fix(community): togetherai response different format handling

[axe-me]

Apparently togetherAI now have more than one response format, other than the old one it also have a format like this:

{
    "id": "8fef9f62bf2dbef4-YYC",
    "object": "text.completion",
    "created": 1736375327,
    "model": "deepseek-ai/DeepSeek-V3",
    "choices": [
        {
            "index": 0,
            "text": " Paris",
            "logprobs": null,
            "finish_reason": "length",
            "matched_stop": null
        }
    ],
    "usage": {
        "prompt_tokens": 11,
        "total_tokens": 12,
        "completion_tokens": 1,
        "prompt_tokens_details": null
    },
    "prompt": []
}

This PR will update the code to handle format like that. Thanks for your time to review this!

Fixes # (issue) #6993
#6993

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
langchainjs-docs	✅ Ready (Inspect)	Visit Preview		Jan 8, 2025 11:07pm

1 Skipped Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchainjs-api-refs	⬜️ Ignored (Inspect)			Jan 8, 2025 11:07pm

[jacoblee93]

Thank you!

Does this apply to chat models too?