Expired50% confidenceFactExact time
Current mainstream embedding models (such as OpenAI's text-embedding-3-large and Zhipu AI's embedding-3) typically output dimensions ranging from 768 to 3072.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/24/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/22/2026(expired)
Sources
Spring AI实战：ChatModel到RAG应用开发完整指南
Related Claims
UnverifiedIn AI applications, vector embeddings typically consist of hundreds to thousands of dimensions.64% similarUnverifiedTierCraft AI combines LangGraph workflow orchestration with the OpenAI o4-mini model.59% similarUnverifiedAI应用中的向量通常是几百维到几千维的高维数据，维度越高承载的语义信息越丰富58% similarUnverifiedIf vscode-antigravity-cockpit can expand support for quota monitoring of more AI service providers (such as OpenAI, Anthropic, etc.) in the future, its practical value will be further amplified.58% similarVerified当前主流AI推理模型赛道中，OpenAI有o1/o3系列，Google有Gemini的思考模式，Anthropic有Claude的extended thinking功能57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/607171API
curl https://kongchang.com/api/v1/knowledge/claims/607171MCP
get_claim(id=607171)