fix RAG with quantized embeddings notebook (#24422)
1. Fix HuggingfacePipeline import error to newer partner package
2. Switch to IPEXModelForCausalLM for performance
There are no dependency changes since optimum intel is also needed for
QuantizedBiEncoderEmbeddings
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
