Python: Add MiniMax AI connector for chat completion

python/semantic_kernel/connectors/ai/README.md

@@ -42,6 +42,7 @@ All base clients inherit from the [`AIServiceClientBase`](../../services/ai_serv
 |           | [`GoogleAITextEmbedding`](./google/google_ai/services/google_ai_text_embedding.py) |
 | HuggingFace | [`HuggingFaceTextCompletion`](./hugging_face/services/hf_text_completion.py) |
 |             | [`HuggingFaceTextEmbedding`](./hugging_face/services/hf_text_embedding.py) |
+| [MiniMax](./minimax/README.md) | [`MiniMaxChatCompletion`](./minimax/services/minimax_chat_completion.py) |
 | Mistral AI | [`MistralAIChatCompletion`](./mistral_ai/services/mistral_ai_chat_completion.py) |
 |            | [`MistralAITextEmbedding`](./mistral_ai/services/mistral_ai_text_embedding.py) |
 | [Nvidia](./nvidia/README.md) | [`NvidiaTextEmbedding`](./nvidia/services/nvidia_text_embedding.py) |

python/semantic_kernel/connectors/ai/minimax/README.md

@@ -0,0 +1,62 @@
+# semantic_kernel.connectors.ai.minimax
+
+This connector enables integration with MiniMax API for chat completion. It allows you to use MiniMax's models within the Semantic Kernel framework.
+
+MiniMax provides an OpenAI-compatible API, making integration straightforward.
+
+## Quick start
+
+### Initialize the kernel
+```python
+import semantic_kernel as sk
+kernel = sk.Kernel()
+```
+
+### Add MiniMax chat completion service
+You can provide your API key directly or through environment variables.
+```python
+from semantic_kernel.connectors.ai.minimax import MiniMaxChatCompletion
+
+chat_service = MiniMaxChatCompletion(
+    ai_model_id="MiniMax-M2.5",  # Default model if not specified
+    api_key="your-minimax-api-key",  # Can also use MINIMAX_API_KEY env variable
+    service_id="minimax-chat"  # Optional service identifier
+)
+kernel.add_service(chat_service)
+```
+
+### Basic chat completion
+```python
+response = await kernel.invoke_prompt("Hello, how are you?")
+```
+
+### Using with Chat Completion Agent
+```python
+from semantic_kernel.agents import ChatCompletionAgent
+from semantic_kernel.connectors.ai.minimax import MiniMaxChatCompletion
+
+agent = ChatCompletionAgent(
+    service=MiniMaxChatCompletion(),
+    name="SK-Assistant",
+    instructions="You are a helpful assistant.",
+)
+response = await agent.get_response(messages="Write a haiku about Semantic Kernel.")
+print(response.content)
+```
+
+## Available Models
+
+- `MiniMax-M2.5` - Standard model with 204K context window
+- `MiniMax-M2.5-highspeed` - High-speed variant with 204K context window
+
+## Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `MINIMAX_API_KEY` | Your MiniMax API key |
+| `MINIMAX_BASE_URL` | API endpoint (defaults to `https://api.minimax.io/v1`) |
+| `MINIMAX_CHAT_MODEL_ID` | Default chat model ID |
+
+## Notes
+
+- MiniMax API requires temperature to be in the range (0.0, 1.0]. A value of exactly 0.0 is not accepted.

python/semantic_kernel/connectors/ai/minimax/__init__.py

@@ -0,0 +1,15 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from semantic_kernel.connectors.ai.minimax.prompt_execution_settings.minimax_prompt_execution_settings import (
+    MiniMaxChatPromptExecutionSettings,
+    MiniMaxPromptExecutionSettings,
+)
+from semantic_kernel.connectors.ai.minimax.services.minimax_chat_completion import MiniMaxChatCompletion
+from semantic_kernel.connectors.ai.minimax.settings.minimax_settings import MiniMaxSettings
+
+__all__ = [
+    "MiniMaxChatCompletion",
+    "MiniMaxChatPromptExecutionSettings",
+    "MiniMaxPromptExecutionSettings",
+    "MiniMaxSettings",
+]

python/semantic_kernel/connectors/ai/minimax/prompt_execution_settings/__init__.py

@@ -0,0 +1 @@
+# Copyright (c) Microsoft. All rights reserved.

python/semantic_kernel/connectors/ai/minimax/prompt_execution_settings/minimax_prompt_execution_settings.py

@@ -0,0 +1,46 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from typing import Annotated, Any, Literal
+
+from pydantic import BaseModel, Field
+
+from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
+
+
+class MiniMaxPromptExecutionSettings(PromptExecutionSettings):
+    """Settings for MiniMax prompt execution."""
+
+    pass
+
+
+class MiniMaxChatPromptExecutionSettings(MiniMaxPromptExecutionSettings):
+    """Settings for MiniMax chat prompt execution."""
+
+    messages: list[dict[str, str]] | None = None
+    ai_model_id: Annotated[str | None, Field(serialization_alias="model")] = None
+    temperature: Annotated[float | None, Field(gt=0.0, le=1.0)] = None
+    top_p: float | None = None
+    n: int | None = None
+    stream: bool = False
+    stop: str | list[str] | None = None
+    max_tokens: int | None = None
+    presence_penalty: float | None = None
+    frequency_penalty: float | None = None
+    user: str | None = None
+    tools: list[dict[str, Any]] | None = None
+    tool_choice: str | dict[str, Any] | None = None
+    response_format: (
+        dict[Literal["type"], Literal["text", "json_object"]] | dict[str, Any] | type[BaseModel] | type | None
+    ) = None
+    seed: int | None = None
+    extra_headers: dict | None = None
+    extra_body: dict | None = None
+    timeout: float | None = None
+
+    def prepare_settings_dict(self, **kwargs) -> dict[str, Any]:
+        """Prepare the settings as a dictionary for the API request."""
+        return self.model_dump(
+            exclude={"service_id", "extension_data", "structured_json_response", "response_format"},
+            exclude_none=True,
+            by_alias=True,
+        )

python/semantic_kernel/connectors/ai/minimax/services/__init__.py

@@ -0,0 +1 @@
+# Copyright (c) Microsoft. All rights reserved.