Python: Fix Azure AI Inference connector model_extras duplication (#13066)

### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Addresses #13005 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Remove the `extra_parameters` key from
`AzureAIInferenceChatPromptExecutionSettings` before calling the chat
completion API to avoid unknown parameter error.
2. Allow setting the API version on the `AzureAIInferenceXXX`
connectors.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

Author: TaoChenOSU

python/samples/concepts/reasoning/simple_reasoning_azure_ai_inference.py

@@ -0,0 +1,87 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+
+from semantic_kernel.connectors.ai.azure_ai_inference import (
+    AzureAIInferenceChatCompletion,
+    AzureAIInferenceChatPromptExecutionSettings,
+)
+from semantic_kernel.contents import ChatHistory
+
+"""
+This sample demonstrates an example of how to use reasoning models using the Azure AI Inference service.
+"""
+
+chat_service = AzureAIInferenceChatCompletion(
+    ai_model_id="gpt-5-mini",
+    # You must specify the endpoint and api_key or configure them via environment variables:
+    # AZURE_AI_INFERENCE_ENDPOINT
+    # AZURE_AI_INFERENCE_API_KEY
+    endpoint="...",
+    api_key="...",
+)
+request_settings = AzureAIInferenceChatPromptExecutionSettings(
+    extra_parameters={
+        "reasoning_effort": "medium",
+        "verbosity": "medium",
+    },
+)
+
+# Create a ChatHistory object
+chat_history = ChatHistory()
+
+# This is the system message that gives the chatbot its personality.
+developer_message = """
+As an assistant supporting the user,
+you recognize all user input
+as questions or consultations and answer them.
+"""
+# The developer message was newly introduced for reasoning models such as OpenAI’s o1 and o1-mini.
+# `system message` cannot be used with reasoning models.
+chat_history.add_developer_message(developer_message)
+
+
+async def chat() -> bool:
+    try:
+        user_input = input("User:> ")
+    except KeyboardInterrupt:
+        print("\n\nExiting chat...")
+        return False
+    except EOFError:
+        print("\n\nExiting chat...")
+        return False
+
+    if user_input == "exit":
+        print("\n\nExiting chat...")
+        return False
+
+    chat_history.add_user_message(user_input)
+
+    # Get the chat message content from the chat completion service.
+    response = await chat_service.get_chat_message_content(
+        chat_history=chat_history,
+        settings=request_settings,
+    )
+    if response:
+        print(f"Reasoning model:> {response}")
+
+        # Add the chat message to the chat history to keep track of the conversation.
+        chat_history.add_message(response)
+
+    return True
+
+
+async def main() -> None:
+    # Start the chat loop. The chat loop will continue until the user types "exit".
+    chatting = True
+    while chatting:
+        chatting = await chat()
+
+    # Sample output:
+    # User:> Why is the sky blue in one sentence?
+    # Mosscap:> The sky appears blue because air molecules in the atmosphere scatter shorter-wavelength (blue)
+    #           light more efficiently than longer-wavelength (red) light.
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

python/semantic_kernel/connectors/ai/azure_ai_inference/azure_ai_inference_settings.py

@@ -4,6 +4,7 @@
 
 from pydantic import SecretStr
 
+from semantic_kernel.connectors.ai.open_ai.const import DEFAULT_AZURE_API_VERSION
 from semantic_kernel.kernel_pydantic import HttpsUrl, KernelBaseSettings
 from semantic_kernel.utils.feature_stage_decorator import experimental
 
@@ -29,9 +30,12 @@ class AzureAIInferenceSettings(KernelBaseSettings):
                 This value can be found in the Keys & Endpoint section when examining
                 your resource from the Azure portal. You can use either KEY1 or KEY2.
                 (Env var AZURE_AI_INFERENCE_API_KEY)
+    - api_version: str | None - The API version to use. The default value is "2024-10-21".
+                (Env var AZURE_AI_INFERENCE_API_VERSION)
     """
 
     env_prefix: ClassVar[str] = "AZURE_AI_INFERENCE_"
 
     endpoint: HttpsUrl
     api_key: SecretStr | None = None
+    api_version: str = DEFAULT_AZURE_API_VERSION

python/semantic_kernel/connectors/ai/azure_ai_inference/services/azure_ai_inference_base.py

@@ -47,6 +47,7 @@ def __init__(
         client_type: AzureAIInferenceClientType,
         api_key: str | None = None,
         endpoint: str | None = None,
+        api_version: str | None = None,
         env_file_path: str | None = None,
         env_file_encoding: str | None = None,
         client: ChatCompletionsClient | EmbeddingsClient | None = None,
@@ -60,11 +61,13 @@ def __init__(
         The following environment variables are used:
         - AZURE_AI_INFERENCE_API_KEY
         - AZURE_AI_INFERENCE_ENDPOINT
+        - AZURE_AI_INFERENCE_API_VERSION
 
         Args:
             client_type (AzureAIInferenceClientType): The client type to use.
             api_key (str | None): The API key for the Azure AI Inference service deployment. (Optional)
             endpoint (str | None): The endpoint of the Azure AI Inference service deployment. (Optional)
+            api_version (str | None): The API version to use. (Optional)
             env_file_path (str | None): The path to the environment file. (Optional)
             env_file_encoding (str | None): The encoding of the environment file. (Optional)
             client (ChatCompletionsClient | None): The Azure AI Inference client to use. (Optional)
@@ -81,6 +84,7 @@ def __init__(
                 azure_ai_inference_settings = AzureAIInferenceSettings(
                     api_key=api_key,
                     endpoint=endpoint,
+                    api_version=api_version,
                     env_file_path=env_file_path,
                     env_file_encoding=env_file_encoding,
                 )
@@ -93,6 +97,7 @@ def __init__(
                     endpoint=endpoint,
                     credential=AzureKeyCredential(azure_ai_inference_settings.api_key.get_secret_value()),
                     user_agent=SEMANTIC_KERNEL_USER_AGENT,
+                    api_version=azure_ai_inference_settings.api_version,
                 )
             else:
                 if credential is None:
@@ -102,6 +107,7 @@ def __init__(
                     endpoint=endpoint,
                     credential=credential,
                     user_agent=SEMANTIC_KERNEL_USER_AGENT,
+                    api_version=azure_ai_inference_settings.api_version,
                 )
 
         args: dict[str, Any] = {

python/semantic_kernel/connectors/ai/azure_ai_inference/services/azure_ai_inference_chat_completion.py

@@ -66,6 +66,7 @@ def __init__(
         ai_model_id: str,
         api_key: str | None = None,
         endpoint: str | None = None,
+        api_version: str | None = None,
         service_id: str | None = None,
         env_file_path: str | None = None,
         env_file_encoding: str | None = None,
@@ -78,11 +79,13 @@ def __init__(
         The following environment variables are used:
         - AZURE_AI_INFERENCE_API_KEY
         - AZURE_AI_INFERENCE_ENDPOINT
+        - AZURE_AI_INFERENCE_API_VERSION
 
         Args:
             ai_model_id: (str): A string that is used to identify the model such as the model name. (Required)
             api_key (str | None): The API key for the Azure AI Inference service deployment. (Optional)
             endpoint (str | None): The endpoint of the Azure AI Inference service deployment. (Optional)
+            api_version (str | None): The API version to use. (Optional)
             service_id (str | None): Service ID for the chat completion service. (Optional)
             env_file_path (str | None): The path to the environment file. (Optional)
             env_file_encoding (str | None): The encoding of the environment file. (Optional)
@@ -99,6 +102,7 @@ def __init__(
             "client_type": AzureAIInferenceClientType.ChatCompletions,
             "client": client,
             "endpoint": endpoint,
+            "api_version": api_version,
             "env_file_path": env_file_path,
             "env_file_encoding": env_file_encoding,
         }
@@ -139,6 +143,9 @@ async def _inner_get_chat_message_contents(
         assert isinstance(self.client, ChatCompletionsClient)  # nosec
         with AzureAIInferenceTracing():
             settings_dict = settings.prepare_settings_dict()
+            # Remove the extra parameters since it will be passed in via the `model_extras` param
+            settings_dict.pop("extra_parameters", None)
+
             self._handle_structured_output(settings, settings_dict)
             response: ChatCompletions = await self.client.complete(
                 messages=self._prepare_chat_history_for_request(chat_history),
@@ -165,6 +172,9 @@ async def _inner_get_streaming_chat_message_contents(
         assert isinstance(self.client, ChatCompletionsClient)  # nosec
         with AzureAIInferenceTracing():
             settings_dict = settings.prepare_settings_dict()
+            # Remove the extra parameters since it will be passed in via the `model_extras` param
+            settings_dict.pop("extra_parameters", None)
+
             self._handle_structured_output(settings, settings_dict)
             response: AsyncStreamingChatCompletions = await self.client.complete(
                 stream=True,

python/semantic_kernel/connectors/ai/azure_ai_inference/services/azure_ai_inference_text_embedding.py

@@ -35,6 +35,7 @@ def __init__(
         ai_model_id: str,
         api_key: str | None = None,
         endpoint: str | None = None,
+        api_version: str | None = None,
         service_id: str | None = None,
         env_file_path: str | None = None,
         env_file_encoding: str | None = None,
@@ -46,11 +47,13 @@ def __init__(
         The following environment variables are used:
         - AZURE_AI_INFERENCE_API_KEY
         - AZURE_AI_INFERENCE_ENDPOINT
+        - AZURE_AI_INFERENCE_API_VERSION
 
         Args:
             ai_model_id: (str): A string that is used to identify the model such as the model name. (Required)
             api_key (str | None): The API key for the Azure AI Inference service deployment. (Optional)
             endpoint (str | None): The endpoint of the Azure AI Inference service deployment. (Optional)
+            api_version (str | None): The API version to use. (Optional)
             service_id (str | None): Service ID for the chat completion service. (Optional)
             env_file_path (str | None): The path to the environment file. (Optional)
             env_file_encoding (str | None): The encoding of the environment file. (Optional)
@@ -65,6 +68,7 @@ def __init__(
             client_type=AzureAIInferenceClientType.Embeddings,
             api_key=api_key,
             endpoint=endpoint,
+            api_version=api_version,
             env_file_path=env_file_path,
             env_file_encoding=env_file_encoding,
             client=client,

python/semantic_kernel/connectors/ai/open_ai/settings/azure_open_ai_settings.py

@@ -84,7 +84,7 @@ class AzureOpenAISettings(KernelBaseSettings):
                 your resource from the Azure portal, the endpoint should end in openai.azure.com.
                 If both base_url and endpoint are supplied, base_url will be used.
                 (Env var AZURE_OPENAI_ENDPOINT)
-    - api_version: str | None - The API version to use. The default value is "2024-02-01".
+    - api_version: str | None - The API version to use. The default value is "2024-10-21".
                 (Env var AZURE_OPENAI_API_VERSION)
     - token_endpoint: str - The token endpoint to use to retrieve the authentication token.
                 The default value is "https://cognitiveservices.azure.com/.default".

python/tests/unit/connectors/ai/azure_ai_inference/services/test_azure_ai_inference_chat_completion.py

@@ -66,6 +66,15 @@ def test_azure_ai_inference_chat_completion_init_with_service_id(
     assert isinstance(azure_ai_inference.client, ChatCompletionsClient)
 
 
+def test_azure_ai_inference_chat_completion_init_with_api_version(azure_ai_inference_unit_test_env, model_id) -> None:
+    """Test initialization of AzureAIInferenceChatCompletion with api_version"""
+    azure_ai_inference = AzureAIInferenceChatCompletion(model_id, api_version="2024-02-15-test")
+
+    assert azure_ai_inference.ai_model_id == model_id
+    assert isinstance(azure_ai_inference.client, ChatCompletionsClient)
+    assert azure_ai_inference.client._config.api_version == "2024-02-15-test"
+
+
 @pytest.mark.parametrize(
     "azure_ai_inference_client",
     [AzureAIInferenceChatCompletion.__name__],
@@ -210,7 +219,6 @@ async def test_azure_ai_inference_chat_completion_with_extra_parameters(
         messages=[UserMessage(content=user_message_content)],
         model=model_id,
         model_extras=settings.extra_parameters,
-        **settings.prepare_settings_dict(),
     )
     assert len(responses) == 1
     assert responses[0].role == "assistant"
@@ -506,7 +514,6 @@ async def test_azure_ai_inference_streaming_chat_completion_with_extra_parameter
         messages=[UserMessage(content=user_message_content)],
         model=model_id,
         model_extras=settings.extra_parameters,
-        **settings.prepare_settings_dict(),
     )
 
 

python/tests/unit/connectors/ai/azure_ai_inference/services/test_azure_ai_inference_text_embedding.py

@@ -52,6 +52,15 @@ def test_azure_ai_inference_text_embedding_init_with_service_id(
     assert isinstance(azure_ai_inference.client, EmbeddingsClient)
 
 
+def test_azure_ai_inference_text_embedding_init_with_api_version(azure_ai_inference_unit_test_env, model_id) -> None:
+    """Test initialization of AzureAIInferenceTextEmbedding with api_version"""
+    azure_ai_inference = AzureAIInferenceTextEmbedding(model_id, api_version="2024-02-15-test")
+
+    assert azure_ai_inference.ai_model_id == model_id
+    assert isinstance(azure_ai_inference.client, EmbeddingsClient)
+    assert azure_ai_inference.client._config.api_version == "2024-02-15-test"
+
+
 @pytest.mark.parametrize(
     "azure_ai_inference_client",
     [AzureAIInferenceTextEmbedding.__name__],