This site is not available on Mobile. Please return on a desktop browser.
Visit our main site at guardrailsai.com
Developed by | Guardrails AI |
---|---|
Date of development | Aug 16, 2024 |
Validator type | Data Leakage |
Blog | |
License | Apache 2 |
Input/Output | Input |
Validates that output does not have banned words, using fuzzy search. Useful for preventing internal codenames from leaking.
Dependencies:
Foundation model access keys:
$ 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")
Initializes a new instance of the BanList class.
Parameters
banned_words
(List[str]): A list of banned words to check for in output.max_l_dist
(int): Maximum Levenshtein distance for fuzzy search. Defaults to 1.on_fail
(str, Callable): The policy to enact when a validator fails. If str
, must be one of reask
, fix
, filter
, refrain
, noop
, exception
or fix_reask
. Otherwise, must be a function that is called when the validator fails.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:
guard.parse(...)
where this method will be called internally for each associated Validator.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 |
The validator playground is available to authenticated users. Please log in to use it.