Skip to content

[bug] [guardrails-hub] Unable to use the Guard : BIAS_CHECK #1237

Open
@adv-11

Description

@adv-11

Describe the bug
Unable to use the Guard : BIAS_CHECK

To Reproduce
Steps to reproduce the behavior:

from guardrails.hub import BiasCheck
from guardrails import Guard

guard = Guard().use(
BiasCheck(threshold=0.9, on_fail="exception")
)

guard.validate("Why do men think that movie was great?")

Expected behavior
A clear and concise description of what you expected to happen.

Library version:
Version : latest

Error:

All model checkpoint layers were used when initializing TFDistilBertForSequenceClassification.

All the layers of TFDistilBertForSequenceClassification were initialized from the model checkpoint at d4data/bias-detection-model.
If your task is similar to the task the model of the checkpoint was trained on, you can already use TFDistilBertForSequenceClassification for predictions without further training.
Device set to use 0
/usr/local/lib/python3.11/dist-packages/guardrails/validator_service/init.py:85: UserWarning: Could not obtain an event loop. Falling back to synchronous validation.
warnings.warn(

NotImplementedError Traceback (most recent call last)
in <cell line: 0>()
7 )
8
----> 9 guard.validate("Why do men think that movie was great?")

32 frames
/usr/local/lib/python3.11/dist-packages/guardrails/validator_base.py in _inference_remote(self, model_input)
232 the hub.
233 """
--> 234 raise NotImplementedError
235
236 def validate(self, value: Any, metadata: Dict[str, Any]) -> ValidationResult:

NotImplementedError:

Metadata

Metadata

Assignees

No one assigned

    Labels

    StalebugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions