[ML] Custom Service add embedding type support

[jonathan-buttner]

This PR addresses the feedback item from the original PR: #127939

This PR adds support for embedding_type so users can specify the format of the text embeddings returned by the upstream service.

Supported embedding types are:

• float (default if not included)
• byte
• bit (or binary)

Comments:
#127939 (comment)

Example

PUT _inference/text_embedding/test-text-embedding
{
    "service": "custom",
    "service_settings": {
        "secret_parameters": {
            "api_key": "<api key>"
        },
        "url": "https://api.cohere.com/v2/embed",
        "headers": {
            "Authorization": "bearer ${api_key}",
            "Content-Type": "application/json"
        },
        "request": "{\"texts\": ${input}, \"model\": \"embed-v4.0\", \"input_type\": ${input_type}, \"embedding_types\": [\"binary\"]}",
        "response": {
            "json_parser": {
                "text_embeddings":"$.embeddings.binary[*]",
                "embedding_type": "binary"
            }
        },
        "input_type": {
            "translation": {
                "ingest": "search_document",
                "search": "search_query"
            },
            "default": "search_document"
        }
    }
}

POST _inference/text_embedding/test-text-embedding
{
    "input": ["The quick brown fox jumps over the lazy dog", "awesome"]
}

[elasticsearchmachine]

Pinging @elastic/ml-core (Team:ML)

[jonathan-buttner]

inferenceId wasn't being used.

[jonathan-buttner]

The element type logic has been delegated to the TextEmbeddingResponseParser so removing it from being hard coded to float here.

[jonathan-buttner]

For older versions, we'll read it but ignore it. It should only be float which we'll default to in the TextEmbeddingResponseParser.

[jonathan-buttner]

The TextEmbeddingResponseParser will now return different types of results depending on the embedding type so we need this to be the base results type to cover all them

[prwhelan]

We never included elementType in the toXContent method, so we don't have to worry about backwards compatibility with older versions of this model, correct?

[jonathan-buttner]

Yep that's correct, it was just hard coded previously.