Add support for 'quantize_embeddings'

I'm looking for quantize the embeddings to speed up the process of indexing / searching / etc.

For example in `sentence_transformers` there is [quantize_embeddings](https://sbert.net/docs/package_reference/quantization.html#sentence_transformers.quantization.quantize_embeddings):
```python
binary_embeddings = quantize_embeddings(embeddings, precision="binary" | "int8")
```

https://sbert.net/examples/applications/embedding-quantization/README.html

Is anything similar already available? Or is it possible to add it for the usage of ColBERT in RAGatouille?

No repository files, tests, or entry points are named. Start by tracing how RAGatouille handles embeddings during indexing and searching, then compare those paths with the linked sentence-transformers quantization documentation. Done means an agreed design and support for the requested embedding quantization modes.

Written by the indexing model from the issue text.