Files
nexus/wiki/concepts/Embedding-Vector.md
2026-04-14 16:02:50 +08:00

24 lines
702 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 Vector"
type: concept
tags: [Embedding, 向量, 语义表示]
---
## Definition
Embedding Vector是文本的数值表示捕获语义信息将文本转为固定长度向量。
## Core Mechanism
- 通过深度学习模型将文本编码为稠密向量
- 语义相似的文本在向量空间中距离相近
- 通常128-2048维浮点数向量
## Key Properties
- 受Context Window限制单次编码的文本长度
- 依赖Embedding Model质量
- 计算相似度通常用余弦相似度或点积
## Connections
- [[Indexing]] ← 输出 ← [[Embedding Vector]]
- [[Retrieval]] ← 依赖 ← [[Embedding Vector]]
- [[Vector Store]] ← 存储 ← [[Embedding Vector]]