experimental[patch]: missing resolution strategy in anonymization (#16653)

- **Description:** Presidio-based anonymizers are not working because
`_remove_conflicts_and_get_text_manipulation_data` was being called
without a conflict resolution strategy. This PR fixes this issue. In
addition, it removes some mutable default arguments (antipattern).
 
To reproduce the issue, just run the very first cell of this
[notebook](https://python.langchain.com/docs/guides/privacy/2/) from
langchain's documentation.

<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes if applicable,
  - **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

libs/experimental/langchain_experimental/data_anonymizer/presidio.py

@@ -27,7 +27,7 @@ if TYPE_CHECKING:
     from presidio_analyzer import AnalyzerEngine, EntityRecognizer
     from presidio_analyzer.nlp_engine import NlpEngineProvider
     from presidio_anonymizer import AnonymizerEngine
-    from presidio_anonymizer.entities import OperatorConfig
+    from presidio_anonymizer.entities import ConflictResolutionStrategy, OperatorConfig
 
 
 def _import_analyzer_engine() -> "AnalyzerEngine":
@@ -102,7 +102,7 @@ class PresidioAnonymizerBase(AnonymizerBase):
         self,
         analyzed_fields: Optional[List[str]] = None,
         operators: Optional[Dict[str, OperatorConfig]] = None,
-        languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
+        languages_config: Optional[Dict] = None,
         add_default_faker_operators: bool = True,
         faker_seed: Optional[int] = None,
     ):
@@ -123,6 +123,8 @@ class PresidioAnonymizerBase(AnonymizerBase):
                 Defaults to None, in which case faker will be seeded randomly
                 and provide random values.
         """
+        if languages_config is None:
+            languages_config = DEFAULT_LANGUAGES_CONFIG
         OperatorConfig = _import_operator_config()
         AnalyzerEngine = _import_analyzer_engine()
         NlpEngineProvider = _import_nlp_engine_provider()
@@ -183,6 +185,7 @@ class PresidioAnonymizer(PresidioAnonymizerBase):
         text: str,
         language: Optional[str] = None,
         allow_list: Optional[List[str]] = None,
+        conflict_resolution: Optional[ConflictResolutionStrategy] = None,
     ) -> str:
         """Anonymize text.
         Each PII entity is replaced with a fake value.
@@ -204,8 +207,7 @@ class PresidioAnonymizer(PresidioAnonymizerBase):
         """
         if language is None:
             language = self.supported_languages[0]
-
+        elif language not in self.supported_languages:
-        if language not in self.supported_languages:
             raise ValueError(
                 f"Language '{language}' is not supported. "
                 f"Supported languages are: {self.supported_languages}. "
@@ -237,7 +239,7 @@ class PresidioAnonymizer(PresidioAnonymizerBase):
 
         filtered_analyzer_results = (
             self._anonymizer._remove_conflicts_and_get_text_manipulation_data(
-                analyzer_results
+                analyzer_results, conflict_resolution
             )
         )
 
@@ -260,10 +262,12 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
         self,
         analyzed_fields: Optional[List[str]] = None,
         operators: Optional[Dict[str, OperatorConfig]] = None,
-        languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
+        languages_config: Optional[Dict] = None,
         add_default_faker_operators: bool = True,
         faker_seed: Optional[int] = None,
     ):
+        if languages_config is None:
+            languages_config = DEFAULT_LANGUAGES_CONFIG
         super().__init__(
             analyzed_fields,
             operators,
@@ -292,6 +296,7 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
         text: str,
         language: Optional[str] = None,
         allow_list: Optional[List[str]] = None,
+        conflict_resolution: Optional[ConflictResolutionStrategy] = None,
     ) -> str:
         """Anonymize text.
         Each PII entity is replaced with a fake value.
@@ -348,7 +353,7 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
 
         filtered_analyzer_results = (
             self._anonymizer._remove_conflicts_and_get_text_manipulation_data(
-                analyzer_results
+                analyzer_results, conflict_resolution
             )
         )
 

libs/experimental/pyproject.toml

@@ -12,8 +12,8 @@ repository = "https://github.com/langchain-ai/langchain"
 python = ">=3.8.1,<4.0"
 langchain-core = "^0.1.7"
 langchain = "^0.1"
-presidio-anonymizer = {version = "^2.2.33", optional = true}
+presidio-anonymizer = {version = "^2.2.352", optional = true}
-presidio-analyzer = {version = "^2.2.33", optional = true}
+presidio-analyzer = {version = "^2.2.352", optional = true}
 faker = {version = "^19.3.1", optional = true}
 vowpal-wabbit-next = {version = "0.6.0", optional = true}
 sentence-transformers = {version = "^2", optional = true}