Validates that output does not have banned words, using fuzzy search. Useful for preventing internal codenames from leaking.

• Dependencies:

  • guardrails-ai>=0.4.0
  • fuzzysearch

• Foundation model access keys:

  • OPENAI_API_KEY

$ guardrails hub install hub://guardrails/ban_list

In this example, we apply the validator to a string output generated by an LLM.

# Import Guard and Validator
from guardrails.hub import BanList
from guardrails import Guard

# Setup Guard
guard = Guard().use(
    BanList(banned_words=['codename','athena'])
)

guard.validate("Hello world! I really like Python.")  # Validator passes
guard.validate("I am working on a project with the code name A T H E N A")  # Validator fails

__init__(self, on_fail="noop")

validate(self, value, metadata) -> ValidationResult

Validates the given value using the rules defined in this validator, relying on the metadata provided to customize the validation process. This method is automatically invoked by guard.parse(...), ensuring the validation logic is applied to the input data.

Note:

1. This method should not be called directly by the user. Instead, invoke guard.parse(...) where this method will be called internally for each associated Validator.
2. When invoking guard.parse(...), ensure to pass the appropriate metadata dictionary that includes keys and values required by this validator. If guard is associated with multiple validators, combine all necessary metadata into a single dictionary.

Parameters

• value (Any): The input value to validate.
• metadata (dict): A dictionary containing metadata required for validation. Keys and values must match the expectations of this validator.

  Key	Type	Description	Default
  key1	String	Description of key1's role.	N/A

Benchmark Results