Unverified50% confidenceFactExact time
向量嵌入通常使用针对代码训练的嵌入模型（如OpenAI的text-embedding-3、Voyage AI的voyage-code-2），将代码块映射为768维或1536维向量
1
Sources
50%
Confidence
Long-term
Relevance
8/4/2026
First Seen
Sources
Tempest开源工具：并行AI编程智能体Token消耗降低64%
Related Claims
VerifiedCode vectorization typically uses embedding models specifically designed for code semantics, such as OpenAI's text-embedding-3 or the CodeBERT series.77% similarUnverifiedModern code intelligence tools are typically based on models specifically trained on code data, such as OpenAI Codex, DeepSeek Coder, and Tongyi Qianwen Code Edition.71% similarUnverifiedCommonly used code embedding models include OpenAI's text-embedding series and Voyage AI's code-specific models, with vector databases such as Pinecone and Chroma responsible for storage and retrieval.70% similarVerifiedThe OpenAI Codex desktop version is based on the codex-1 model, which has been fine-tuned with reinforcement learning and specifically optimized for code generation, debugging, and engineering tasks.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/681175API
curl https://kongchang.com/api/v1/knowledge/claims/681175MCP
get_claim(id=681175)