github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-27 00:48:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Temporarily remove language selection (#10097)

Browse Source 
Adapting Microsoft Presidio to other languages requires a bit more work,
so for now it will be good idea to remove the language option to choose,
so as not to cause errors and confusion.
https://microsoft.github.io/presidio/analyzer/languages/

I will handle different languages after the weekend 😄
This commit is contained in:
maks-operlejn-ds 2023-09-01 20:30:48 +02:00 committed by GitHub
parent 71c418725f
commit b5a74fb973
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
libs/experimental/langchain_experimental/data_anonymizer/presidio.py
View File

@ -18,14 +18,12 @@ class PresidioAnonymizer(AnonymizerBase):
def __init__( def __init__(
self, self,
analyzed_fields: Optional[List[str]] = None, analyzed_fields: Optional[List[str]] = None,
language: str = "en",
operators: Optional[Dict[str, OperatorConfig]] = None, operators: Optional[Dict[str, OperatorConfig]] = None,
): ):
""" """
Args: Args:
analyzed_fields: List of fields to detect and then anonymize. analyzed_fields: List of fields to detect and then anonymize.
Defaults to all entities supported by Microsoft Presidio. Defaults to all entities supported by Microsoft Presidio.
language: Language to use for analysis. Defaults to english.
operators: Operators to use for anonymization. operators: Operators to use for anonymization.
Operators allow for custom anonymization of detected PII. Operators allow for custom anonymization of detected PII.
Learn more: Learn more:
@ -54,7 +52,6 @@ class PresidioAnonymizer(AnonymizerBase):
if analyzed_fields is not None if analyzed_fields is not None
else list(get_pseudoanonymizer_mapping().keys()) else list(get_pseudoanonymizer_mapping().keys())
) )
self.language = language
self.operators = ( self.operators = (
operators operators
if operators is not None if operators is not None
@ -72,7 +69,7 @@ class PresidioAnonymizer(AnonymizerBase):
results = self._analyzer.analyze( results = self._analyzer.analyze(
text, text,
entities=self.analyzed_fields, entities=self.analyzed_fields,
language=self.language, language="en",
) )
return self._anonymizer.anonymize( return self._anonymizer.anonymize(