spark-nlp 6.1.4__tar.gz → 6.1.5__tar.gz

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.4
+Version: 6.1.5
 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==6.1.4 pyspark==3.3.1
+$ pip install spark-nlp==6.1.5 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 *6.1.4* 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 *6.1.5* 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 | 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 6.1.4 has been tested and is compatible with the following runtimes:
+Spark NLP 6.1.5 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 6.1.4 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.1.5 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/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==6.1.4 pyspark==3.3.1
+$ pip install spark-nlp==6.1.5 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 *6.1.4* 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 *6.1.5* 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 | 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 6.1.4 has been tested and is compatible with the following runtimes:
+Spark NLP 6.1.5 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 6.1.4 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.1.5 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/setup.py

@@ -41,7 +41,7 @@ setup(
     # project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
 
-    version='6.1.4',  # Required
+    version='6.1.5',  # Required
 
     # This is a one-line description or tagline of what your project does. This
     # corresponds to the 'Summary' metadata field:

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/spark_nlp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.4
+Version: 6.1.5
 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==6.1.4 pyspark==3.3.1
+$ pip install spark-nlp==6.1.5 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 *6.1.4* 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 *6.1.5* 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 | 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 6.1.4 has been tested and is compatible with the following runtimes:
+Spark NLP 6.1.5 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 6.1.4 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.1.5 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/spark_nlp.egg-info/SOURCES.txt

@@ -260,6 +260,7 @@ sparknlp/reader/pdf_to_text.py
 sparknlp/reader/reader2doc.py
 sparknlp/reader/reader2image.py
 sparknlp/reader/reader2table.py
+sparknlp/reader/reader_assembler.py
 sparknlp/reader/sparknlp_reader.py
 sparknlp/training/__init__.py
 sparknlp/training/conll.py

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/sparknlp/__init__.py

@@ -66,7 +66,7 @@ sys.modules['com.johnsnowlabs.ml.ai'] = annotator
 annotators = annotator
 embeddings = annotator
 
-__version__ = "6.1.4"
+__version__ = "6.1.5"
 
 
 def start(gpu=False,

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/sparknlp/partition/partition_properties.py

@@ -18,6 +18,23 @@ from pyspark.ml.param import Param, Params, TypeConverters
 
 class HasReaderProperties(Params):
 
+    inputCol = Param(
+        Params._dummy(),
+        "inputCol",
+        "input column name",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setInputCol(self, value):
+        """Sets input column name.
+
+        Parameters
+        ----------
+        value : str
+            Name of the Input Column
+        """
+        return self._set(inputCol=value)
+
     outputCol = Param(
         Params._dummy(),
         "outputCol",
@@ -25,6 +42,16 @@ class HasReaderProperties(Params):
         typeConverter=TypeConverters.toString
     )
 
+    def setOutputCol(self, value):
+        """Sets output column name.
+
+        Parameters
+        ----------
+        value : str
+            Name of the Output Column
+        """
+        return self._set(outputCol=value)
+
     contentPath = Param(
         Params._dummy(),
         "contentPath",
@@ -167,6 +194,56 @@ class HasReaderProperties(Params):
         """
         return self._set(explodeDocs=value)
 
+    flattenOutput = Param(
+        Params._dummy(),
+        "flattenOutput",
+        "If true, output is flattened to plain text with minimal metadata",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setFlattenOutput(self, value):
+        """Sets whether to flatten the output to plain text with minimal metadata.
+
+        ParametersF
+        ----------
+        value : bool
+            If true, output is flattened to plain text with minimal metadata
+        """
+        return self._set(flattenOutput=value)
+
+    titleThreshold = Param(
+        Params._dummy(),
+        "titleThreshold",
+        "Minimum font size threshold for title detection in PDF docs",
+        typeConverter=TypeConverters.toFloat
+    )
+
+    def setTitleThreshold(self, value):
+        """Sets the minimum font size threshold for title detection in PDF documents.
+
+        Parameters
+        ----------
+        value : float
+            Minimum font size threshold for title detection in PDF docs
+        """
+        return self._set(titleThreshold=value)
+
+    outputAsDocument = Param(
+        Params._dummy(),
+        "outputAsDocument",
+        "Whether to return all sentences joined into a single document",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setOutputAsDocument(self, value):
+        """Sets whether to return all sentences joined into a single document.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to return all sentences joined into a single document
+        """
+        return self._set(outputAsDocument=value)
 
 class HasEmailReaderProperties(Params):
 
@@ -683,13 +760,3 @@ class HasPdfProperties(Params):
             True to read as images, False otherwise.
         """
         return self._set(readAsImage=value)
-
-    def setOutputCol(self, value):
-        """Sets output column name.
-
-        Parameters
-        ----------
-        value : str
-            Name of the Output Column
-        """
-        return self._set(outputCol=value)

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/sparknlp/reader/reader2doc.py

@@ -12,7 +12,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 from pyspark import keyword_only
-from pyspark.ml.param import TypeConverters, Params, Param
 
 from sparknlp.common import AnnotatorType
 from sparknlp.internal import AnnotatorTransformer
@@ -69,32 +68,11 @@ class Reader2Doc(
     |[{'document', 15, 38, 'This is a narrative text', {'pageNumber': 1, 'elementType': 'NarrativeText', 'fileName': 'pdf-title.pdf'}, []}]|
     |[{'document', 39, 68, 'This is another narrative text', {'pageNumber': 1, 'elementType': 'NarrativeText', 'fileName': 'pdf-title.pdf'}, []}]|
     +------------------------------------------------------------------------------------------------------------------------------------+
-"""
+    """
 
     name = "Reader2Doc"
-    outputAnnotatorType = AnnotatorType.DOCUMENT
-
-
-    flattenOutput = Param(
-        Params._dummy(),
-        "flattenOutput",
-        "If true, output is flattened to plain text with minimal metadata",
-        typeConverter=TypeConverters.toBoolean
-    )
 
-    titleThreshold = Param(
-        Params._dummy(),
-        "titleThreshold",
-        "Minimum font size threshold for title detection in PDF docs",
-        typeConverter=TypeConverters.toFloat
-    )
-
-    outputAsDocument = Param(
-        Params._dummy(),
-        "outputAsDocument",
-        "Whether to return all sentences joined into a single document",
-        typeConverter=TypeConverters.toBoolean
-    )
+    outputAnnotatorType = AnnotatorType.DOCUMENT
 
     excludeNonText = Param(
         Params._dummy(),
@@ -103,6 +81,16 @@ class Reader2Doc(
         typeConverter=TypeConverters.toBoolean
     )
 
+    def setExcludeNonText(self, value):
+        """Sets whether to exclude non-text content from the output.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to exclude non-text content from the output. Default is False.
+        """
+        return self._set(excludeNonText=value)
+
     @keyword_only
     def __init__(self):
         super(Reader2Doc, self).__init__(classname="com.johnsnowlabs.reader.Reader2Doc")
@@ -117,44 +105,3 @@ class Reader2Doc(
     def setParams(self):
         kwargs = self._input_kwargs
         return self._set(**kwargs)
-
-
-    def setFlattenOutput(self, value):
-        """Sets whether to flatten the output to plain text with minimal metadata.
-
-        ParametersF
-        ----------
-        value : bool
-            If true, output is flattened to plain text with minimal metadata
-        """
-        return self._set(flattenOutput=value)
-
-    def setTitleThreshold(self, value):
-        """Sets the minimum font size threshold for title detection in PDF documents.
-
-        Parameters
-        ----------
-        value : float
-            Minimum font size threshold for title detection in PDF docs
-        """
-        return self._set(titleThreshold=value)
-
-    def setOutputAsDocument(self, value):
-        """Sets whether to return all sentences joined into a single document.
-
-        Parameters
-        ----------
-        value : bool
-            Whether to return all sentences joined into a single document
-        """
-        return self._set(outputAsDocument=value)
-
-    def setExcludeNonText(self, value):
-        """Sets whether to exclude non-text content from the output.
-
-        Parameters
-        ----------
-        value : bool
-            Whether to exclude non-text content from the output. Default is False.
-        """
-        return self._set(excludeNonText=value)

{spark_nlp-6.1.4 → spark_nlp-6.1.5}/sparknlp/reader/reader2table.py

@@ -32,20 +32,6 @@ class Reader2Table(
 
     outputAnnotatorType = AnnotatorType.DOCUMENT
 
-    flattenOutput = Param(
-        Params._dummy(),
-        "flattenOutput",
-        "If true, output is flattened to plain text with minimal metadata",
-        typeConverter=TypeConverters.toBoolean
-    )
-
-    titleThreshold = Param(
-        Params._dummy(),
-        "titleThreshold",
-        "Minimum font size threshold for title detection in PDF docs",
-        typeConverter=TypeConverters.toFloat
-    )
-
     @keyword_only
     def __init__(self):
         super(Reader2Table, self).__init__(classname="com.johnsnowlabs.reader.Reader2Table")
@@ -55,23 +41,3 @@ class Reader2Table(
     def setParams(self):
         kwargs = self._input_kwargs
         return self._set(**kwargs)
-
-    def setFlattenOutput(self, value):
-        """Sets whether to flatten the output to plain text with minimal metadata.
-
-        Parameters
-        ----------
-        value : bool
-            If true, output is flattened to plain text with minimal metadata
-        """
-        return self._set(flattenOutput=value)
-
-    def setTitleThreshold(self, value):
-        """Sets the minimum font size threshold for title detection in PDF documents.
-
-        Parameters
-        ----------
-        value : float
-            Minimum font size threshold for title detection in PDF docs
-        """
-        return self._set(titleThreshold=value)

spark_nlp-6.1.5/sparknlp/reader/reader_assembler.py

@@ -0,0 +1,159 @@
+#  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 import keyword_only
+
+from sparknlp.common import AnnotatorType
+from sparknlp.internal import AnnotatorTransformer
+from sparknlp.partition.partition_properties import *
+
+class ReaderAssembler(
+    AnnotatorTransformer,
+    HasReaderProperties,
+    HasHTMLReaderProperties,
+    HasEmailReaderProperties,
+    HasExcelReaderProperties,
+    HasPowerPointProperties,
+    HasTextReaderProperties,
+    HasPdfProperties
+):
+    """
+    The ReaderAssembler annotator provides a unified interface for combining multiple Spark NLP
+    readers (such as Reader2Doc, Reader2Table, and Reader2Image) into a single, configurable
+    component. It automatically orchestrates the execution of different readers based on input type,
+    configured priorities, and fallback strategies allowing you to handle diverse content formats
+    without manually chaining multiple readers in your pipeline.
+
+    ReaderAssembler simplifies the process of building flexible pipelines capable of ingesting and
+    processing documents, tables, and images in a consistent way. It handles reader selection,
+    ordering, and fault-tolerance internally, ensuring that pipelines remain concise, robust, and
+    easy to maintain.
+
+    Examples
+    --------
+    >>> from johnsnowlabs.reader import ReaderAssembler
+    >>> from pyspark.ml import Pipeline
+    >>>
+    >>> reader_assembler = ReaderAssembler() \\
+    ...     .setContentType("text/html") \\
+    ...     .setContentPath("/table-image.html") \\
+    ...     .setOutputCol("document")
+    >>>
+    >>> pipeline = Pipeline(stages=[reader_assembler])
+    >>> pipeline_model = pipeline.fit(empty_data_set)
+    >>> result_df = pipeline_model.transform(empty_data_set)
+    >>>
+    >>> result_df.show()
+    +--------+--------------------+--------------------+--------------------+---------+
+    |fileName|       document_text|      document_table|      document_image|exception|
+    +--------+--------------------+--------------------+--------------------+---------+
+    |    null|[{'document', 0, 26...|[{'document', 0, 50...|[{'image', , 5, 5, ...|     null|
+    +--------+--------------------+--------------------+--------------------+---------+
+
+    This annotator is especially useful when working with heterogeneous input data — for example,
+    when a dataset includes PDFs, spreadsheets, and images — allowing Spark NLP to automatically
+    invoke the appropriate reader for each file type while preserving a unified schema in the output.
+"""
+
+
+    name = 'ReaderAssembler'
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    excludeNonText = Param(
+        Params._dummy(),
+        "excludeNonText",
+        "Whether to exclude non-text content from the output. Default is False.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    userMessage = Param(
+        Params._dummy(),
+        "userMessage",
+        "Custom user message.",
+        typeConverter=TypeConverters.toString
+    )
+
+    promptTemplate = Param(
+        Params._dummy(),
+        "promptTemplate",
+        "Format of the output prompt.",
+        typeConverter=TypeConverters.toString
+    )
+
+    customPromptTemplate = Param(
+        Params._dummy(),
+        "customPromptTemplate",
+        "Custom prompt template for image models.",
+        typeConverter=TypeConverters.toString
+    )
+
+    @keyword_only
+    def __init__(self):
+        super(ReaderAssembler, self).__init__(classname="com.johnsnowlabs.reader.ReaderAssembler")
+        self._setDefault(contentType="",
+                         explodeDocs=False,
+                         userMessage="Describe this image",
+                         promptTemplate="qwen2vl-chat",
+                         readAsImage=True,
+                         customPromptTemplate="",
+                         ignoreExceptions=True,
+                         flattenOutput=False,
+                         titleThreshold=18)
+
+
+    @keyword_only
+    def setParams(self):
+        kwargs = self._input_kwargs
+        return self._set(**kwargs)
+
+    def setExcludeNonText(self, value):
+        """Sets whether to exclude non-text content from the output.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to exclude non-text content from the output. Default is False.
+        """
+        return self._set(excludeNonText=value)
+
+    def setUserMessage(self, value: str):
+        """Sets custom user message.
+
+        Parameters
+        ----------
+        value : str
+            Custom user message to include.
+        """
+        return self._set(userMessage=value)
+
+    def setPromptTemplate(self, value: str):
+        """Sets format of the output prompt.
+
+        Parameters
+        ----------
+        value : str
+            Prompt template format.
+        """
+        return self._set(promptTemplate=value)
+
+    def setCustomPromptTemplate(self, value: str):
+        """Sets custom prompt template for image models.
+
+        Parameters
+        ----------
+        value : str
+            Custom prompt template string.
+        """
+        return self._set(customPromptTemplate=value)