[HELP] Can Ragatouille take chunks with their embeddings as input for indexing?

- I want to index a long document with muti-vector embeddings.
- Say I have span annotation for how I want my document to be chunked and want to apply late chunking to it, that is i want to have all the embeddings of my tokens before I perform the chunking.
- This way I have contextualized chunks with multi-vector representation.
Essentially what I want to do is Late Chunking without the chunk-wise vector pooling at the end

How do I do it with ragatouille?
I know how to get multi-vector embeddings for my document but can't figure out how to index and leverage the optimizations provided by Ragatouille.

No files or tests are named. Start by reviewing RAGatouille's indexing entry points and documentation to determine whether pre-chunked multi-vector embeddings are accepted; done means establishing whether late chunking without final vector pooling can be indexed and used with Ragatouille's retrieval optimizations.

Written by the indexing model from the issue text.