A user should be able to use SPLATE

[mtbarta]

Paper: https://arxiv.org/html/2404.13950v1

As an MLE, I want to use SPLATE to get the same quality of results with less latency.

This will involve several tasks:

1. Create a new Index type for sparse indexing.
2. Create a new candidate generator using SPLATE.
3. Create a new retriever based on SPLATE.