Update langchain_community/embeddings/huggingface.py for Sentence-Transformers v2.4.0

[johneckberg]

Checked

• I searched existing ideas and did not find a similar one
• I added a very descriptive title
• I've clearly described the feature request and motivation for it

Feature request

Update huggingface.py as Sentence Transformers now supports prompt templates.

Some of the logic for embedding using HuggingFaceBgeEmbeddings might now be redundant as prompts/instructions can be handled inside of Sentence Transformers. Note that not all INSTRUCTOR models are not supported in Sentence Transformers yet. I would be more than happy to work on this!

Motivation

Yesterday, a new version of the sentence-tranformers library was released. This version now supports prompt templates as well as some INSTRUCTOR models through the use of the prompts parameter. Prompts is an optional argument that accepts a dictionary of prompts with prompt names to prompt texts. Prompts can also be passed as a string using the prompt option.

Proposal (If applicable)

No response