spark-nlp 6.1.5__tar.gz → 6.2.0__tar.gz

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.5
+Version: 6.2.0
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs
@@ -102,7 +102,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==6.1.5 pyspark==3.3.1
+$ pip install spark-nlp==6.2.0 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -168,7 +168,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *6.1.5* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *6.2.0* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -198,7 +198,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.1.5 has been tested and is compatible with the following runtimes:
+Spark NLP 6.2.0 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -216,7 +216,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.1.5 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.2.0 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|
@@ -306,7 +306,7 @@ Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integr
 Need more **examples**? Check out our dedicated [Spark NLP Examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
 repository to showcase all Spark NLP use cases!
 
-Also, don't forget to check [Spark NLP in Action](https://sparknlp.org/demo) built by Streamlit.
+Also, don't forget to check [Spark NLP in Action](https://sparknlp.org/demos) built by Streamlit.
 
 #### All examples: [spark-nlp/examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
 

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/README.md

@@ -63,7 +63,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==6.1.5 pyspark==3.3.1
+$ pip install spark-nlp==6.2.0 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -129,7 +129,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *6.1.5* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *6.2.0* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -159,7 +159,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.1.5 has been tested and is compatible with the following runtimes:
+Spark NLP 6.2.0 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -177,7 +177,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.1.5 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.2.0 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|
@@ -267,7 +267,7 @@ Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integr
 Need more **examples**? Check out our dedicated [Spark NLP Examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
 repository to showcase all Spark NLP use cases!
 
-Also, don't forget to check [Spark NLP in Action](https://sparknlp.org/demo) built by Streamlit.
+Also, don't forget to check [Spark NLP in Action](https://sparknlp.org/demos) built by Streamlit.
 
 #### All examples: [spark-nlp/examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
 

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/setup.py

@@ -41,7 +41,7 @@ setup(
     # project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
 
-    version='6.1.5',  # Required
+    version='6.2.0',  # Required
 
     # This is a one-line description or tagline of what your project does. This
     # corresponds to the 'Summary' metadata field:

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/spark_nlp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.5
+Version: 6.2.0
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs
@@ -102,7 +102,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==6.1.5 pyspark==3.3.1
+$ pip install spark-nlp==6.2.0 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -168,7 +168,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *6.1.5* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *6.2.0* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -198,7 +198,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.1.5 has been tested and is compatible with the following runtimes:
+Spark NLP 6.2.0 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -216,7 +216,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.1.5 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.2.0 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|
@@ -306,7 +306,7 @@ Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integr
 Need more **examples**? Check out our dedicated [Spark NLP Examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
 repository to showcase all Spark NLP use cases!
 
-Also, don't forget to check [Spark NLP in Action](https://sparknlp.org/demo) built by Streamlit.
+Also, don't forget to check [Spark NLP in Action](https://sparknlp.org/demos) built by Streamlit.
 
 #### All examples: [spark-nlp/examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
 

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/spark_nlp.egg-info/SOURCES.txt

@@ -231,6 +231,7 @@ sparknlp/common/annotator_approach.py
 sparknlp/common/annotator_model.py
 sparknlp/common/annotator_properties.py
 sparknlp/common/annotator_type.py
+sparknlp/common/completion_post_processing.py
 sparknlp/common/coverage_result.py
 sparknlp/common/match_strategy.py
 sparknlp/common/properties.py

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/__init__.py

@@ -66,7 +66,7 @@ sys.modules['com.johnsnowlabs.ml.ai'] = annotator
 annotators = annotator
 embeddings = annotator
 
-__version__ = "6.1.5"
+__version__ = "6.2.0"
 
 
 def start(gpu=False,

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/annotator/document_normalizer.py

@@ -122,6 +122,21 @@ class DocumentNormalizer(AnnotatorModel):
                      "file encoding to apply on normalized documents",
                      typeConverter=TypeConverters.toString)
 
+    presetPattern = Param(
+        Params._dummy(),
+        "presetPattern",
+        "Selects a single text cleaning function from the functional presets (e.g., 'CLEAN_BULLETS', 'CLEAN_DASHES', etc.).",
+        typeConverter=TypeConverters.toString
+    )
+
+    autoMode = Param(
+        Params._dummy(),
+        "autoMode",
+        "Enables a predefined cleaning mode combining multiple text cleaner functions (e.g., 'light_clean', 'document_clean', 'html_clean', 'full_auto').",
+        typeConverter=TypeConverters.toString
+    )
+
+
     @keyword_only
     def __init__(self):
         super(DocumentNormalizer, self).__init__(classname="com.johnsnowlabs.nlp.annotators.DocumentNormalizer")
@@ -197,3 +212,24 @@ class DocumentNormalizer(AnnotatorModel):
             File encoding to apply on normalized documents, by default "UTF-8"
         """
         return self._set(encoding=value)
+
+    def setPresetPattern(self, value):
+        """Sets a single text cleaning preset pattern.
+
+        Parameters
+        ----------
+        value : str
+            Preset cleaning pattern name, e.g., 'CLEAN_BULLETS', 'CLEAN_DASHES'.
+        """
+        return self._set(presetPattern=value)
+
+
+    def setAutoMode(self, value):
+        """Sets an automatic text cleaning mode using predefined groups of cleaning functions.
+
+        Parameters
+        ----------
+        value : str
+            Auto cleaning mode, e.g., 'light_clean', 'document_clean', 'social_clean', 'html_clean', 'full_auto'.
+        """
+        return self._set(autoMode=value)

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/annotator/embeddings/auto_gguf_embeddings.py

@@ -532,3 +532,8 @@ class AutoGGUFEmbeddings(AnnotatorModel, HasBatchedAnnotate):
         return ResourceDownloader.downloadModel(
             AutoGGUFEmbeddings, name, lang, remote_loc
         )
+
+    def close(self):
+        """Closes the llama.cpp model backend freeing resources. The model is reloaded when used again.
+        """
+        self._java_obj.close()

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/annotator/er/entity_ruler.py

@@ -215,6 +215,20 @@ class EntityRulerModel(AnnotatorModel, HasStorageModel):
 
     outputAnnotatorType = AnnotatorType.CHUNK
 
+    autoMode = Param(
+        Params._dummy(),
+        "autoMode",
+        "Enable built-in regex presets that combine related entity patterns (e.g., 'communication_entities', 'network_entities', 'media_entities', etc.).",
+        typeConverter=TypeConverters.toString
+    )
+
+    extractEntities = Param(
+        Params._dummy(),
+        "extractEntities",
+        "List of entity types to extract. If not set, all entities in the active autoMode or from regexPatterns are used.",
+        typeConverter=TypeConverters.toListString
+    )
+
     def __init__(self, classname="com.johnsnowlabs.nlp.annotators.er.EntityRulerModel", java_model=None):
         super(EntityRulerModel, self).__init__(
             classname=classname,
@@ -230,3 +244,24 @@ class EntityRulerModel(AnnotatorModel, HasStorageModel):
     def loadStorage(path, spark, storage_ref):
         HasStorageModel.loadStorages(path, spark, storage_ref, EntityRulerModel.database)
 
+
+    def setAutoMode(self, value):
+        """Sets the auto mode for predefined regex entity groups.
+
+        Parameters
+        ----------
+        value : str
+            Name of the auto mode to activate (e.g., 'communication_entities', 'network_entities', etc.)
+        """
+        return self._set(autoMode=value)
+
+
+    def setExtractEntities(self, value):
+        """Sets specific entities to extract, filtering only those defined in regexPatterns or autoMode.
+
+        Parameters
+        ----------
+        value : list[str]
+            List of entity names to extract, e.g., ['EMAIL_ADDRESS_PATTERN', 'IPV4_PATTERN'].
+        """
+        return self._set(extractEntities=value)

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/annotator/seq2seq/auto_gguf_model.py

@@ -12,12 +12,10 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 """Contains classes for the AutoGGUFModel."""
-from typing import List, Dict
-
 from sparknlp.common import *
 
 
-class AutoGGUFModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
+class AutoGGUFModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties, CompletionPostProcessing):
     """
     Annotator that uses the llama.cpp library to generate text completions with large language
     models.
@@ -243,7 +241,6 @@ class AutoGGUFModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
     inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
     outputAnnotatorType = AnnotatorType.DOCUMENT
 
-
     @keyword_only
     def __init__(self, classname="com.johnsnowlabs.nlp.annotators.seq2seq.AutoGGUFModel", java_model=None):
         super(AutoGGUFModel, self).__init__(
@@ -300,3 +297,8 @@ class AutoGGUFModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
         """
         from sparknlp.pretrained import ResourceDownloader
         return ResourceDownloader.downloadModel(AutoGGUFModel, name, lang, remote_loc)
+
+    def close(self):
+        """Closes the llama.cpp model backend freeing resources. The model is reloaded when used again.
+        """
+        self._java_obj.close()

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/annotator/seq2seq/auto_gguf_reranker.py

@@ -327,3 +327,8 @@ class AutoGGUFReranker(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties
         """
         from sparknlp.pretrained import ResourceDownloader
         return ResourceDownloader.downloadModel(AutoGGUFReranker, name, lang, remote_loc)
+
+    def close(self):
+        """Closes the llama.cpp model backend freeing resources. The model is reloaded when used again.
+        """
+        self._java_obj.close()

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/annotator/seq2seq/auto_gguf_vision_model.py

@@ -15,7 +15,7 @@
 from sparknlp.common import *
 
 
-class AutoGGUFVisionModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
+class AutoGGUFVisionModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties, CompletionPostProcessing):
     """Multimodal annotator that uses the llama.cpp library to generate text completions with large
     language models. It supports ingesting images for captioning.
 
@@ -329,3 +329,8 @@ class AutoGGUFVisionModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppPropert
         """
         from sparknlp.pretrained import ResourceDownloader
         return ResourceDownloader.downloadModel(AutoGGUFVisionModel, name, lang, remote_loc)
+
+    def close(self):
+        """Closes the llama.cpp model backend freeing resources. The model is reloaded when used again.
+        """
+        self._java_obj.close()

{spark_nlp-6.1.5 → spark_nlp-6.2.0}/sparknlp/common/__init__.py

@@ -23,3 +23,4 @@ from sparknlp.common.storage import *
 from sparknlp.common.utils import *
 from sparknlp.common.annotator_type import *
 from sparknlp.common.match_strategy import *
+from sparknlp.common.completion_post_processing import *

spark_nlp-6.2.0/sparknlp/common/completion_post_processing.py

@@ -0,0 +1,37 @@
+#  Copyright 2017-2025 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+from pyspark.ml.param import Param, Params, TypeConverters
+
+
+class CompletionPostProcessing:
+    removeThinkingTag = Param(
+        Params._dummy(),
+        "removeThinkingTag",
+        "Set a thinking tag (e.g. think) to be removed from output. Will match <TAG>...</TAG>",
+        typeConverter=TypeConverters.toString,
+    )
+
+    def setRemoveThinkingTag(self, value: str):
+        """Set a thinking tag (e.g. `think`) to be removed from output.
+        Will produce the regex: `(?s)<$TAG>.+?</$TAG>`
+        """
+        self._set(removeThinkingTag=value)
+        return self
+
+    def getRemoveThinkingTag(self):
+        """Get the thinking tag to be removed from output."""
+        value = None
+        if self.removeThinkingTag in self._paramMap:
+            value = self._paramMap[self.removeThinkingTag]
+        return value