# Embedding

> A numerical representation of data that captures semantic similarity.

- Category: Retrieval & Grounding
- Stage: Established
- Also called: Vector embedding, Semantic vector
- Canonical: https://www.joelcsaji.com/ai-dictionary/embedding

## Plain English

Embeddings let computers compare meaning, not just exact words.

## Example

A search query and a help-center article can match because their embeddings are close in vector space.

## Why it matters

Embeddings power semantic search, recommendations, clustering, and many RAG systems.

## Related

- [Vector Database](https://www.joelcsaji.com/ai-dictionary/vector-database)
- [Hybrid Search](https://www.joelcsaji.com/ai-dictionary/hybrid-search)
- [Chunking](https://www.joelcsaji.com/ai-dictionary/chunking)

## Sources

- [Google Cloud Generative AI Glossary](https://docs.cloud.google.com/docs/generative-ai/glossary)
- [IBM: Retrieval-Augmented Generation](https://www.ibm.com/think/topics/retrieval-augmented-generation)