[ML] Integrate with DeepSeek API

[prwhelan]

Integrating for Chat Completion and Completion task types, both calling the chat completion API for DeepSeek.

---

Verified:

• content string
• content object with "type": "text" + "text": "what is elastic"
• max_completion_tokens does not work, we need to map to max_tokens
• role field works
• tools work
• sending n is benign
• temperature works
• tool_choice works
• strict tools is benign
• top_p works
• stream works
• Added tests verifying unified error response

[elasticsearchmachine]

Hi @prwhelan, I've created a changelog YAML for you.

[elasticsearchmachine]

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

[jonathan-buttner]

Do we want to allow users to set the URL in the create inference endpoint request? If this is only for testing, then I think we can allow the child classes to override a method to return it, or pass it in via the constructor. Then in the tests we can set it via a constructor or a setter or something.

[prwhelan]

I really only left it exposed but optional because anyone can in theory run the model locally behind an OpenAI compatible endpoint and then call it that way.

I can remove it though if that's not something we want to support, I'm neutral towards it