Unverified60% confidenceFactTime unknown

现代Embedding模型（如OpenAI的text-embedding-ada-002、阿里的千问Embedding系列）能够将整个句子或段落编码为固定维度的稠密向量，通常为768维或1024维

2

Sources

60%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

Agentic RAG实战：原理剖析与LangChain代码实现指南

bilibiliAI大模型__

Related Entities

text-embedding-ada-002model OpenAIcompany 千问Embeddingmodel 阿里company

Related Claims

Unverified嵌入模型可将文本压缩为1536维或1024维的浮点向量，OpenAI的text-embedding-ada-002和Cohere的embed-multilingual是常见示例80% similar UnverifiedRAG的向量检索依赖Embedding模型将文本编码为稠密向量，通常为512至4096维，通过余弦相似度或内积计算语义距离74% similar Unverified文本经Embedding模型编码为768至3072维的浮点向量，存入向量数据库后通过近似最近邻算法（HNSW、IVF等）在毫秒级完成相似度检索74% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/26805

API

curl https://kongchang.com/api/v1/knowledge/claims/26805

MCP

get_claim(id=26805)