microsoft/semantic-kernel · error · ServiceInitializationError

Failed to validate Vertex AI settings: {e}

Error message

Failed to validate Vertex AI settings: {e}

What it means

Raised by VertexAITextCompletion.__init__ when VertexAISettings construction throws a pydantic ValidationError. The error wraps the validation detail into a ServiceInitializationError so text-completion service initialization fails fast with the underlying reason (project_id/region/env).

Source

Thrown at python/semantic_kernel/connectors/ai/google/vertex_ai/services/vertex_ai_text_completion.py:75

        Args:
            project_id (str): The Google Cloud project ID.
            region (str): The Google Cloud region.
            gemini_model_id (str): The Gemini model ID.
            service_id (str): The Vertex AI service ID.
            env_file_path (str): The path to the environment file.
            env_file_encoding (str): The encoding of the environment file.
        """
        try:
            vertex_ai_settings = VertexAISettings(
                project_id=project_id,
                region=region,
                gemini_model_id=gemini_model_id,
                env_file_path=env_file_path,
                env_file_encoding=env_file_encoding,
            )
        except ValidationError as e:
            raise ServiceInitializationError(f"Failed to validate Vertex AI settings: {e}") from e
        if not vertex_ai_settings.gemini_model_id:
            raise ServiceInitializationError("The Vertex AI Gemini model ID is required.")

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

    # region Overriding base class methods

    # Override from AIServiceClientBase
    @override
    def get_prompt_execution_settings_class(self) -> type["PromptExecutionSettings"]:
        return VertexAITextPromptExecutionSettings

    @override
    @trace_text_completion(VertexAIBase.MODEL_PROVIDER_NAME)

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Inspect the embedded {e} to find the failing field(s).
2. Provide project_id and region explicitly or via env/ .env.
3. Confirm env_file_path is correct and the file has the expected keys.

Example fix

# before
svc = VertexAITextCompletion()
# after
svc = VertexAITextCompletion(project_id='my-project', region='us-central1', gemini_model_id='gemini-1.5-pro')

from semantic_kernel.connectors.ai.google.vertex_ai.vertex_ai_settings import VertexAISettings
try:
    s = VertexAISettings()
except Exception as e:
    print('config invalid:', e)

try:
    svc = VertexAITextCompletion(project_id=..., region=..., gemini_model_id=...)
except ServiceInitializationError as e:
    raise

When it happens

Trigger: Instantiating VertexAITextCompletion with missing/malformed project_id, region, or env configuration. Same root causes as the chat variant but on the text-completion constructor.

Common situations: Missing VERTEX_AI_PROJECT or region env var. Bad .env path/encoding. Credentials not configured for the text-completion flow.

Related errors

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

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/40a0f1006b1c63cf. Report an issue: GitHub.