Toxicity Detection validators (#80)

Co-authored-by: dennyabrain <[email protected]>

Author: rkritika1508

backend/app/api/API_USAGE.md

@@ -101,6 +101,7 @@ Optional filters:
 - `ids=<uuid>&ids=<uuid>`
 - `stage=input|output`
 - `type=uli_slur_match|pii_remover|gender_assumption_bias|ban_list|llm_critic|topic_relevance|llamaguard_7b|profanity_free|nsfw_text`
+- `type=uli_slur_match|pii_remover|gender_assumption_bias|ban_list|llm_critic|topic_relevance|llamaguard_7b|profanity_free`
 
 Example:
 

backend/app/core/validators/config/base_validator_config.py

@@ -19,14 +19,9 @@ def _on_fix(self, value: str, fail_result: FailResult):
         fix_value = fail_result.fix_value if fail_result else None
         if not fix_value:
             self.validator_metadata = {
-<<<<<<< feat/toxicity-huggingface-model
-                "reason": f"Empty string has been returned since the validation failed for: {self.type}"
-            }
-=======
                 "reason": f"Empty string has been returned since the validation failed for: {self.type}"  # type: ignore[attr-defined]
             }
             return ""
->>>>>>> feat/toxicity-hub-validators
         return fix_value
 
     def resolve_on_fail(self):