Python: New AI Connector abstract methods (microsoft#8526)

### 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.
-->
This PR implements:
https://github.com/microsoft/semantic-kernel/blob/main/docs/decisions/0052-python-ai-connector-new-abstract-methods.md
(PR: microsoft#8430).

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Add abstract methods `_inner_get_chat_message_content` and
`_inner_get_streaming_chat_message_content` to
`ChatCompletionClientBase`.
2. Implement the abstractions in all chat completion connectors.
3. Add abstract methods `_inner_get_text_contents` and
`_inner_get_streaming_text_contents` to `TextCompletionClientBase`.
4. Implement the abstractions in all text completion connectors.
5. Remove text completion APIs from `OllamaChatCompletion` (breaking
changes).
> No breaking changes on other connectors except Ollama, and public APIs
stay the same.


### 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 😄

docs/decisions/0052-python-ai-connector-new-abstract-methods.md

@@ -30,24 +30,24 @@ Auto function invocation can cause a side effect where a single call to get_chat
 
 ### Two new abstract methods
 
+> Revision: In order to not break existing customers who have implemented their own AI connectors, these two methods are not decorated with the `@abstractmethod` decorator, but instead throw an exception if they are not implemented in the built-in AI connectors.
+
 ```python
-@abstractmethod
-async def _send_chat_request(
+async def _inner_get_chat_message_content(
     self,
     chat_history: ChatHistory,
     settings: PromptExecutionSettings
 ) -> list[ChatMessageContent]:
-    pass
+    raise NotImplementedError
 ```
 
 ```python
-@abstractmethod
-async def _send_streaming_chat_request(
+async def _inner_get_streaming_chat_message_content(
     self,
     chat_history: ChatHistory,
     settings: PromptExecutionSettings
 ) -> AsyncGenerator[list[StreamingChatMessageContent], Any]:
-    pass
+    raise NotImplementedError
 ```
 
 ### A new `ClassVar[bool]` variable in `ChatCompletionClientBase` to indicate whether a connector supports function calling

python/.cspell.json

@@ -57,6 +57,7 @@
         "contoso",
         "opentelemetry",
         "SEMANTICKERNEL",
-        "OTEL"
+        "OTEL",
+        "mistralai"
     ]
 }

python/semantic_kernel/connectors/ai/anthropic/services/anthropic_chat_completion.py

@@ -54,6 +54,7 @@ class AnthropicChatCompletion(ChatCompletionClientBase):
     """Antropic ChatCompletion class."""
 
     MODEL_PROVIDER_NAME: ClassVar[str] = "anthropic"
+    SUPPORTS_FUNCTION_CALLING: ClassVar[bool] = False
 
     async_client: AsyncAnthropic
 
@@ -103,31 +104,25 @@ def __init__(
             ai_model_id=anthropic_settings.chat_model_id,
         )
 
+    # region Overriding base class methods
+
+    # Override from AIServiceClientBase
+    @override
+    def get_prompt_execution_settings_class(self) -> type["PromptExecutionSettings"]:
+        return AnthropicChatPromptExecutionSettings
+
     @override
     @trace_chat_completion(MODEL_PROVIDER_NAME)
-    async def get_chat_message_contents(
+    async def _inner_get_chat_message_contents(
         self,
         chat_history: "ChatHistory",
         settings: "PromptExecutionSettings",
-        **kwargs: Any,
     ) -> list["ChatMessageContent"]:
-        """Executes a chat completion request and returns the result.
-
-        Args:
-            chat_history: The chat history to use for the chat completion.
-            settings: The settings to use for the chat completion request.
-            kwargs: The optional arguments.
-
-        Returns:
-            The completion result(s).
-        """
         if not isinstance(settings, AnthropicChatPromptExecutionSettings):
             settings = self.get_prompt_execution_settings_from_settings(settings)
         assert isinstance(settings, AnthropicChatPromptExecutionSettings)  # nosec
 
-        if not settings.ai_model_id:
-            settings.ai_model_id = self.ai_model_id
-
+        settings.ai_model_id = settings.ai_model_id or self.ai_model_id
         settings.messages = self._prepare_chat_history_for_request(chat_history)
         try:
             response = await self.async_client.messages.create(**settings.prepare_settings_dict())
@@ -146,29 +141,17 @@ async def get_chat_message_contents(
             self._create_chat_message_content(response, content_block, metadata) for content_block in response.content
         ]
 
-    async def get_streaming_chat_message_contents(
+    @override
+    async def _inner_get_streaming_chat_message_contents(
         self,
-        chat_history: ChatHistory,
-        settings: PromptExecutionSettings,
-        **kwargs: Any,
-    ) -> AsyncGenerator[list[StreamingChatMessageContent], Any]:
-        """Executes a streaming chat completion request and returns the result.
-
-        Args:
-            chat_history: The chat history to use for the chat completion.
-            settings: The settings to use for the chat completion request.
-            kwargs: The optional arguments.
-
-        Yields:
-            A stream of StreamingChatMessageContent.
-        """
+        chat_history: "ChatHistory",
+        settings: "PromptExecutionSettings",
+    ) -> AsyncGenerator[list["StreamingChatMessageContent"], Any]:
         if not isinstance(settings, AnthropicChatPromptExecutionSettings):
             settings = self.get_prompt_execution_settings_from_settings(settings)
         assert isinstance(settings, AnthropicChatPromptExecutionSettings)  # nosec
 
-        if not settings.ai_model_id:
-            settings.ai_model_id = self.ai_model_id
-
+        settings.ai_model_id = settings.ai_model_id or self.ai_model_id
         settings.messages = self._prepare_chat_history_for_request(chat_history)
         try:
             async with self.async_client.messages.stream(**settings.prepare_settings_dict()) as stream:
@@ -189,13 +172,14 @@ async def get_streaming_chat_message_contents(
                         ]
                     elif isinstance(stream_event, ContentBlockStopEvent):
                         content_block_idx += 1
-
         except Exception as ex:
             raise ServiceResponseException(
                 f"{type(self)} service failed to complete the request",
                 ex,
             ) from ex
 
+    # endregion
+
     def _create_chat_message_content(
         self, response: Message, content: TextBlock, response_metadata: dict[str, Any]
     ) -> "ChatMessageContent":
@@ -249,7 +233,3 @@ def _create_streaming_chat_message_content(
             finish_reason=finish_reason,
             items=items,
         )
-
-    def get_prompt_execution_settings_class(self) -> "type[AnthropicChatPromptExecutionSettings]":
-        """Create a request settings object."""
-        return AnthropicChatPromptExecutionSettings