---
title: "Embedding"
type: "glossary-term"
category: "AI & LLMs"
canonical_url: "https://www.graphcanon.com/glossary/ai-and-llms/embedding"
updated: "2026-07-09"
---

# Embedding

**An embedding is a list of numbers (a vector) that represents the meaning of a piece of text, image, or code so that similar things sit close together.**

An **embedding** turns content - a sentence, a document, an image - into a fixed-length vector of numbers. The model that produces it is trained so that items with similar meaning land near each other in that vector space.

Once content is embedded, "find similar" becomes a math operation (measuring distance between vectors) instead of exact keyword matching. Embeddings are the backbone of vector search, semantic search, and RAG.

## In GraphCanon

GraphCanon stores an embedding for each tool so it can measure how semantically close two tools are - useful for suggesting neighbours and detecting miscategorization.

## See also

- [Vector databases category](/categories/vector-databases)

## Related terms

- [Vector search](/glossary/ai-and-llms/vector-search.md)
- [Semantic search](/glossary/ai-and-llms/semantic-search.md)
- [Retrieval-augmented generation (RAG)](/glossary/ai-and-llms/retrieval-augmented-generation.md)

[AI & LLMs](/glossary/ai-and-llms.md) · [All glossary terms](/glossary.md)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon`](/api/graphcanon)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_