Python: Introduce NvidiaChatCompletion AI Connector

python/samples/concepts/setup/ALL_SETTINGS.md

@@ -30,7 +30,8 @@
 |  | [VertexAITextEmbedding](../../../semantic_kernel/connectors/ai/google/google_ai/services/google_ai_text_embedding.py) | project_id, <br> region, <br> embedding_model_id | VERTEX_AI_PROJECT_ID, <br> VERTEX_AI_REGION, <br> VERTEX_AI_EMBEDDING_MODEL_ID | Yes, <br> No, <br> Yes |  |
 | HuggingFace | [HuggingFaceTextCompletion](../../../semantic_kernel/connectors/ai/hugging_face/services/hf_text_completion.py) | ai_model_id | N/A | Yes | |
 |  | [HuggingFaceTextEmbedding](../../../semantic_kernel/connectors/ai/hugging_face/services/hf_text_embedding.py) | ai_model_id | N/A | Yes | |
-| NVIDIA NIM | [NvidiaTextEmbedding](../../../semantic_kernel/connectors/ai/nvidia/services/nvidia_text_embedding.py) | ai_model_id, <br> api_key, <br> base_url | NVIDIA_API_KEY, <br> NVIDIA_TEXT_EMBEDDING_MODEL_ID, <br> NVIDIA_BASE_URL | Yes | [NvidiaAISettings](../../../semantic_kernel/connectors/ai/nvidia/settings/nvidia_settings.py) |
+| NVIDIA NIM | [NvidiaChatCompletion](../../../semantic_kernel/connectors/ai/nvidia/services/nvidia_chat_completion.py) | ai_model_id, <br> api_key, <br> base_url | NVIDIA_CHAT_MODEL_ID, <br> NVIDIA_API_KEY, <br> NVIDIA_BASE_URL | Yes (default: meta/llama-3.1-8b-instruct), <br> Yes, <br> No | [NvidiaAISettings](../../../semantic_kernel/connectors/ai/nvidia/settings/nvidia_settings.py) |
+|  | [NvidiaTextEmbedding](../../../semantic_kernel/connectors/ai/nvidia/services/nvidia_text_embedding.py) | ai_model_id, <br> api_key, <br> base_url | NVIDIA_API_KEY, <br> NVIDIA_TEXT_EMBEDDING_MODEL_ID, <br> NVIDIA_BASE_URL | Yes | [NvidiaAISettings](../../../semantic_kernel/connectors/ai/nvidia/settings/nvidia_settings.py) |
 | Mistral AI | [MistralAIChatCompletion](../../../semantic_kernel/connectors/ai/mistral_ai/services/mistral_ai_chat_completion.py) | ai_model_id, <br> api_key | MISTRALAI_CHAT_MODEL_ID, <br> MISTRALAI_API_KEY | Yes, <br> Yes | [MistralAISettings](../../../semantic_kernel/connectors/ai/mistral_ai/settings/mistral_ai_settings.py) |
 |  | [MistralAITextEmbedding](../../../semantic_kernel/connectors/ai/mistral_ai/services/mistral_ai_text_embedding.py) | ai_model_id, <br> api_key | MISTRALAI_EMBEDDING_MODEL_ID, <br> MISTRALAI_API_KEY | Yes, <br> Yes |  |
 | Ollama | [OllamaChatCompletion](../../../semantic_kernel/connectors/ai/ollama/services/ollama_chat_completion.py) | ai_model_id, <br> host | OLLAMA_CHAT_MODEL_ID, <br> OLLAMA_HOST | Yes, <br> No | [OllamaSettings](../../../semantic_kernel/connectors/ai/ollama/ollama_settings.py) |

python/samples/concepts/setup/chat_completion_services.py

@@ -28,6 +28,7 @@ class Services(str, Enum):
     ONNX = "onnx"
     VERTEX_AI = "vertex_ai"
     DEEPSEEK = "deepseek"
+    NVIDIA = "nvidia"
 
 
 service_id = "default"
@@ -64,6 +65,7 @@ def get_chat_completion_service_and_request_settings(
         Services.ONNX: lambda: get_onnx_chat_completion_service_and_request_settings(),
         Services.VERTEX_AI: lambda: get_vertex_ai_chat_completion_service_and_request_settings(),
         Services.DEEPSEEK: lambda: get_deepseek_chat_completion_service_and_request_settings(),
+        Services.NVIDIA: lambda: get_nvidia_chat_completion_service_and_request_settings(),
     }
 
     # Call the appropriate lambda or function based on the service name
@@ -414,3 +416,27 @@ def get_deepseek_chat_completion_service_and_request_settings() -> tuple[
     request_settings = OpenAIChatPromptExecutionSettings(service_id=service_id)
 
     return chat_service, request_settings
+
+
+def get_nvidia_chat_completion_service_and_request_settings() -> tuple[
+    "ChatCompletionClientBase", "PromptExecutionSettings"
+]:
+    """Return NVIDIA chat completion service and request settings.
+
+    The service credentials can be read by 3 ways:
+    1. Via the constructor
+    2. Via the environment variables
+    3. Via an environment file
+
+    The request settings control the behavior of the service. The default settings are sufficient to get started.
+    However, you can adjust the settings to suit your needs.
+    Note: Some of the settings are NOT meant to be set by the user.
+    Please refer to the Semantic Kernel Python documentation for more information:
+    https://learn.microsoft.com/en-us/python/api/semantic-kernel/semantic_kernel?view=semantic-kernel-python
+    """
+    from semantic_kernel.connectors.ai.nvidia import NvidiaChatCompletion, NvidiaChatPromptExecutionSettings
+
+    chat_service = NvidiaChatCompletion(service_id=service_id)
+    request_settings = NvidiaChatPromptExecutionSettings(service_id=service_id)
+
+    return chat_service, request_settings

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

@@ -1,6 +1,6 @@
 # semantic_kernel.connectors.ai.nvidia
 
-This connector enables integration with NVIDIA NIM API for text embeddings. It allows you to use NVIDIA's embedding models within the Semantic Kernel framework.
+This connector enables integration with NVIDIA NIM API for text embeddings and chat completion. It allows you to use NVIDIA's models within the Semantic Kernel framework.
 
 ## Quick start
 
@@ -13,6 +13,8 @@ kernel = sk.Kernel()
 ### Add NVIDIA text embedding service
 You can provide your API key directly or through environment variables
 ```python
+from semantic_kernel.connectors.ai.nvidia import NvidiaTextEmbedding
+
 embedding_service = NvidiaTextEmbedding(
 ai_model_id="nvidia/nv-embedqa-e5-v5", # Default model if not specified
 api_key="your-nvidia-api-key", # Can also use NVIDIA_API_KEY env variable
@@ -30,3 +32,35 @@ kernel.add_service(embedding_service)
 texts = ["Hello, world!", "Semantic Kernel is awesome"]
 embeddings = await kernel.get_service("nvidia-embeddings").generate_embeddings(texts)
 ```
+
+### Add NVIDIA chat completion service
+```python
+from semantic_kernel.connectors.ai.nvidia import NvidiaChatCompletion
+
+chat_service = NvidiaChatCompletion(
+    ai_model_id="meta/llama-3.1-8b-instruct", # Default model if not specified
+    api_key="your-nvidia-api-key", # Can also use NVIDIA_API_KEY env variable
+    service_id="nvidia-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.nvidia import NvidiaChatCompletion
+
+agent = ChatCompletionAgent(
+    service=NvidiaChatCompletion(),
+    name="SK-Assistant",
+    instructions="You are a helpful assistant.",
+)
+response = await agent.get_response(messages="Write a haiku about Semantic Kernel.")
+print(response.content)
+```
+

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

@@ -1,13 +1,17 @@
 # Copyright (c) Microsoft. All rights reserved.
 
 from semantic_kernel.connectors.ai.nvidia.prompt_execution_settings.nvidia_prompt_execution_settings import (
+    NvidiaChatPromptExecutionSettings,
     NvidiaEmbeddingPromptExecutionSettings,
     NvidiaPromptExecutionSettings,
 )
+from semantic_kernel.connectors.ai.nvidia.services.nvidia_chat_completion import NvidiaChatCompletion
 from semantic_kernel.connectors.ai.nvidia.services.nvidia_text_embedding import NvidiaTextEmbedding
 from semantic_kernel.connectors.ai.nvidia.settings.nvidia_settings import NvidiaSettings
 
 __all__ = [
+    "NvidiaChatCompletion",
+    "NvidiaChatPromptExecutionSettings",
     "NvidiaEmbeddingPromptExecutionSettings",
     "NvidiaPromptExecutionSettings",
     "NvidiaSettings",

python/semantic_kernel/connectors/ai/nvidia/prompt_execution_settings/nvidia_prompt_execution_settings.py

@@ -2,7 +2,7 @@
 
 from typing import Annotated, Any, Literal
 
-from pydantic import Field
+from pydantic import BaseModel, Field
 
 from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
 
@@ -13,18 +13,6 @@ class NvidiaPromptExecutionSettings(PromptExecutionSettings):
     format: Literal["json"] | None = None
     options: dict[str, Any] | None = None
 
-    def prepare_settings_dict(self, **kwargs) -> dict[str, Any]:
-        """Prepare the settings as a dictionary for sending to the AI service.
-
-        By default, this method excludes the service_id and extension_data fields.
-        As well as any fields that are None.
-        """
-        return self.model_dump(
-            exclude={"service_id", "extension_data", "structured_json_response", "input_type", "truncate"},
-            exclude_none=True,
-            by_alias=True,
-        )
-
 
 class NvidiaEmbeddingPromptExecutionSettings(NvidiaPromptExecutionSettings):
     """Settings for NVIDIA embedding prompt execution."""
@@ -39,3 +27,47 @@ class NvidiaEmbeddingPromptExecutionSettings(NvidiaPromptExecutionSettings):
     extra_body: dict | None = None
     timeout: float | None = None
     dimensions: Annotated[int | None, Field(gt=0)] = None
+
+    def prepare_settings_dict(self, **kwargs) -> dict[str, Any]:
+        """Override only for embeddings to exclude input_type and truncate."""
+        return self.model_dump(
+            exclude={"service_id", "extension_data", "structured_json_response", "input_type", "truncate"},
+            exclude_none=True,
+            by_alias=True,
+        )
+
+
+class NvidiaChatPromptExecutionSettings(NvidiaPromptExecutionSettings):
+    """Settings for NVIDIA chat prompt execution."""
+
+    messages: list[dict[str, str]] | None = None
+    ai_model_id: Annotated[str | None, Field(serialization_alias="model")] = None
+    temperature: float | None = 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
+    logit_bias: dict[str, 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
+    # NVIDIA-specific structured output support
+    nvext: dict[str, Any] | None = None
+
+    def prepare_settings_dict(self, **kwargs) -> dict[str, Any]:
+        """Override only for embeddings to exclude input_type and truncate."""
+        return self.model_dump(
+            exclude={"service_id", "extension_data", "structured_json_response", "response_format"},
+            exclude_none=True,
+            by_alias=True,
+        )