microsoft/semantic-kernel · error · NotImplementedError

Model type {self.ai_model_type} is not supported

Error message

Model type {self.ai_model_type} is not supported

What it means

Raised as NotImplementedError in `NvidiaHandler._send_request` when `self.ai_model_type` matches neither NvidiaModelTypes.EMBEDDING nor NvidiaModelTypes.CHAT. This is a programming/contract error, not a runtime network issue: the handler is configured with an unsupported model type, so it cannot dispatch the request.

Source

Thrown at python/semantic_kernel/connectors/ai/nvidia/services/nvidia_handler.py:47

    """Internal class for calls to Nvidia API's."""

    MODEL_PROVIDER_NAME: ClassVar[str] = "nvidia"
    client: AsyncOpenAI
    ai_model_type: NvidiaModelTypes = NvidiaModelTypes.CHAT
    completion_tokens: int = 0
    total_tokens: int = 0
    prompt_tokens: int = 0

    async def _send_request(self, settings: PromptExecutionSettings) -> RESPONSE_TYPE:
        """Send a request to the Nvidia API."""
        if self.ai_model_type == NvidiaModelTypes.EMBEDDING:
            assert isinstance(settings, NvidiaEmbeddingPromptExecutionSettings)  # nosec
            return await self._send_embedding_request(settings)
        if self.ai_model_type == NvidiaModelTypes.CHAT:
            assert isinstance(settings, NvidiaChatPromptExecutionSettings)  # nosec
            return await self._send_chat_completion_request(settings)

        raise NotImplementedError(f"Model type {self.ai_model_type} is not supported")

    async def _send_embedding_request(self, settings: NvidiaEmbeddingPromptExecutionSettings) -> list[Any]:
        """Send a request to the OpenAI embeddings endpoint."""
        try:
            # unsupported parameters are internally excluded from main dict and added to extra_body
            response = await self.client.embeddings.create(**settings.prepare_settings_dict())

            self.store_usage(response)
            return [x.embedding for x in response.data]
        except Exception as ex:
            raise ServiceResponseException(
                f"{type(self)} service failed to generate embeddings",
                ex,
            ) from ex

    async def _send_chat_completion_request(
        self, settings: NvidiaChatPromptExecutionSettings
    ) -> ChatCompletion | AsyncStream[Any]:

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Use one of the supported NvidiaModelTypes (CHAT or EMBEDDING) for ai_model_type.
2. If you need a new type, extend _send_request with a dispatch branch instead of relying on the default.
3. Prefer the high-level NvidiaChatCompletion / NvidiaTextEmbedding classes (they set ai_model_type correctly) over constructing NvidiaHandler directly.

Example fix

# before
handler = MyHandler(...)
handler.ai_model_type = 'vision'   # not supported

# after
from semantic_kernel.connectors.ai.nvidia.services.nvidia_model_types import NvidiaModelTypes
handler.ai_model_type = NvidiaModelTypes.CHAT

from semantic_kernel.connectors.ai.nvidia.services.nvidia_model_types import NvidiaModelTypes
assert handler.ai_model_type in (NvidiaModelTypes.CHAT, NvidiaModelTypes.EMBEDDING), \
    f'unsupported ai_model_type: {handler.ai_model_type}'

from semantic_kernel.connectors.ai.nvidia.services.nvidia_model_types import NvidiaModelTypes

def is_supported_nvidia_type(t) -> bool:
    return t in (NvidiaModelTypes.CHAT, NvidiaModelTypes.EMBEDDING)

try:
    resp = await handler._send_request(settings)
except NotImplementedError as e:
    raise ValueError(f'Configure ai_model_type to CHAT or EMBEDDING: {e}') from e

When it happens

Trigger: Subclassing NvidiaHandler (or otherwise constructing it) and setting ai_model_type to a value outside {CHAT, EMBEDDING}, then calling invoke/generate_embeddings which routes through _send_request. Also if a future NvidiaModelTypes member is added but _send_request isn't updated.

Common situations: Custom NvidiaHandler subclass that invents a model type string; passing a raw string instead of the NvidiaModelTypes enum; code that monkeypatches ai_model_type.

Related errors

• Unsupported service name: {service_name}
• Unsupported service: {service}. Supported services are: {',
• Failed to create NVIDIA settings.
• The NVIDIA API key is required.
• Failed to create NVIDIA settings.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/2c1c57c7d4615b1e. Report an issue: GitHub.