Add embedding instruction prompt support for to hf-embedder

[jobergum]

It's becoming the norm to have prompt prefixes for text embedding models. I think we should add this to the hf-embedder.

<component id="snow" type="hugging-face-embedder">
        <transformer-model url="https://huggingface.co/Snowflake/snowflake-arctic-embed-l/resolve/main/onnx/model_int8.onnx"/>
        <tokenizer-model url="https://huggingface.co/Snowflake/snowflake-arctic-embed-l/raw/main/tokenizer.json"/>
        <normalize>true</normalize>
        <pooling-strategy>cls</pooling-strategy>
        <instruction-prompt>
           <query>Represent this sentence for searching relevant passages:</query>
           <document>passage:</document>
       </instruction-prompt>
</component>

The embedder would then prepend the input with these instructions depending on the context (query or indexing)

[jobergum]

Alternatives

Alternative 1

<instruction-prompts>
           <query>Represent this sentence for searching relevant passages:</query>
           <document>passage:</document>
</instruction-prompt>

Alternative 2

<prefixes>
           <query>Represent this sentence for searching relevant passages:</query>
           <document>passage:</document>
</prefixes>

Alternative 3

<prepend query="Represent this sentence for searching relevant passages:" document="passage:"/>

Alternative 4

<prepend>
           <query>Represent this sentence for searching relevant passages:</query>
           <document>passage:</document>
</prepend>

Since normalize is a verb I think that prepend is a good alternative, so I'm voting for alternative 4.