[FEATURE] Support for Azure OpenAI Fine-Tuned Models

[alexh2b]

Currently, the endpoint is hard-coded:
https://${azureOpenAIApiInstanceName}.openai.azure.com

This approach won't work with fine-tuned models.

Endpoints typically look like:
https://xxxxxxxxxx.services.ai.azure.com/

However, this could potentially change in the future.

It would be better to adopt a more flexible approach, allowing users to input the full URL.

[HenryHengZJ]

Can you try using Custom OpenAI node and use the Base Path for your fine tuned endpoint?

[alexh2b]

Getting:

404 Resource not found

Troubleshooting URL:
https://js.langchain.com/docs/troubleshooting/errors/MODEL_NOT_FOUND/

///

Tried as model name:

1. the model name as displayed in the Azure dashboard
2. Deployment name
3. gpt-4o-mini