[Feature] vector quantization

[yuye-aws]

This feature is proposed by @Jon-AtAWS . The target is to enable customers to choose different quantization techniques during text embedding.

Here are a few references:

1. https://opensearch.org/blog/byte-quantized-vectors-in-opensearch/
2. https://opensearch.org/docs/latest/search-plugins/knn/knn-vector-quantization/