[BUG] Big-AGI 2.0 Azure deepseek support

[tsoernes]

Environment

GitHub v2-dev branch

Description

I cannot get a deepseek deployment on azure to work.

This python code WORKS:

import os
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from dotenv import load_dotenv

load_dotenv()
api_key = os.getenv("AZURE_INFERENCE_CREDENTIAL", '')
if not api_key:
  raise Exception("A key should be provided to invoke the endpoint")

client = ChatCompletionsClient(
    endpoint="https://MYDEPLOYMENTl.services.ai.azure.com/models",
    credential=AzureKeyCredential(api_key),
    model="DeepSeek-R1",
)
# Adding the model name in the header
headers = {
    'x-ms-model-mesh-model-name': 'DeepSeek-R1'
}

print(client.get_model_info(headers=headers))

from azure.ai.inference.models import SystemMessage, UserMessage

response = client.complete(
    messages=[
        SystemMessage(content="You are a helpful assistant."),
        UserMessage(content="How many languages are in the world?"),
    ],
)

When trying the same URL with big-AGI it says
[OpenAI/azure issue]: Resource Not Found - Resource not found - "https://XXXX.services.ai.azure.com/models/openai/deployments?api-version=2023-03-15-preview" cannot be found by the server

The azure config is not compatible with deepseek (non openai deployments)

Device and browser

Brave

Screenshots and more

No response

Willingness to Contribute

• 🙋‍♂️ Yes, I would like to contribute a fix.