| Developed by | Guardrails AI | | Date of development | Feb 15, 2024 | | Validator type | Rule-following | | Blog | | | License | Apache 2 | | Input/Output | Output |
This validator ensures that any given output follows a pre-specified regex rule.
- Dependencies:
- guardrails-ai>=0.4.0
- rstr
$ guardrails hub install hub://guardrails/regex_match
In this example, we apply the validator to a string output generated by an LLM.
# Import Guard and Validator
from guardrails.hub import RegexMatch
from guardrails import Guard
# Use the Guard with the validator
guard = Guard().use(
RegexMatch, regex="Open.*", on_fail="exception"
)
# Test passing response
guard.validate(
"OpenAI's GPT3.5 model is the latest in the GPT series. It is a powerful language model."
)
try:
# Test failing response
guard.validate(
"MetaAI's Llama2 is the latest in their open-source LLM series. It is a powerful language model."
)
except Exception as e:
print(e)
Output:
Validation failed for field with errors: Result must match Open.*
__init__(self, regex, match_type=None, on_fail="noop")
-
Initializes a new instance of the Validator class.
regex
(str): String representing the regex patternmatch_type
(Optional[str]): One ofsearch
orfullmatch
on_fail
(str, Callable): The policy to enact when a validator fails. Ifstr
, must be one ofreask
,fix
,filter
,refrain
,noop
,exception
orfix_reask
. Otherwise, must be a function that is called when the validator fails.
Parameters
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.
- 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. - When invoking
guard.parse(...)
, ensure to pass the appropriatemetadata
dictionary that includes keys and values required by this validator. Ifguard
is associated with multiple validators, combine all necessary metadata into a single dictionary. value
(Any): The input value to validate.metadata
(dict): A dictionary containing metadata required for validation. No additional metadata keys are needed for this validator.
Note:
Parameters