---
Title: "What Are Embeddings in AI? Simple Explanation"
Url: "https://computer.io/glossary/embeddings"
Topic: "AI foundations"
Description: "Embeddings are numerical vectors that represent the meaning of text, images or other data, so AI can measure similarity. Examples and how they power search."
---

# What are embeddings in AI?

Embeddings are lists of numbers (vectors) that represent the meaning of text, images or other data, so that similar items end up close together. AI systems use embeddings to compare meaning, power semantic search and retrieve context for language models.

## Example

"Reset my password" and "I forgot my login" have similar embeddings even though they share few words.

## Uses

| Use | How |
| --- | --- |
| Semantic search | Find related content |
| RAG | Retrieve context |
| Clustering | Group similar tickets |
| Deduplication | Spot duplicate issues |
| Recommendations | Similar items |

## Considerations

Choose a model suited to your languages and domain, and re-embed when content changes.

## FAQ

### How are embeddings created?

By passing data through an embedding model that outputs a vector.

### What is cosine similarity?

A common way to measure how close two embeddings are.

### Are embeddings the same as tokens?

No. Tokens are text pieces; embeddings are numeric meaning representations.

## Related terms

- [Vector database](https://computer.io/glossary/vector-database)
- [Semantic search](https://computer.io/glossary/semantic-search)
- [Retrieval-augmented generation (RAG)](https://computer.io/glossary/retrieval-augmented-generation)

## How Computer helps

- [Enterprise search and answers](https://devrev.ai/enterprise-search-and-answers)

## Further reading

- [Knowledge graph vs vector database](https://devrev.ai/blog/knowledge-graph-vs-vector-database)