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
Related Claims
UnverifiedOpenAI's text-embedding-ada-002 can map text into a high-dimensional vector space, where semantically similar texts are closer together in the vector space.80% similarVerifiedEmbedding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% similarUnverified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/362341API
curl https://kongchang.com/api/v1/knowledge/claims/362341MCP
get_claim(id=362341)