microsoft/semantic-kernel · error · ServiceInitializationError

The OpenAI text model ID is required.

Error message

The OpenAI text model ID is required.

What it means

Raised while constructing an OpenAITextCompletion service. The constructor builds an OpenAISettings (merging the ai_model_id argument with OPENAI_* env vars and an optional .env file); if openai_settings.text_model_id is still falsy afterward, the service cannot target a completion model and throws ServiceInitializationError. This is a startup-time configuration fault, distinct from the 'Failed to create OpenAI settings' ValidationError wrapper.

Source

Thrown at python/semantic_kernel/connectors/ai/open_ai/services/open_ai_text_completion.py:62

            default_headers: The default headers mapping of string keys to
                string values for HTTP requests. (Optional)
            async_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)
        """
        try:
            openai_settings = OpenAISettings(
                api_key=api_key,
                org_id=org_id,
                text_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 OpenAI settings.", ex) from ex
        if not openai_settings.text_model_id:
            raise ServiceInitializationError("The OpenAI text model ID is required.")
        super().__init__(
            ai_model_id=openai_settings.text_model_id,
            service_id=service_id,
            api_key=openai_settings.api_key.get_secret_value() if openai_settings.api_key else None,
            org_id=openai_settings.org_id,
            ai_model_type=OpenAIModelTypes.TEXT,
            default_headers=default_headers,
            client=async_client,
        )

    @classmethod
    def from_dict(cls, settings: dict[str, Any]) -> "OpenAITextCompletion":
        """Initialize an Open AI service from a dictionary of settings.

        Args:
            settings: A dictionary of settings for the service.
        """
        if "default_headers" in settings and isinstance(settings["default_headers"], str):

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Pass ai_model_id explicitly: OpenAITextCompletion(ai_model_id='gpt-3.5-turbo-instruct', api_key='sk-...')
2. Set the environment variable: export OPENAI_TEXT_MODEL_ID=gpt-3.5-turbo-instruct
3. Create/repair a .env file containing OPENAI_TEXT_MODEL_ID and pass env_file_path='.env' to the constructor
4. Verify the exact variable name: this is text completions (OPENAI_TEXT_MODEL_ID), not chat (OPENAI_CHAT_MODEL_ID)

Example fix

# before
service = OpenAITextCompletion(api_key="sk-...")
# raises ServiceInitializationError: The OpenAI text model ID is required.

# after
service = OpenAITextCompletion(ai_model_id="gpt-3.5-turbo-instruct", api_key="sk-...")

import os
from semantic_kernel.connectors.ai.open_ai.settings.open_ai_settings import OpenAISettings

s = OpenAISettings()
if not s.text_model_id:
    raise ValueError("OPENAI_TEXT_MODEL_ID is required before building OpenAITextCompletion")

import os


def has_text_completion_model(ai_model_id: str | None) -> bool:
    return bool(ai_model_id or os.getenv("OPENAI_TEXT_MODEL_ID"))

from semantic_kernel.exceptions.service_exceptions import ServiceInitializationError

try:
    service = OpenAITextCompletion()
except ServiceInitializationError as e:
    if "text model ID is required" in str(e):
        raise SystemExit("Set OPENAI_TEXT_MODEL_ID or pass ai_model_id") from e
    raise

When it happens

Trigger: Calling OpenAITextCompletion() or OpenAITextCompletion.from_dict({}) with no ai_model_id argument AND no OPENAI_TEXT_MODEL_ID environment variable. Both the explicit argument and the env var must be absent for this guard to fire.

Common situations: The OPENAI_TEXT_MODEL_ID env var was never set in the deployment/CI environment; a .env file is used but the key is misspelled or env_file_path points to the wrong file; the developer reused chat model config (OPENAI_CHAT_MODEL_ID) assuming it covers text completion, which it does not; text completion needs its own model such as gpt-3.5-turbo-instruct.

Related errors

• The OpenAI embedding model ID is required.
• The OpenAI text to audio model ID is required.
• The OpenAI text to image model ID is required.
• The Amazon Bedrock Chat Model ID is missing.
• The Amazon Bedrock Text Model ID is missing.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/b14b43bce023c86f. Report an issue: GitHub.