Glossary Core Concepts 1 min read

Embeddings

Also known as: Vector Embeddings, Text Embeddings, Semantic Embeddings

Dense numerical vector representations of data (text, images, audio) that capture semantic meaning, enabling similarity comparisons and machine learning operations in a continuous vector space.

Vector embeddings, word embeddings, sentence embeddings, text embeddings, embedding space, vector representation, Word2Vec, GloVe, FastText, BERT embeddings, dimensionality reduction, semantic similarity, embedding model, dense vectors

Sources & References

1
Embeddings - OpenAI API

OpenAI

Documentation
2
Efficient Estimation of Word Representations in Vector Space (Word2Vec)

Google

Research
3
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

UKP Lab, TU Darmstadt

Research

Related Terms

Retrieval-Augmented Generation

A technique that enhances AI model outputs by retrieving relevant information from external knowledge sources and incorporating it into the model's context before generating a response.

Semantic Search

A search methodology that understands the contextual meaning and intent behind a query rather than matching exact keywords, using embeddings and vector similarity to find semantically relevant results.

Tokens

The basic units of text that language models process, typically representing words, subwords, or characters. Token counts determine context window usage and API costs.

Vector Database

A specialized database designed to store, index, and query high-dimensional vector embeddings, enabling efficient similarity search used in RAG systems and AI applications.
Previous Embedding Refresh Latency
Next Encryption at Rest Protocol
Back to Glossary