From d706d3b6723dcd73cbf85d37a4858485ce130e69 Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Tue, 20 Feb 2024 16:01:15 -0800
Subject: [PATCH] fix(presidio_pii_masking.py): enable user to pass ad hoc
 recognizer for pii masking

---
 .../example_presidio_ad_hoc_recognizer.json   | 28 +++++++++++++++++++
 litellm/proxy/hooks/presidio_pii_masking.py   |  4 ++-
 2 files changed, 31 insertions(+), 1 deletion(-)
 create mode 100644 litellm/proxy/hooks/example_presidio_ad_hoc_recognizer.json

diff --git a/litellm/proxy/hooks/example_presidio_ad_hoc_recognizer.json b/litellm/proxy/hooks/example_presidio_ad_hoc_recognizer.json
new file mode 100644
index 0000000000..6a94d8de12
--- /dev/null
+++ b/litellm/proxy/hooks/example_presidio_ad_hoc_recognizer.json
@@ -0,0 +1,28 @@
+[
+    {
+        "name": "Zip code Recognizer",
+        "supported_language": "en",
+        "patterns": [
+            {
+                "name": "zip code (weak)",
+                "regex": "(\\b\\d{5}(?:\\-\\d{4})?\\b)",
+                "score": 0.01
+            }
+        ],
+        "context": ["zip", "code"],
+        "supported_entity": "ZIP"
+    },
+    {
+        "name": "Swiss AHV Number Recognizer",
+        "supported_language": "en",
+        "patterns": [
+            {
+                "name": "AHV number (strong)",
+                "regex": "(756\\.\\d{4}\\.\\d{4}\\.\\d{2})|(756\\d{10})",
+                "score": 0.95
+            }
+        ],
+        "context": ["AHV", "social security", "Swiss"],
+        "supported_entity": "AHV_NUMBER"
+    }
+]
\ No newline at end of file
diff --git a/litellm/proxy/hooks/presidio_pii_masking.py b/litellm/proxy/hooks/presidio_pii_masking.py
index 99e501589f..86c88975e0 100644
--- a/litellm/proxy/hooks/presidio_pii_masking.py
+++ b/litellm/proxy/hooks/presidio_pii_masking.py
@@ -235,7 +235,9 @@ class _OPTIONAL_PresidioPIIMasking(CustomLogger):
                         messages[index][
                             "content"
                         ] = r  # replace content with redacted string
-                verbose_proxy_logger.debug(f"Redacted pii message: {data['messages']}")
+                verbose_proxy_logger.info(
+                    f"Presidio PII Masking: Redacted pii message: {data['messages']}"
+                )
             return data
         except Exception as e:
             verbose_proxy_logger.info(f"An error occurred - {str(e)}")