as documents, images, audios, videos, or tabular data—into dense numerical vectors (i.e. embeddings) that capture their semantic meanings.

Rerankers are neural networks that output relevance scores between a query and multiple documents. It is common practice to use the relevance scores to rerank the documents initially retrieved with embedding-based methods (or with lexical search algorithms such as BM25 and TF-IDF). Selecting the highest-scored documents refines the retrieval results into a more relevant subset.

Vector search (or semantic search) is a technique that transforms unstructured data into numbers using machine learning models and then measures similarity to produce relevant results not possible with traditional search methods like full-text or keyword search.