[Textanalytics] python sdk 20251115preview (#43666)

* Configurations:  'specification/cognitiveservices/data-plane/LanguageAnalyzeText/tspconfig.yaml', API Version: 2025-11-15-preview, SDK Release Type: beta, and CommitSHA: '856560f304f6a4df7c50f17b7d72ac73884fab74' in SpecRepo: 'https://github.com/Azure/azure-rest-api-specs' Pipeline run: https://dev.azure.com/azure-sdk/internal/_build/results?buildId=5503780 Refer to https://eng.ms/docs/products/azure-developer-experience/develop/sdk-release/sdk-release-prerequisites to prepare for SDK release.

* updated clientname to TextAnalysisClient

* removed generated tests and samples

* removed generated tests

* delete

* added patch from last preview

* set begin_analyze_text_job to private

* updated version

* added test for recognize_pii_redaction_policies

* added test for pii_redaction_policies_async

* make language optional and added test for pii_confidence_score_threshold

* added test for pii_confidence_score_threshold_async

* updated the tests for new features

* update all test records

* added samples for the new features

* update assets.json

* updated the change log

* updated readme

* fixed spelling error

* add samples of new features in readme

* update snippets

* removed 3.0, 3.1

---------

Co-authored-by: azure-sdk <azuresdk@microsoft.com>

Author: amber-Chen-86

sdk/cognitivelanguage/azure-ai-textanalytics/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Release History
 
+## 6.0.0b2 (2025-11-06)
+
+This version of the client library defaults to the service API version `2025-11-15-preview`.
+
+### Features Added
+
+- Added support for **multiple redaction policies** in a single request.
+- Added **synthetic replacement redaction**, enabling selected PII types (e.g., Person, Email) to be replaced with realistic synthetic values rather than masked.
+- Added **confidence score thresholding**, allowing customers to define minimum confidence levels—globally or per-entity—so that only entities meeting the required confidence are returned.
+- Added **entity validation control** with the `disableEntityValidation` parameter, allowing users to bypass entity validation when needed.
+
 ## 6.0.0b1 (2025-09-11)
 
 This version of the client library defaults to the service API version `2025-05-15-preview`.
@@ -216,7 +227,7 @@ Note: this version will be the last to officially support Python 3.5, future ver
 
 ### Features Added
 
-- Added `catagories_filter` to `RecognizePiiEntitiesAction`
+- Added `categories_filter` to `RecognizePiiEntitiesAction`
 - Added `HealthcareEntityCategory`
 - Added AAD support for the `begin_analyze_healthcare_entities` methods.
 

sdk/cognitivelanguage/azure-ai-textanalytics/README.md

@@ -81,7 +81,8 @@ This table shows the relationship between SDK versions and supported API version
 
 | SDK version  | Supported API version of service  |
 | ------------ | --------------------------------- |
-| 6.0.0b1 - Latest preview release | 3.0, 3.1, 2022-05-01, 2023-04-01, 2024-11-01, 2024-11-15-preview, 2025-05-15-preview (default) |
+| 6.0.0b2 - Latest preview release | 2022-05-01, 2023-04-01, 2024-11-01, 2025-11-15-preview (default) |
+| 6.0.0b1  | 2022-05-01, 2023-04-01, 2024-11-01, 2025-05-15-preview (default) |
 | 5.3.X - Latest stable release | 3.0, 3.1, 2022-05-01, 2023-04-01 (default) |
 | 5.2.X  | 3.0, 3.1, 2022-05-01 (default) |
 | 5.1.0  | 3.0, 3.1 (default) |
@@ -253,14 +254,16 @@ Sample code snippets are provided to illustrate using long-running operations [b
 
 The following section provides several code snippets covering some of the most common Language service tasks, including:
 
-- [Analyze Sentiment](#analyze-sentiment "Analyze sentiment")
-- [Recognize Entities](#recognize-entities "Recognize entities")
-- [Recognize Linked Entities](#recognize-linked-entities "Recognize linked entities")
-- [Recognize PII Entities](#recognize-pii-entities "Recognize pii entities")
-- [Extract Key Phrases](#extract-key-phrases "Extract key phrases")
-- [Detect Language](#detect-language "Detect language")
-- [Healthcare Entities Analysis](#healthcare-entities-analysis "Healthcare Entities Analysis")
-- [Multiple Analysis](#multiple-analysis "Multiple analysis")
+- [Analyze Sentiment][analyze_sentiment_sample]
+- [Recognize Entities][recognize_entities_sample]
+- [Recognize Linked Entities][recognize_linked_entities_sample]
+- [Recognize PII Entities][recognize_pii_entities_sample]
+- [Recognize PII Entities with multiple redaction policies][recognize_pii_entities_with_redaction_policies_sample]
+- [Recognize PII Entities with confidence score][recognize_pii_entities_with_confidence_score_sample]
+- [Extract Key Phrases][extract_key_phrases_sample]
+- [Detect Language][detect_language_sample]
+- [Healthcare Entities Analysis][analyze_healthcare_entities_sample]
+- [Multiple Analysis][analyze_sample]
 - [Custom Entity Recognition][recognize_custom_entities_sample]
 - [Custom Single Label Classification][single_label_classify_sample]
 - [Custom Multi Label Classification][multi_label_classify_sample]
@@ -672,14 +675,10 @@ def sample_detect_language():
     client = TextAnalysisClient(endpoint, credential=credential)
 
     # Build input
-    text_a = (
-        "Sentences in different languages."
-    )
+    text_a = "Sentences in different languages."
 
     body = TextLanguageDetectionInput(
-        text_input=LanguageDetectionTextInput(
-            language_inputs=[LanguageInput(id="A", text=text_a)]
-        )
+        text_input=LanguageDetectionTextInput(language_inputs=[LanguageInput(id="A", text=text_a)])
     )
 
     # Sync (non-LRO) call
@@ -793,12 +792,12 @@ def sample_analyze_healthcare_entities():
                 print(f"Kind: {op_result.kind}")
 
                 hc_result = op_result.results
-                for doc in (hc_result.documents or []):
+                for doc in hc_result.documents or []:
                     print(f"\nDocument ID: {doc.id}")
 
                     # Entities
                     print("Entities:")
-                    for entity in (doc.entities or []):
+                    for entity in doc.entities or []:
                         print(f"  Text: {entity.text}")
                         print(f"  Category: {entity.category}")
                         print(f"  Offset: {entity.offset}")
@@ -812,9 +811,9 @@ def sample_analyze_healthcare_entities():
 
                     # Relations
                     print("Relations:")
-                    for relation in (doc.relations or []):
+                    for relation in doc.relations or []:
                         print(f"  Relation type: {relation.relation_type}")
-                        for rel_entity in (relation.entities or []):
+                        for rel_entity in relation.entities or []:
                             print(f"    Role: {rel_entity.role}")
                             print(f"    Ref: {rel_entity.ref}")
                         print()
@@ -883,9 +882,7 @@ def sample_analyze():
         " offers services for childcare in case you want that."
     )
 
-    text_b = (
-        "Sentences in different languages."
-    )
+    text_b = "Sentences in different languages."
 
     text_c = (
         "That was the best day of my life! We went on a 4 day trip where we stayed at Hotel Foo. They had"
@@ -943,7 +940,7 @@ def sample_analyze():
                     print(f"    Confidence score: {entity.confidence_score}")
                     print()
             for err in action_result.results.errors:
-                print(f'  Error in document: {err.id}!')
+                print(f"  Error in document: {err.id}!")
                 print(f"  Document error: {err.error}")
 
         # --- Key Phrases ---
@@ -955,7 +952,7 @@ def sample_analyze():
                     print(f"    {kp}")
                 print()
             for err in action_result.results.errors:
-                print(f'  Error in document: {err.id}!')
+                print(f"  Error in document: {err.id}!")
                 print(f"  Document error: {err.error}")
 ```
 
@@ -1031,6 +1028,8 @@ Common scenarios
 - Analyze sentiment: [sample_analyze_sentiment.py][analyze_sentiment_sample] ([async version][analyze_sentiment_sample_async])
 - Recognize entities: [sample_recognize_entities.py][recognize_entities_sample] ([async version][recognize_entities_sample_async])
 - Recognize personally identifiable information: [sample_recognize_pii_entities.py][recognize_pii_entities_sample] ([async version][recognize_pii_entities_sample_async])
+- Recognize personally identifiable information(Multiple redaction policies): [sample_recognize_pii_entities_with_redaction_policies.py][recognize_pii_entities_with_redaction_policies_sample] ([async version][recognize_pii_entities_with_redaction_policies_sample_async])
+- Recognize personally identifiable information(Confidence score): [sample_recognize_pii_entities_with_confidence_score.py][recognize_pii_entities_with_confidence_score_sample] ([async version][recognize_pii_entities_with_confidence_score_sample_async])
 - Recognize linked entities: [sample_recognize_linked_entities.py][recognize_linked_entities_sample] ([async version][recognize_linked_entities_sample_async])
 - Extract key phrases: [sample_extract_key_phrases.py][extract_key_phrases_sample] ([async version][extract_key_phrases_sample_async])
 - Detect language: [sample_detect_language.py][detect_language_sample] ([async version][detect_language_sample_async])
@@ -1127,6 +1126,10 @@ This project has adopted the [Microsoft Open Source Code of Conduct][code_of_con
 [recognize_linked_entities_sample_async]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/async_samples/sample_recognize_linked_entities_async.py
 [recognize_pii_entities_sample]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/sample_recognize_pii_entities.py
 [recognize_pii_entities_sample_async]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/async_samples/sample_recognize_pii_entities_async.py
+[recognize_pii_entities_with_redaction_policies_sample]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/sample_recognize_pii_entities_with_redaction_policies.py
+[recognize_pii_entities_with_redaction_policies_sample_async]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/async_samples/sample_recognize_pii_entities_with_redaction_policies_async.py
+[recognize_pii_entities_with_confidence_score_sample]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/sample_recognize_pii_entities_with_confidence_score.py
+[recognize_pii_entities_with_confidence_score_sample_async]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/async_samples/sample_recognize_pii_entities_with_confidence_score_async.py
 [analyze_healthcare_entities_sample]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/sample_analyze_healthcare_entities.py
 [analyze_healthcare_entities_sample_async]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/async_samples/sample_analyze_healthcare_entities_async.py
 [analyze_sample]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-textanalytics/samples/sample_analyze_actions.py

sdk/cognitivelanguage/azure-ai-textanalytics/_metadata.json

@@ -1,3 +1,3 @@
 {
-  "apiVersion": "2025-05-15-preview"
+  "apiVersion": "2025-11-15-preview"
 }

sdk/cognitivelanguage/azure-ai-textanalytics/apiview-properties.json

@@ -10,6 +10,7 @@
         "azure.ai.textanalytics.models.AbstractiveSummary": "Language.Text.AbstractiveSummary",
         "azure.ai.textanalytics.models.AbstractiveSummaryActionResult": "Language.Text.AbstractiveSummaryDocumentResultWithDetectedLanguage",
         "azure.ai.textanalytics.models.BaseMetadata": "Language.Text.BaseMetadata",
+        "azure.ai.textanalytics.models.AddressMetadata": "Language.Text.AddressMetadata",
         "azure.ai.textanalytics.models.AgeMetadata": "Language.Text.AgeMetadata",
         "azure.ai.textanalytics.models.EntityOverlapPolicy": "Language.Text.BaseEntityOverlapPolicy",
         "azure.ai.textanalytics.models.AllowOverlapEntityPolicyType": "Language.Text.AllowOverlapEntityPolicyType",
@@ -28,6 +29,8 @@
         "azure.ai.textanalytics.models.CharacterMaskPolicyType": "Language.Text.CharacterMaskPolicyType",
         "azure.ai.textanalytics.models.ClassificationActionResult": "Language.Text.ClassificationDocumentResultWithDetectedLanguage",
         "azure.ai.textanalytics.models.ClassificationResult": "Language.Text.ClassificationResult",
+        "azure.ai.textanalytics.models.ConfidenceScoreThreshold": "Language.Text.ConfidenceScoreThreshold",
+        "azure.ai.textanalytics.models.ConfidenceScoreThresholdOverride": "Language.Text.ConfidenceScoreThresholdOverride",
         "azure.ai.textanalytics.models.CurrencyMetadata": "Language.Text.CurrencyMetadata",
         "azure.ai.textanalytics.models.CustomEntitiesActionContent": "Language.Text.CustomEntitiesTaskParameters",
         "azure.ai.textanalytics.models.CustomEntitiesLROTask": "Language.Text.CustomEntitiesLROTask",
@@ -125,6 +128,7 @@
         "azure.ai.textanalytics.models.SentimentResult": "Language.Text.SentimentResponse",
         "azure.ai.textanalytics.models.SpeedMetadata": "Language.Text.SpeedMetadata",
         "azure.ai.textanalytics.models.SummaryContext": "Language.Text.SummaryContext",
+        "azure.ai.textanalytics.models.SyntheticReplacementPolicyType": "Language.Text.SyntheticReplacementPolicyType",
         "azure.ai.textanalytics.models.TargetConfidenceScoreLabel": "Language.Text.TargetConfidenceScoreLabel",
         "azure.ai.textanalytics.models.TargetRelation": "Language.Text.TargetRelation",
         "azure.ai.textanalytics.models.TemperatureMetadata": "Language.Text.TemperatureMetadata",

sdk/cognitivelanguage/azure-ai-textanalytics/assets.json

@@ -2,5 +2,5 @@
   "AssetsRepo": "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath": "python",
   "TagPrefix": "python/cognitivelanguage/azure-ai-textanalytics",
-  "Tag": "python/cognitivelanguage/azure-ai-textanalytics_92b0429189"
+  "Tag": "python/cognitivelanguage/azure-ai-textanalytics_104e72feb4"
 }

sdk/cognitivelanguage/azure-ai-textanalytics/azure/ai/textanalytics/_client.py

@@ -40,7 +40,7 @@ class TextAnalysisClient(_TextAnalysisClientOperationsMixin):
     :type credential: ~azure.core.credentials.AzureKeyCredential or
      ~azure.core.credentials.TokenCredential
     :keyword api_version: The API version to use for this operation. Default value is
-     "2025-05-15-preview". Note that overriding this default value may result in unsupported
+     "2025-11-15-preview". Note that overriding this default value may result in unsupported
      behavior.
     :paramtype api_version: str
     :keyword int polling_interval: Default waiting time between two polls for LRO operations if no

sdk/cognitivelanguage/azure-ai-textanalytics/azure/ai/textanalytics/_configuration.py

@@ -31,13 +31,13 @@ class TextAnalysisClientConfiguration:  # pylint: disable=too-many-instance-attr
     :type credential: ~azure.core.credentials.AzureKeyCredential or
      ~azure.core.credentials.TokenCredential
     :keyword api_version: The API version to use for this operation. Default value is
-     "2025-05-15-preview". Note that overriding this default value may result in unsupported
+     "2025-11-15-preview". Note that overriding this default value may result in unsupported
      behavior.
     :paramtype api_version: str
     """
 
     def __init__(self, endpoint: str, credential: Union[AzureKeyCredential, "TokenCredential"], **kwargs: Any) -> None:
-        api_version: str = kwargs.pop("api_version", "2025-05-15-preview")
+        api_version: str = kwargs.pop("api_version", "2025-11-15-preview")
 
         if endpoint is None:
             raise ValueError("Parameter 'endpoint' must not be None.")

sdk/cognitivelanguage/azure-ai-textanalytics/azure/ai/textanalytics/_operations/_operations.py

@@ -5,7 +5,7 @@
 # Code generated by Microsoft (R) Python Code Generator.
 # Changes may cause incorrect behavior and will be lost if the code is regenerated.
 # --------------------------------------------------------------------------
-from collections.abc import MutableMapping # pylint:disable=import-error
+from collections.abc import MutableMapping
 from io import IOBase
 import json
 from typing import Any, Callable, IO, Iterator, Optional, TypeVar, Union, cast, overload
@@ -48,7 +48,7 @@ def build_text_analysis_analyze_text_request(*, show_stats: Optional[bool] = Non
     _params = case_insensitive_dict(kwargs.pop("params", {}) or {})
 
     content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None))
-    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-05-15-preview"))
+    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-11-15-preview"))
     accept = _headers.pop("Accept", "application/json")
 
     # Construct URL
@@ -78,7 +78,7 @@ def build_text_analysis_get_job_status_request(  # pylint: disable=name-too-long
     _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {})
     _params = case_insensitive_dict(kwargs.pop("params", {}) or {})
 
-    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-05-15-preview"))
+    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-11-15-preview"))
     accept = _headers.pop("Accept", "application/json")
 
     # Construct URL
@@ -109,7 +109,7 @@ def build_text_analysis_analyze_text_job_request(**kwargs: Any) -> HttpRequest:
     _params = case_insensitive_dict(kwargs.pop("params", {}) or {})
 
     content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None))
-    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-05-15-preview"))
+    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-11-15-preview"))
     # Construct URL
     _url = "/analyze-text/jobs"
 
@@ -126,7 +126,7 @@ def build_text_analysis_analyze_text_job_request(**kwargs: Any) -> HttpRequest:
 def build_text_analysis_cancel_job_request(job_id: str, **kwargs: Any) -> HttpRequest:
     _params = case_insensitive_dict(kwargs.pop("params", {}) or {})
 
-    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-05-15-preview"))
+    api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2025-11-15-preview"))
     # Construct URL
     _url = "/analyze-text/jobs/{jobId}:cancel"
     path_format_arguments = {

sdk/cognitivelanguage/azure-ai-textanalytics/azure/ai/textanalytics/_patch.py

@@ -151,7 +151,7 @@ def begin_analyze_text_job(
         display_name: Optional[str] = None,
         default_language: Optional[str] = None,
         cancel_after: Optional[float] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> AnalyzeTextLROPoller[ItemPaged["TextActions"]]:
         """Submit a collection of text documents for analysis. Specify one or more unique tasks to be
         executed as a long-running operation.
@@ -223,11 +223,11 @@ def begin_analyze_text_job(  # type: ignore[override]
         display_name: Optional[str] = None,
         default_language: Optional[str] = None,
         cancel_after: Optional[float] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> AnalyzeTextLROPoller[ItemPaged["TextActions"]]:
         """Submit a collection of text documents for analysis. Specify one or more unique tasks to be
         executed as a long-running operation.
-        
+
         :param body: Is either a JSON type or a IO[bytes] type. Required.
         :type body: JSON or IO[bytes]
         :keyword text_input: Contains the input to be analyzed. Required.
@@ -313,7 +313,7 @@ def get_long_running_output(pipeline_response: PipelineResponse[HttpRequest, Htt
                 continuation_token=cont_token,
             )
 
-        initial_kwargs = dict( # pylint:disable=use-dict-literal
+        initial_kwargs = dict(  # pylint:disable=use-dict-literal
             text_input=text_input,
             actions=actions,
             display_name=display_name,

sdk/cognitivelanguage/azure-ai-textanalytics/azure/ai/textanalytics/_utils/model_base.py

@@ -22,7 +22,7 @@
 from datetime import datetime, date, time, timedelta, timezone
 from json import JSONEncoder
 import xml.etree.ElementTree as ET
-from collections.abc import MutableMapping # pylint:disable=import-error
+from collections.abc import MutableMapping
 from typing_extensions import Self
 import isodate
 from azure.core.exceptions import DeserializationError
@@ -640,7 +640,7 @@ def __new__(cls, *args: typing.Any, **kwargs: typing.Any) -> Self:
             cls._attr_to_rest_field: dict[str, _RestField] = dict(attr_to_rest_field.items())
             cls._calculated.add(f"{cls.__module__}.{cls.__qualname__}")
 
-        return super().__new__(cls) # pylint:disable=no-value-for-parameter
+        return super().__new__(cls)
 
     def __init_subclass__(cls, discriminator: typing.Optional[str] = None) -> None:
         for base in cls.__bases__: