Auto-sync: update nexus workspace
This commit is contained in:
24
wiki/concepts/Embedding.md
Normal file
24
wiki/concepts/Embedding.md
Normal file
@@ -0,0 +1,24 @@
|
||||
---
|
||||
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]]
|
||||
Reference in New Issue
Block a user