fix(presidio_pii_masking.py): enable user to pass their own ad hoc recognizers to presidio

litellm/__init__.py

@@ -55,9 +55,12 @@ baseten_key: Optional[str] = None
 aleph_alpha_key: Optional[str] = None
 nlp_cloud_key: Optional[str] = None
 use_client: bool = False
+### GUARDRAILS ###
 llamaguard_model_name: Optional[str] = None
+presidio_ad_hoc_recognizers: Optional[str] = None
 google_moderation_confidence_threshold: Optional[float] = None
 llamaguard_unsafe_content_categories: Optional[str] = None
+##################
 logging: bool = True
 caching: bool = (
     False  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648

litellm/proxy/hooks/presidio_pii_masking.py

@@ -9,7 +9,7 @@
 
 
 from typing import Optional, Literal, Union
-import litellm, traceback, sys, uuid
+import litellm, traceback, sys, uuid, json
 from litellm.caching import DualCache
 from litellm.proxy._types import UserAPIKeyAuth
 from litellm.integrations.custom_logger import CustomLogger
@@ -27,6 +27,7 @@ import aiohttp, asyncio
 
 class _OPTIONAL_PresidioPIIMasking(CustomLogger):
     user_api_key_cache = None
+    ad_hoc_recognizers = None
 
     # Class variables or attributes
     def __init__(
@@ -40,6 +41,22 @@ class _OPTIONAL_PresidioPIIMasking(CustomLogger):
         if mock_testing == True:  # for testing purposes only
             return
 
+        ad_hoc_recognizers = litellm.presidio_ad_hoc_recognizers
+        if ad_hoc_recognizers is not None:
+            try:
+                with open(ad_hoc_recognizers, "r") as file:
+                    self.ad_hoc_recognizers = json.load(file)
+            except FileNotFoundError:
+                raise Exception(f"File not found. file_path={ad_hoc_recognizers}")
+            except json.JSONDecodeError as e:
+                raise Exception(
+                    f"Error decoding JSON file: {str(e)}, file_path={ad_hoc_recognizers}"
+                )
+            except Exception as e:
+                raise Exception(
+                    f"An error occurred: {str(e)}, file_path={ad_hoc_recognizers}"
+                )
+
         self.presidio_analyzer_api_base = litellm.get_secret(
             "PRESIDIO_ANALYZER_API_BASE", None
         )
@@ -78,6 +95,8 @@ class _OPTIONAL_PresidioPIIMasking(CustomLogger):
                     analyze_url = f"{self.presidio_analyzer_api_base}analyze"
                     verbose_proxy_logger.debug(f"Making request to: {analyze_url}")
                     analyze_payload = {"text": text, "language": "en"}
+                    if self.ad_hoc_recognizers is not None:
+                        analyze_payload["ad_hoc_recognizers"] = self.ad_hoc_recognizers
                     redacted_text = None
                     async with session.post(
                         analyze_url, json=analyze_payload