Text Embedding
A dense vector representation of text (word, sentence, or document) that captures semantic meaning in a numerical format suitable for machine learning.
Evolution
Word2Vec/GloVe (static word embeddings) -> BERT (contextual embeddings) -> Sentence-BERT (sentence embeddings) -> Modern embedding models (text-embedding-3, BGE, E5). Each generation improved quality and versatility.
Use Cases
Semantic search, RAG retrieval, clustering, classification, recommendation, deduplication, and as input features for downstream ML models.