jina-ai/vectordb

Does vectordb search the document only with embedding?

jiwoochris opened this issue · 4 comments

Thank you for your great project.
It's really good.

My question is "Does vectordb search the document only with embedding?"
I mean the search algorithm.

class ToyDoc(BaseDoc):
    text: str = ""
    embedding: NdArray[1536] 

If I set ToyDoc Class like this. (refer to your examples)
What does the vairable "text" do?

Just for save the information related to embedding?

Or use some search algorithm for "text" too?

JoanFM commented

Hey @juicyjung ,

It is only used to sabe the informstion so that at retrieve time u have the trxt and do not need to map embeddings to IDs on ur own

Hey @juicyjung ,

It is only used to sabe the informstion so that at retrieve time u have the trxt and do not need to map embeddings to IDs on ur own

um..
I don't get it.

I don't need to map text and embedding??

vectordb search by text? not embedding?

If I add some variable to save more information, It doesn't affect to the search right?

JoanFM commented

Exactly, the search is done only by EMBEDDING. Other fields are just to store them without any effect on results.

I got you bro, Thanks a lot