BerriAI/litellm · error · Exception
Trying to use Google Text Moderation,This uses the enterpris
Error message
Trying to use Google Text Moderation,This uses the enterprise folder - only available on the Docker image.
What it means
Raised at startup when callbacks enables 'google_text_moderation' but importing enterprise.enterprise_hooks.google_text_moderation._ENTERPRISE_GoogleTextModeration fails with ImportError. Like openai_moderations, this hook lives in the 'enterprise' folder that exists only in LiteLLM's official Docker image; a pip-installed proxy cannot load it, and the concatenated message directs you to the Docker image.
Source
Thrown at litellm/proxy/common_utils/callback_utils.py:256
callback_specific_params["lakera_prompt_injection"], dict
):
init_params = callback_specific_params["lakera_prompt_injection"]
lakera_moderations_object = lakeraAI_Moderation(**init_params)
imported_list.append(lakera_moderations_object)
elif isinstance(callback, str) and callback == "aporia_prompt_injection":
from litellm.proxy.guardrails.guardrail_hooks.aporia_ai.aporia_ai import (
AporiaGuardrail,
)
aporia_guardrail_object = AporiaGuardrail()
imported_list.append(aporia_guardrail_object)
elif isinstance(callback, str) and callback == "google_text_moderation":
try:
from enterprise.enterprise_hooks.google_text_moderation import (
_ENTERPRISE_GoogleTextModeration,
)
except ImportError:
raise Exception(
"Trying to use Google Text Moderation,"
+ CommonProxyErrors.missing_enterprise_package_docker.value
)
if premium_user is not True:
raise Exception("Trying to use Google Text Moderation" + CommonProxyErrors.not_premium_user.value)
google_text_moderation_obj = _ENTERPRISE_GoogleTextModeration()
imported_list.append(google_text_moderation_obj)
elif isinstance(callback, str) and callback == "llmguard_moderations":
try:
from litellm_enterprise.enterprise_callbacks.llm_guard import (
_ENTERPRISE_LLMGuard,
)
except ImportError:
raise Exception("Trying to use Llm Guard" + CommonProxyErrors.missing_enterprise_package.value)
if premium_user is not True:View on GitHub (pinned to 77b7c6c40c)
Solutions
- Deploy with the official litellm/litellm Docker image that includes the enterprise folder.
- Or remove 'google_text_moderation' from callbacks for non-docker installs.
- Remember the license gate follows: set LITELLM_LICENSE once the import resolves.
- Smoke-test custom images: python -c "import enterprise.enterprise_hooks.google_text_moderation".
Example fix
# before uv pip install litellm && litellm --config config.yaml # config has callbacks: ["google_text_moderation"] # after docker run -e LITELLM_LICENSE=$LITELLM_LICENSE -v $PWD/config.yaml:/app/config.yaml litellm/litellm
Defensive patterns
Strategy: validation
Validate before calling
import importlib.util
if 'google_text_moderation' in callbacks and importlib.util.find_spec('enterprise.enterprise_hooks.google_text_moderation') is None:
callbacks = [c for c in callbacks if c != 'google_text_moderation']
logger.warning('google_text_moderation unavailable outside the official Docker image; removed') Prevention
- Maintain separate config profiles: docker (enterprise hooks allowed) vs pip (OSS callbacks only).
- CI should validate that every callback in config resolves on the target runtime.
- Remember the license gate follows the import gate for this callback.
When it happens
Trigger: callbacks: ['google_text_moderation'] in config.yaml while running litellm from pip, uv, or a custom slim image that does not vendor the enterprise folder. Fails during config load before the server binds.
Common situations: Same config reused across pip dev environments and docker prod; teams building minimal images to cut size and accidentally excluding enterprise hooks; OSS-only installs trialing moderation features.
Related errors
- Trying to use OpenAI Moderations Check,This uses the enterpr
- MissingTrying to use Llama GuardMissing litellm-enterprise p
- Trying to use Secret DetectionMissing litellm-enterprise pac
- Trying to use OpenAI Moderations CheckYou must be a LiteLLM
- Trying to use Llama GuardYou must be a LiteLLM Enterprise us
AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18).
Data as JSON: /api/errors/cd126a0a32438b5a.
Report an issue: GitHub.