This ticket is a sub compound of implementing sparse vector functionality to Jina. Currently, there is some low-level code implementation to support sparse vectors. Over the course of this epic we will implement the remaining logic. Main goal is to be able to build a fully neural search system where embedding representations are sparse vectors. This will support certain usecase like TD-IDF, and provide the functionitilty for graph embedding in the future.
Acceptance Criteria
We should have someway to perform Nearest Neighbours or Approximate Nearest Neighbours search on sparse vectors stored within Jina.
Feature Request
This ticket is a sub compound of implementing sparse vector functionality to Jina. Currently, there is some low-level code implementation to support sparse vectors. Over the course of this epic we will implement the remaining logic. Main goal is to be able to build a fully neural search system where embedding representations are
sparse vectors
. This will support certain usecase like TD-IDF, and provide the functionitilty for graph embedding in the future.Acceptance Criteria