Instance anonymization

libs/experimental/langchain_experimental/data_anonymizer/deanonymizer_mapping.py

@@ -17,5 +17,17 @@ def data(self) -> MappingDataType:
         return {k: dict(v) for k, v in self.mapping.items()}
 
     def update(self, new_mapping: MappingDataType) -> None:
+        """Update the deanonymizer mapping with new values
+        Duplicate values will not be added
+        """
+        new_values_seen = set()
+
         for entity_type, values in new_mapping.items():
-            self.mapping[entity_type].update(values)
+            for k, v in values.items():
+                # Make sure it is not a duplicate value
+                if (
+                    v not in self.mapping[entity_type].values()
+                    and v not in new_values_seen
+                ):
+                    self.mapping[entity_type][k] = v
+                    new_values_seen.update({v})

libs/experimental/langchain_experimental/data_anonymizer/presidio.py

@@ -282,7 +282,12 @@ def _anonymize(self, text: str, language: Optional[str] = None) -> str:
             text, filtered_analyzer_results, anonymizer_results
         )
 
-        return anonymizer_results.text
+        anonymizer_mapping = {
+            key: {v: k for k, v in inner_dict.items()}
+            for key, inner_dict in self.deanonymizer_mapping.items()
+        }
+
+        return default_matching_strategy(text, anonymizer_mapping)
 
     def _deanonymize(
         self,