microsoft/semantic-kernel · error · ServiceInitializationError

Failed to create MistralAI settings.

Error message

Failed to create MistralAI settings.

What it means

Raised by MistralAIChatCompletion.__init__ when constructing MistralAISettings raises a pydantic ValidationError. The constructor wraps the validation failure (api_key, chat_model_id, env) into a ServiceInitializationError chained from the cause, failing fast at service creation.

Source

Thrown at python/semantic_kernel/connectors/ai/mistral_ai/services/mistral_ai_chat_completion.py:94

            ai_model_id : MistralAI model name, see
                https://docs.mistral.ai/getting-started/models/
            service_id : Service ID tied to the execution settings.
            api_key : The optional API key to use. If provided will override,
                the env vars or .env file value.
            async_client : An existing client to use.
            env_file_path : Use the environment settings file as a fallback
                to environment variables.
            env_file_encoding : The encoding of the environment settings file.
        """
        try:
            mistralai_settings = MistralAISettings(
                api_key=api_key,
                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 MistralAI settings.", ex) from ex

        if not mistralai_settings.chat_model_id:
            raise ServiceInitializationError("The MistralAI chat model ID is required.")

        if not async_client:
            async_client = Mistral(
                api_key=mistralai_settings.api_key.get_secret_value(),
            )

        super().__init__(
            async_client=async_client,
            service_id=service_id or mistralai_settings.chat_model_id,
            ai_model_id=ai_model_id or mistralai_settings.chat_model_id,
        )

    # region Overriding base class methods

    # Override from AIServiceClientBase

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Inspect the chained cause (ValidationError detail) to find the failing field.
2. Set MISTRAL_API_KEY (and model id) via env / .env, or pass api_key and ai_model_id explicitly.
3. Verify env_file_path is correct and readable.

Example fix

# before
svc = MistralAIChatCompletion()
# after
svc = MistralAIChatCompletion(ai_model_id='mistral-large-latest', api_key=os.environ['MISTRAL_API_KEY'])

from semantic_kernel.connectors.ai.mistral_ai.mistral_ai_settings import MistralAISettings
try:
    s = MistralAISettings(api_key=..., chat_model_id=...)
except Exception as e:
    print('config invalid:', e)

try:
    svc = MistralAIChatCompletion(api_key=..., ai_model_id=...)
except ServiceInitializationError as e:
    raise

When it happens

Trigger: Instantiating MistralAIChatCompletion with missing/malformed api_key or model id and no env fallback. A .env file that doesn't satisfy MistralAISettings validators.

Common situations: MISTRAL_API_KEY not set. Wrong env file path/encoding. Empty/malformed api_key or model id passed explicitly.

Related errors

• Failed to validate Vertex AI settings: {e}
• Failed to validate Vertex AI settings: {e}
• Failed to validate Vertex AI settings: {e}
• The MistralAI chat model ID is required.
• Failed to validate Mistral AI settings: {e}

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/9c72ff8973336364. Report an issue: GitHub.