OpenAI embeddings are models that turn text into lists of numbers, so a program can measure how closely two pieces of text are related.
In plain words
An embedding is a vector: a long list of decimal numbers. OpenAI's embedding models, such as text-embedding-3-small and text-embedding-3-large, produce one for any text you send. Texts with similar meaning get vectors that sit close together, so a short distance means closely related. You can store the vectors in a vector database and use them to search, group, recommend or classify text. You can also ask for shorter vectors to save space.
A quick example
Imagine a help centre that turns every article into an embedding once. When a customer types a question, it embeds the question too and shows the articles whose vectors are nearest, even if they use different words.
Where you'll meet it
- Search and question answering over your own documents.
- Recommendations and clustering.
- Classification and anomaly detection.
Related
Sources
- DocsVector embeddings, OpenAI API docs · read 29 Sept 2026
- DocsNew embedding models and API updates, OpenAI · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.