How to extract embeddings generated by Colbert?

I am trying to use RAPTOR hierarchical clustering with Colbertv2 but I need to extract the embeddings generated by the model for the clustering step which involve a Gaussian Mixture Model.

How do I go about doing that? Any help would be appreciated.

Start with the RAPTOR hierarchical clustering and ColBERTv2 integration points; the issue names no file or test. Check how embeddings are exposed for the Gaussian Mixture Model step, and document the supported extraction path or define the required code change.

Written by the indexing model from the issue text.