[Suggestion]: Need a performance evaluation on all embedding models

[xiaofan-luan]

Is there an existing issue for this?

• [X] I have searched the existing issues

Topic

A lot of user is curious about how fast those embeddings are and how it can be improved.

We should add more documents talking about performance and how it can be optimized

Type

None

Outline

No response

[liyun95]

/assign @wxywb can you help proceed with this?