Unverified50% confidenceFactExact time

text-embedding-ada-002将文本转化为1536维的稠密向量，语义相近的文本在向量空间中距离更近

1

Sources

50%

Confidence

Long-term

Relevance

7/9/2026

First Seen

Sources

OpenAI大模型开发入门：模型选型、Token计费与API实战指南

bilibiliSCI论文发刊7/8/2026

Related Claims

UnverifiedOpenAI的text-embedding-ada-002能将文字映射到高维向量空间，语义相近的文本在向量空间中距离更近80% similar VerifiedEmbedding是将文本转换为高维数值向量的过程，语义相近的文本在向量空间中距离更近77% similar 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76% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/362341

API

curl https://kongchang.com/api/v1/knowledge/claims/362341

MCP

get_claim(id=362341)