microsoft/semantic-kernel · error · ServiceInitializationError

Failed to create NVIDIA settings.

Error message

Failed to create NVIDIA settings.

What it means

Raised as ServiceInitializationError when constructing the pydantic `NvidiaSettings` for the NVIDIA chat completion service raises a `ValidationError`. The original validation error is passed as a second arg and chained with `from ex`. This is a configuration/structure failure, not a network failure.

Source

Thrown at python/semantic_kernel/connectors/ai/nvidia/services/nvidia_chat_completion.py:96

                the env vars or .env file value.
            base_url (str | None): Custom API endpoint. (Optional)
            client (Optional[AsyncOpenAI]): An existing client to use. (Optional)
            env_file_path (str | None): Use the environment settings file as a fallback
                to environment variables. (Optional)
            env_file_encoding (str | None): The encoding of the environment settings file. (Optional)
            instruction_role (Literal["system", "user", "assistant", "developer"] | None): The role to use for
                'instruction' messages. Defaults to "system". (Optional)
        """
        try:
            nvidia_settings = NvidiaSettings(
                api_key=api_key,
                base_url=base_url,
                chat_model_id=ai_model_id,
                env_file_path=env_file_path,
                env_file_encoding=env_file_encoding,
            )
        except ValidationError as ex:
            raise ServiceInitializationError("Failed to create NVIDIA settings.", ex) from ex

        if not client and not nvidia_settings.api_key:
            raise ServiceInitializationError("The NVIDIA API key is required.")
        if not nvidia_settings.chat_model_id:
            # Default fallback model
            nvidia_settings.chat_model_id = DEFAULT_NVIDIA_CHAT_MODEL
            logger.warning(f"Default chat model set as: {nvidia_settings.chat_model_id}")

        # Create client if not provided
        if not client:
            client = AsyncOpenAI(
                api_key=nvidia_settings.api_key.get_secret_value() if nvidia_settings.api_key else None,
                base_url=nvidia_settings.base_url,
            )

        super().__init__(
            ai_model_id=nvidia_settings.chat_model_id,
            api_key=nvidia_settings.api_key.get_secret_value() if nvidia_settings.api_key else None,

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Inspect the chained `ex` for the exact failing field.
2. Pass valid base_url (full https:// URL) and api_key explicitly, or fix the matching env vars.
3. Verify env_file_path exists and is parseable in the given encoding.
4. Confirm NVIDIA settings field names against the NvidiaSettings model (NVIDIA_API_KEY, NVIDIA_BASE_URL, NVIDIA_CHAT_MODEL_ID).

Example fix

# before
svc = NvidiaChatCompletion()  # -> ServiceInitializationError

# after
svc = NvidiaChatCompletion(
    api_key=os.environ['NVIDIA_API_KEY'],
    base_url='https://integrate.api.nvidia.com/v1',
    ai_model_id='meta/llama3-8b-instruct',
)

from semantic_kernel.connectors.ai.nvidia import NvidiaSettings
from pydantic import ValidationError
try:
    NvidiaSettings(api_key=os.environ.get('NVIDIA_API_KEY'),
                   base_url=os.environ.get('NVIDIA_BASE_URL', 'https://integrate.api.nvidia.com/v1'),
                   chat_model_id='meta/llama3-8b-instruct')
except ValidationError as e:
    raise SystemExit(f'Fix NVIDIA settings first: {e}')

from semantic_kernel.exceptions import ServiceInitializationError

def is_nvidia_settings_error(e: BaseException) -> bool:
    return isinstance(e, ServiceInitializationError) and 'Failed to create NVIDIA settings' in str(e)

from semantic_kernel.exceptions import ServiceInitializationError
try:
    svc = NvidiaChatCompletion()
except ServiceInitializationError as e:
    raise SystemExit(f'NVIDIA chat misconfigured: {e.__cause__ or e}') from e

When it happens

Trigger: Constructing `NvidiaChatCompletion(...)` where merged config (constructor args + NVIDIA_API_KEY/NVIDIA_BASE_URL/NVIDIA_CHAT_MODEL_ID env + .env) fails pydantic validation: invalid base_url format (not a valid HttpUrl), api_key wrong type, or env_file unreadable.

Common situations: NVIDIA_BASE_URL missing the scheme (e.g. 'host.com' instead of 'https://host.com'), a .env path that does not exist, NVIDIA_API_KEY empty string failing the SecretStr validator, pydantic v1/v2 behavior differences.

Related errors

• Failed to create NVIDIA settings.
• Failed to create Ollama settings.
• Failed to validate Mistral AI settings: {e}
• The NVIDIA API key is required.
• Failed to create Ollama settings.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/2c468e45cec6f466. Report an issue: GitHub.