# What is Vector Embeddings? | Yungle glossary

> Vector embeddings are the numerical representations AI models use to understand meaning and similarity.

Source: https://yungle.ai/glossary/vector-embeddings/

1.  [Resources](https://yungle.ai/resources)
2.  Glossary

Glossary · V

# Vector Embeddings

In plain words

Vector embeddings are numerical representations of words, sentences, or documents that capture their meaning in a way AI models can compare mathematically. Embeddings are what let AI search systems match a user's query to the most semantically relevant content, even when the exact wording differs.

Example

An AI search tool matches the question “how do I get cited by ChatGPT?” to a page about AEO because their embeddings are close in meaning.

Related resources

-   Glossary

    ## Large Language Model

    An LLM is the type of AI model, like GPT or Gemini, that powers modern AI search and chat answers.

    [See term](https://yungle.ai/glossary/large-language-model-llm)
-   Glossary

    ## Retrieval-Augmented Generation

    RAG is the technique AI systems use to pull in outside sources before generating an answer.

    [See term](https://yungle.ai/glossary/retrieval-augmented-generation-rag)
-   Insight

    ## How to Write Copy AI Answer Engines Can Quote

    A practical guide to writing website copy that ChatGPT, Perplexity and Google AI Overviews can extract, attribute to your brand and cite.

    [Read insight](https://yungle.ai/insights/writing-copy-that-ai-answer-engines-can-quote)
-   Glossary

    ## Natural Language Processing

    NLP is the branch of AI that lets computers understand, interpret, and generate human language.

    [See term](https://yungle.ai/glossary/natural-language-processing-nlp)

Next step

## Let's talk

_Image: Engraving of a jungle panorama with mountains_

Inspired by Tulum, QROO, MX