microsoft/semantic-kernel · error · ServiceInitializationError

Failed to initialize the Amazon Bedrock Text Completion…

Error message

Failed to initialize the Amazon Bedrock Text Completion Service.

What it means

Raised during BedrockTextCompletion construction when BedrockSettings (text_model_id, model_provider, env vars) fails Pydritic validation. Mirrors the chat-completion init error: a ServiceInitializationError thrown before the client is created, with the ValidationError chained.

Solutions

Inspect the chained ValidationError (e.__cause__) to find the failing field.
Supply a valid text_model_id and supported model_provider.
Verify env file path/encoding if loading from .env.

Example fix

# before
service = BedrockTextCompletion(model_id="amazon.titan-text", model_provider="bogus")

# after
service = BedrockTextCompletion(model_id="amazon.titan-text-express-v1", model_provider="amazon")

Defensive patterns

Strategy: try-catch

Validate before calling

SUPPORTED_PROVIDERS = {"anthropic", "amazon", "meta", "mistral", "ai21", "cohere", "stability"}
assert model_provider is None or model_provider in SUPPORTED_PROVIDERS

Try / catch

from semantic_kernel.exceptions import ServiceInitializationError
try:
    service = BedrockTextCompletion(model_id=model_id, model_provider=model_provider)
except ServiceInitializationError as e:
    print("Bedrock settings error:", e.__cause__)

Prevention

Use a supported model_provider or omit to infer from model_id.
Inspect __cause__ for the failing field.
Verify env file path/encoding.

When it happens

Trigger: BedrockSettings validation fails — invalid model_provider, malformed env, missing/invalid required config for the text-completion settings path.

Common situations: Unsupported model_provider string; wrong env_file_path; settings schema change after an SDK upgrade; typos in configuration.

Related errors

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/7c5971ee2cfe498e. Report an issue: GitHub.

Appendix: source

Thrown at python/semantic_kernel/connectors/ai/bedrock/services/bedrock_text_completion.py:71

        Args:
            model_id: The Amazon Bedrock text model ID to use.
            model_provider: The Bedrock model provider to use.
            service_id: The Service ID for the text completion service.
            runtime_client: The Amazon Bedrock runtime client to use.
            client: The Amazon Bedrock client to use.
            env_file_path: The path to the .env file to load settings from.
            env_file_encoding: The encoding of the .env file.
        """
        try:
            bedrock_settings = BedrockSettings(
                text_model_id=model_id,
                model_provider=model_provider,
                env_file_path=env_file_path,
                env_file_encoding=env_file_encoding,
            )
        except ValidationError as e:
            raise ServiceInitializationError("Failed to initialize the Amazon Bedrock Text Completion Service.") from e

        if bedrock_settings.text_model_id is None:
            raise ServiceInitializationError("The Amazon Bedrock Text Model ID is missing.")

        super().__init__(
            ai_model_id=bedrock_settings.text_model_id,
            service_id=service_id or bedrock_settings.text_model_id,
            runtime_client=runtime_client,
            client=client,
            bedrock_model_provider=bedrock_settings.model_provider,
        )

    # region Overriding base class methods

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

View on GitHub (pinned to c028a0c7dc)