fix: update Azure Provider with openai models

[Valkea]

The current implementation of the Azure provider works with some models but not with some others.

Some will use :

https://YOUR_DEPLOYMENT_NAME.YOUR_REGION_NAME.models.ai.azure.com/v1/chat/completions?api-version=YOUR_API_VERSION
headers = {"Content-Type": "application/json", "Authorization": self.api_key}

And some other will call:

https://YOUR_RESSOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME
headers = {"Content-Type": "application/json", "api-key": self.api_key}

So, I updated the provider to make it detect which one is used and prepare the parameters correctly.

        if ".openai.azure.com" in self.base_url:
            url = f"{self.base_url}/openai/deployments/{model}/chat/completions"
            headers = {"Content-Type": "application/json", "api-key": self.api_key}
        else:
            url = f"{self.base_url}/chat/completions"
            headers = {"Content-Type": "application/json", "Authorization": self.api_key}

[siddheshp]

In Foundry, I see the endpoint URL as https://{resource-name}.cognitiveservices.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2025-01-01-preview.

@Valkea can you add this too? seems this is the change for Foundry projects