Verified80% confidenceFactExact time

嵌入模型（如OpenAI的text-embedding-ada-002或开源的BGE系列）将文本转换为高维向量，通常为768或1536维

6

Sources

80%

Confidence

Medium-term (~90 days)

Relevance

7/2/2026

First Seen

Valid until: 9/30/2026

Sources

AI大模型学习路线拆解：三阶段从应用开发到模型微调

bilibiliAI因斯坦大模型6/13/2026

Related Claims

Unverified向量数据库通过嵌入模型（如OpenAI的text-embedding-3-large或开源的BGE-M3）将文本转化为数百至数千维的浮点数向量，向量距离对应语义相似度77% similar VerifiedOpenAI 的 text-embedding-3-small 模型会将文本转换为 1536 维的浮点数数组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77% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/47803

API

curl https://kongchang.com/api/v1/knowledge/claims/47803

MCP

get_claim(id=47803)