Files
nexus/wiki/concepts/Embedding.md

25 lines
900 B
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "Embedding"
type: concept
tags: [embedding, vector, nlp, similarity]
aliases: [Embedding, 向量化, Text Embedding, 词向量]
last_updated: 2025-12-20
---
## Definition
Embedding向量化将词或文本转换为浮点数向量的技术。通过计算向量之间的距离欧氏距离、余弦相似度等判断语义关联性。
## Key Facts
- 词的意义取决于上下文语境(如"苹果"可指水果或手机)
- Embedding 将词转化为高维浮点向量
- 语义相近的词在向量空间中距离更近
- 示例:一百和两百的距离近,而一百离一千远,说明一百比一千更接近两百的语义
- 是 [[RAG]] 检索的基础技术
## Connections
- [[RAG]] ← 依赖 ← [[Embedding]]
- [[Vector-Embedding]] ← 同义词 ← [[Embedding]]
## Sources
- [[大模型相关术语和框架总结llm-mcp-prompt-rag-vllm-token-数据蒸馏]]