BerriAI/litellm · error · Exception

Trying to use Blocked User ListThis uses the enterprise fold

Error message

Trying to use Blocked User ListThis uses the enterprise folder - only available on the Docker image.

What it means

The callback 'blocked_user_check' is handled by code that imports from the 'enterprise' folder (enterprise.enterprise_hooks.blocked_user_list). That folder ships only inside the LiteLLM enterprise Docker image; a plain pip install of litellm does not contain it. The ImportError is caught and re-raised with this message that names the Docker requirement.

Source

Thrown at litellm/proxy/common_utils/callback_utils.py:285

                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:
                    raise Exception("Trying to use Llm Guard" + CommonProxyErrors.not_premium_user.value)

                llm_guard_moderation_obj = _ENTERPRISE_LLMGuard()
                imported_list.append(llm_guard_moderation_obj)
            elif isinstance(callback, str) and callback == "blocked_user_check":
                try:
                    from enterprise.enterprise_hooks.blocked_user_list import (
                        _ENTERPRISE_BlockedUserList,
                    )
                except ImportError:
                    raise Exception(
                        "Trying to use Blocked User List" + CommonProxyErrors.missing_enterprise_package_docker.value
                    )

                if premium_user is not True:
                    raise Exception("Trying to use ENTERPRISE BlockedUser" + CommonProxyErrors.not_premium_user.value)

                blocked_user_list = _ENTERPRISE_BlockedUserList(prisma_client=prisma_client)
                imported_list.append(blocked_user_list)
            elif isinstance(callback, str) and callback == "banned_keywords":
                try:
                    from enterprise.enterprise_hooks.banned_keywords import (
                        _ENTERPRISE_BannedKeywords,
                    )
                except ImportError:
                    raise Exception(
                        "Trying to use Banned Keywords" + CommonProxyErrors.missing_enterprise_package_docker.value
                    )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Remove 'blocked_user_check' from litellm_settings.callbacks.
2. Or run the proxy with the LiteLLM enterprise Docker image, which contains the enterprise folder.
3. Note: even on Docker, a valid LITELLM_LICENSE is still required next (error 2884).

Example fix

# before
litellm_settings:
  callbacks: ["blocked_user_check"]
# started with: pip install litellm && litellm --config config.yaml

# after
litellm_settings:
  callbacks: []
# or run the enterprise docker image with a license

import os

def blocked_user_check_ok() -> bool:
    return os.path.isdir("enterprise") and os.path.exists("enterprise/enterprise_hooks/blocked_user_list.py")

if "blocked_user_check" in callbacks and not blocked_user_check_ok():
    raise SystemExit("blocked_user_check needs the enterprise Docker image")

try:
    start_proxy(cfg)
except Exception as e:
    if "enterprise folder" in str(e):
        raise SystemExit("switch to the litellm enterprise docker image or remove the callback")
    raise

When it happens

Trigger: Run the proxy from a pip install or from a source checkout with callbacks: ['blocked_user_check']. Any environment where the top-level 'enterprise' package does not exist produces this error at config load.

Common situations: A config that ran on the official enterprise Docker image is reused on a local pip install or on a custom slim image. Someone builds their own Dockerfile with pip install litellm and loses the enterprise folder.

Understand the failure class

Background: "X is not installed. Please install it with pip install Y": missing optional dependency errors — ImportError/ValueError raised when a library's optional extra was never installed — this error's family across 22 libraries.

Related errors

• Trying to use Banned KeywordsThis uses the enterprise folder
• Trying to use Llm GuardMissing litellm-enterprise package. P
• Trying to use ENTERPRISE BlockedUserYou must be a LiteLLM En
• Trying to use OpenAI Moderations Check,This uses the enterpr
• Trying to use Google Text Moderation,This uses the enterpris

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/e7205b8d70db97b8. Report an issue: GitHub.