admin 管理员组

文章数量: 1086019

I'm using Pinecone with cosine metric to perform similarity search. I have the word "dog" with the llama-text-embed-v2 and I'm searching the word "dog". I'm expected a cosine similarity of 1 or very close to it, but I'm getting such a low number.

Maybe I'm miss understanding something, but why is the score so low?

本文标签： Low Cosine Similarity for Identical Words Using llamatextembedv2 in PineconeStack Overflow

版权声明：本文标题：Low Cosine Similarity for Identical Words Using llama-text-embed-v2 in Pinecone - Stack Overflow 内容由网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：http://roclinux.cn/p/1744063645a2527181.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。