[ML] EIS Unified chat completions integration

[jonathan-buttner]

WIP

This PR implements the changes to add chat completion support to EIS within the inference plugin.

The current state of this PR is hard coded to work against OpenAI.

Testing

Run elasticsearch with a few feature flags enabled:

run-es -Des.inference_unified_feature_flag_enabled=true -Des.elastic_inference_service_feature_flag_enabled=true

Create an endpoint

PUT http://localhost:9200/_inference/completion/test
{
    "service": "elastic",
    "service_settings": {
        "api_key": "key",
        "model_id": "gpt-4o"
    }
}

Send request

POST http://localhost:9200/_inference/completion/test/_unified
{
    "model": "gpt-4o",
    "messages": [
        {
            "role": "user",
            "content": "What is the weather like in Boston today?"
        }
    ],
    "stop": ["none"],
    "tools": [
        {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
            "type": "object",
            "properties": {
                "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
                },
                "unit": {
                "type": "string",
                "enum": ["celsius", "fahrenheit"]
                }
            },
            "required": ["location"]
            }
        }
        }
    ],
    "tool_choice": "auto"
}

[elasticsearchmachine]

Hi @jonathan-buttner, I've created a changelog YAML for you.

[jonathan-buttner]

Closing in favor of: #118871