Text Embedding in Elastic Search

Elastic Stack Elasticsearch
1

Hi All,

I have implemented text embedding using doc 2 vec and stored the vectors in elastic search , using cosine similarity I am trying to search for similar texts. But the issue is whenver I am giving a same text twice the output differs , for the same text the output changes constantly and also the scores differs.

Can anyone explain me why is this happening? I am confused...

Hope I am clear..
....

Thank you

2

I am giving a same text twice the output differs

Can you please clarify the meaning of this? Is this on the stage of generating the vector embeddings from a text? If yes, elasticsearch is not responsible for this.

3

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.