microsoft/semantic-kernel · error · ServiceInitializationError

The Google AI Gemini model ID is required.

Error message

The Google AI Gemini model ID is required.

What it means

Raised during GoogleAIChatCompletion.__init__ when the resolved GoogleAISettings.gemini_model_id is falsy (None or empty string). Even though the field is optional in settings (so it passes pydantic validation), the service cannot operate without a model ID, so construction is rejected after settings load.

Source

Thrown at python/semantic_kernel/connectors/ai/google/google_ai/services/google_ai_chat_completion.py:117

        Raises:
            ServiceInitializationError: If an error occurs during initialization.
        """
        try:
            google_ai_settings = GoogleAISettings(
                gemini_model_id=gemini_model_id,
                api_key=api_key,
                cloud_project_id=project_id,
                cloud_region=region,
                use_vertexai=use_vertexai,
                env_file_path=env_file_path,
                env_file_encoding=env_file_encoding,
            )
        except ValidationError as e:
            raise ServiceInitializationError(f"Failed to validate Google AI settings: {e}") from e

        if not google_ai_settings.gemini_model_id:
            raise ServiceInitializationError("The Google AI Gemini model ID is required.")

        if not client:
            if google_ai_settings.use_vertexai and not google_ai_settings.cloud_project_id:
                raise ServiceInitializationError("Project ID must be provided when use_vertexai is True.")
            if google_ai_settings.use_vertexai and not google_ai_settings.cloud_region:
                raise ServiceInitializationError("Region must be provided when use_vertexai is True.")
            if not google_ai_settings.use_vertexai and not google_ai_settings.api_key:
                raise ServiceInitializationError("The API key is required when use_vertexai is False.")

        super().__init__(
            ai_model_id=google_ai_settings.gemini_model_id,
            service_id=service_id or google_ai_settings.gemini_model_id,
            service_settings=google_ai_settings,
            client=client,
        )

    # region Overriding base class methods

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Set GOOGLE_AI_GEMINI_MODEL_ID to a valid model (e.g. gemini-1.5-pro) in the environment or .env.
2. Pass gemini_model_id explicitly to the constructor.
3. Verify the env_file_path/encoding arguments point to the .env file that actually defines the variable.

Example fix

# before
svc = GoogleAIChatCompletion()  # GOOGLE_AI_GEMINI_MODEL_ID unset
# after
svc = GoogleAIChatCompletion(gemini_model_id="gemini-1.5-pro")

def has_gemini_model_id(model_id: str | None) -> bool:
    return isinstance(model_id, str) and bool(model_id.strip())

def is_non_empty_model_id(value: object) -> bool:
    return isinstance(value, str) and bool(value.strip())

from semantic_kernel.exceptions.service_exceptions import ServiceInitializationError

try:
    svc = GoogleAIChatCompletion(gemini_model_id=model_id)
except ServiceInitializationError as e:
    if "model ID is required" in str(e):
        raise ValueError("Set GOOGLE_AI_GEMINI_MODEL_ID or pass gemini_model_id") from e
    raise

When it happens

Trigger: Constructing GoogleAIChatCompletion without a gemini_model_id argument and without GOOGLE_AI_GEMINI_MODEL_ID in the environment/.env, so the settings field resolves to None.

Common situations: Missing GOOGLE_AI_GEMINI_MODEL_ID env var; typo in the env var name; .env not loaded (wrong path/encoding); passing gemini_model_id=None explicitly and relying on env that is absent.

Related errors

• The Google AI Gemini model ID is required.
• Failed to validate Google AI settings: {e}
• Project ID must be provided when use_vertexai is True.
• Region must be provided when use_vertexai is True.
• The API key is required when use_vertexai is False.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/080843bb769a8b98. Report an issue: GitHub.