spark-nlp 6.1.3__py2.py3-none-any.whl → 6.1.4__py2.py3-none-any.whl

{spark_nlp-6.1.3.dist-info → spark_nlp-6.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.3
+Version: 6.1.4
 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==6.1.3 pyspark==3.3.1
+$ pip install spark-nlp==6.1.4 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 *6.1.3* 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 *6.1.4* 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 | 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 6.1.3 has been tested and is compatible with the following runtimes:
+Spark NLP 6.1.4 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 6.1.3 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.1.4 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.1.3.dist-info → spark_nlp-6.1.4.dist-info}/RECORD

@@ -3,7 +3,7 @@ com/johnsnowlabs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 com/johnsnowlabs/ml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 com/johnsnowlabs/ml/ai/__init__.py,sha256=YQiK2M7U4d8y5irPy_HB8ae0mSpqS9583MH44pnKJXc,295
 com/johnsnowlabs/nlp/__init__.py,sha256=DPIVXtONO5xXyOk-HB0-sNiHAcco17NN13zPS_6Uw8c,294
-sparknlp/__init__.py,sha256=UR0dRykX67j-Ksuzk5Xe-Mod5qCK24iBjHHa0omOp2w,13814
+sparknlp/__init__.py,sha256=LcfC7bWeae5XgjWbNbWH94LlJkBon5dA8fYnb_2NyGc,13814
 sparknlp/annotation.py,sha256=I5zOxG5vV2RfPZfqN9enT1i4mo6oBcn3Lrzs37QiOiA,5635
 sparknlp/annotation_audio.py,sha256=iRV_InSVhgvAwSRe9NTbUH9v6OGvTM-FPCpSAKVu0mE,1917
 sparknlp/annotation_image.py,sha256=xhCe8Ko-77XqWVuuYHFrjKqF6zPd8Z-RY_rmZXNwCXU,2547
@@ -241,7 +241,7 @@ sparknlp/logging/__init__.py,sha256=DoROFF5KLZe4t4Q-OHxqk1nhqbw9NQ-wb64y8icNwgw,
 sparknlp/logging/comet.py,sha256=_ZBi9-hlilCAnd4lvdYMWiq4Vqsppv8kow3k0cf-NG4,15958
 sparknlp/partition/__init__.py,sha256=L0w-yv_HnnvoKlSX5MzI2GKHW3RLLfGyq8bgWYVeKjU,749
 sparknlp/partition/partition.py,sha256=GXEAUvOea04Vc_JK0z112cAKFrJ4AEpjLJ8xlzZt6Kw,8551
-sparknlp/partition/partition_properties.py,sha256=xhAMhlsTBg-WS6KWDyVbRPwO7IzpowVVhJNR-ZGhvdo,9520
+sparknlp/partition/partition_properties.py,sha256=2tGdIv1NaJNaux_TTskKQHnARAwBkFctaqCcNw21Wr8,19920
 sparknlp/partition/partition_transformer.py,sha256=lRR1h-IMlHR8M0VeB50SbU39GHHF5PgMaJ42qOriS6A,6855
 sparknlp/pretrained/__init__.py,sha256=GV-x9UBK8F2_IR6zYatrzFcVJtkSUIMbxqWsxRUePmQ,793
 sparknlp/pretrained/pretrained_pipeline.py,sha256=lquxiaABuA68Rmu7csamJPqBoRJqMUO0oNHsmEZDAIs,5740
@@ -250,8 +250,9 @@ sparknlp/pretrained/utils.py,sha256=T1MrvW_DaWk_jcOjVLOea0NMFE9w8fe0ZT_5urZ_nEY,
 sparknlp/reader/__init__.py,sha256=-Toj3AIBki-zXPpV8ezFTI2LX1yP_rK2bhpoa8nBkTw,685
 sparknlp/reader/enums.py,sha256=MNGug9oJ1BBLM1Pbske13kAabalDzHa2kucF5xzFpHs,770
 sparknlp/reader/pdf_to_text.py,sha256=eWw-cwjosmcSZ9eHso0F5QQoeGBBnwsOhzhCXXvMjZA,7169
-sparknlp/reader/reader2doc.py,sha256=8x1tvx7Hj2J4xpyRiCUvrG-kmOPBvIE8K1tJZY-e0Xw,8200
-sparknlp/reader/reader2table.py,sha256=GC6Yz0gQ83S6XKOi329TUNQuAvLrBxysqDkDRZPvcYA,4759
+sparknlp/reader/reader2doc.py,sha256=87aMk8-_1NHd3bB1rxw56BQMJc6mGgtnYGXwKw2uCmU,5916
+sparknlp/reader/reader2image.py,sha256=k3gb4LEiqDV-pnD-HEaA1KHoAxXmoYys2Y817i1yvP0,4557
+sparknlp/reader/reader2table.py,sha256=pIR9r6NapUV4xdsFecadWlKTSJmRMAm36eqM9aXf13k,2416
 sparknlp/reader/sparknlp_reader.py,sha256=MJs8v_ECYaV1SOabI1L_2MkVYEDVImtwgbYypO7DJSY,20623
 sparknlp/training/__init__.py,sha256=qREi9u-5Vc2VjpL6-XZsyvu5jSEIdIhowW7_kKaqMqo,852
 sparknlp/training/conll.py,sha256=wKBiSTrjc6mjsl7Nyt6B8f4yXsDJkZb-sn8iOjix9cE,6961
@@ -283,7 +284,7 @@ sparknlp/training/_tf_graph_builders_1x/ner_dl/dataset_encoder.py,sha256=R4yHFN3
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model.py,sha256=EoCSdcIjqQ3wv13MAuuWrKV8wyVBP0SbOEW41omHlR0,23189
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model_saver.py,sha256=k5CQ7gKV6HZbZMB8cKLUJuZxoZWlP_DFWdZ--aIDwsc,2356
 sparknlp/training/_tf_graph_builders_1x/ner_dl/sentence_grouper.py,sha256=pAxjWhjazSX8Vg0MFqJiuRVw1IbnQNSs-8Xp26L4nko,870
-spark_nlp-6.1.3.dist-info/METADATA,sha256=U4Fb5wRd8Ql6BULfRwQSE6Pa77wsLwOGwTk-s038YuI,19774
-spark_nlp-6.1.3.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
-spark_nlp-6.1.3.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
-spark_nlp-6.1.3.dist-info/RECORD,,
+spark_nlp-6.1.4.dist-info/METADATA,sha256=CqRyNEZCA_8F_J5vHG4GUZXRiavXyfb3tPMTStidr4c,19774
+spark_nlp-6.1.4.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
+spark_nlp-6.1.4.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
+spark_nlp-6.1.4.dist-info/RECORD,,

sparknlp/__init__.py

@@ -66,7 +66,7 @@ sys.modules['com.johnsnowlabs.ml.ai'] = annotator
 annotators = annotator
 embeddings = annotator
 
-__version__ = "6.1.3"
+__version__ = "6.1.4"
 
 
 def start(gpu=False,

sparknlp/partition/partition_properties.py

@@ -13,8 +13,159 @@
 #  limitations under the License.
 """Contains classes for partition properties used in reading various document types."""
 from typing import Dict
+from pyspark.ml.param import Param, Params, TypeConverters
 
-from pyspark.ml.param import TypeConverters, Params, Param
+
+class HasReaderProperties(Params):
+
+    outputCol = Param(
+        Params._dummy(),
+        "outputCol",
+        "output column name",
+        typeConverter=TypeConverters.toString
+    )
+
+    contentPath = Param(
+        Params._dummy(),
+        "contentPath",
+        "Path to the content source.",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setContentPath(self, value: str):
+        """Sets content path.
+
+        Parameters
+        ----------
+        value : str
+            Path to the content source.
+        """
+        return self._set(contentPath=value)
+
+    contentType = Param(
+        Params._dummy(),
+        "contentType",
+        "Set the content type to load following MIME specification.",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setContentType(self, value: str):
+        """Sets content type following MIME specification.
+
+        Parameters
+        ----------
+        value : str
+            Content type string (MIME format).
+        """
+        return self._set(contentType=value)
+
+    storeContent = Param(
+        Params._dummy(),
+        "storeContent",
+        "Whether to include the raw file content in the output DataFrame "
+        "as a separate 'content' column, alongside the structured output.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setStoreContent(self, value: bool):
+        """Sets whether to store raw file content.
+
+        Parameters
+        ----------
+        value : bool
+            True to include raw file content, False otherwise.
+        """
+        return self._set(storeContent=value)
+
+    titleFontSize = Param(
+        Params._dummy(),
+        "titleFontSize",
+        "Minimum font size threshold used as part of heuristic rules to detect "
+        "title elements based on formatting (e.g., bold, centered, capitalized).",
+        typeConverter=TypeConverters.toInt
+    )
+
+    def setTitleFontSize(self, value: int):
+        """Sets minimum font size for detecting titles.
+
+        Parameters
+        ----------
+        value : int
+            Minimum font size threshold for title detection.
+        """
+        return self._set(titleFontSize=value)
+
+    inferTableStructure = Param(
+        Params._dummy(),
+        "inferTableStructure",
+        "Whether to generate an HTML table representation from structured table content. "
+        "When enabled, a full <table> element is added alongside cell-level elements, "
+        "based on row and column layout.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setInferTableStructure(self, value: bool):
+        """Sets whether to infer table structure.
+
+        Parameters
+        ----------
+        value : bool
+            True to generate HTML table representation, False otherwise.
+        """
+        return self._set(inferTableStructure=value)
+
+    includePageBreaks = Param(
+        Params._dummy(),
+        "includePageBreaks",
+        "Whether to detect and tag content with page break metadata. "
+        "In Word documents, this includes manual and section breaks. "
+        "In Excel files, this includes page breaks based on column boundaries.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setIncludePageBreaks(self, value: bool):
+        """Sets whether to include page break metadata.
+
+        Parameters
+        ----------
+        value : bool
+            True to detect and tag page breaks, False otherwise.
+        """
+        return self._set(includePageBreaks=value)
+
+    ignoreExceptions = Param(
+        Params._dummy(),
+        "ignoreExceptions",
+        "Whether to ignore exceptions during processing.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setIgnoreExceptions(self, value: bool):
+        """Sets whether to ignore exceptions during processing.
+
+        Parameters
+        ----------
+        value : bool
+            True to ignore exceptions, False otherwise.
+        """
+        return self._set(ignoreExceptions=value)
+
+    explodeDocs = Param(
+        Params._dummy(),
+        "explodeDocs",
+        "Whether to explode the documents into separate rows.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setExplodeDocs(self, value: bool):
+        """Sets whether to explode the documents into separate rows.
+
+        Parameters
+        ----------
+        value : bool
+            True to split documents into multiple rows, False to keep them in one row.
+        """
+        return self._set(explodeDocs=value)
 
 
 class HasEmailReaderProperties(Params):
@@ -144,6 +295,28 @@ class HasHTMLReaderProperties(Params):
         self._call_java("setHeadersPython", headers)
         return self
 
+    outputFormat = Param(
+        Params._dummy(),
+        "outputFormat",
+        "Output format for the table content. Options are 'plain-text' or 'html-table'. Default is 'json-table'.",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setOutputFormat(self, value: str):
+        """Sets output format for the table content.
+
+        Options
+        -------
+        - 'plain-text'
+        - 'html-table'
+        - 'json-table' (default)
+
+        Parameters
+        ----------
+        value : str
+            Output format for the table content.
+        """
+        return self._set(outputFormat=value)
 
 class HasPowerPointProperties(Params):
 
@@ -317,3 +490,206 @@ class HasChunkerProperties(Params):
 
     def setOverlapAll(self, value):
         return self._set(overlapAll=value)
+
+
+from pyspark.ml.param import Param, Params, TypeConverters
+
+
+class HasPdfProperties(Params):
+
+    pageNumCol = Param(
+        Params._dummy(),
+        "pageNumCol",
+        "Page number output column name.",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setPageNumCol(self, value: str):
+        """Sets page number output column name.
+
+        Parameters
+        ----------
+        value : str
+            Name of the column for page numbers.
+        """
+        return self._set(pageNumCol=value)
+
+    originCol = Param(
+        Params._dummy(),
+        "originCol",
+        "Input column name with original path of file.",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setOriginCol(self, value: str):
+        """Sets input column with original file path.
+
+        Parameters
+        ----------
+        value : str
+            Column name that stores the file path.
+        """
+        return self._set(originCol=value)
+
+    partitionNum = Param(
+        Params._dummy(),
+        "partitionNum",
+        "Number of partitions.",
+        typeConverter=TypeConverters.toInt
+    )
+
+    def setPartitionNum(self, value: int):
+        """Sets number of partitions.
+
+        Parameters
+        ----------
+        value : int
+            Number of partitions to use.
+        """
+        return self._set(partitionNum=value)
+
+    storeSplittedPdf = Param(
+        Params._dummy(),
+        "storeSplittedPdf",
+        "Force to store bytes content of splitted pdf.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setStoreSplittedPdf(self, value: bool):
+        """Sets whether to store byte content of split PDF pages.
+
+        Parameters
+        ----------
+        value : bool
+            True to store PDF page bytes, False otherwise.
+        """
+        return self._set(storeSplittedPdf=value)
+
+    splitPage = Param(
+        Params._dummy(),
+        "splitPage",
+        "Enable/disable splitting per page to identify page numbers and improve performance.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setSplitPage(self, value: bool):
+        """Sets whether to split PDF into pages.
+
+        Parameters
+        ----------
+        value : bool
+            True to split per page, False otherwise.
+        """
+        return self._set(splitPage=value)
+
+    onlyPageNum = Param(
+        Params._dummy(),
+        "onlyPageNum",
+        "Extract only page numbers.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setOnlyPageNum(self, value: bool):
+        """Sets whether to extract only page numbers.
+
+        Parameters
+        ----------
+        value : bool
+            True to extract only page numbers, False otherwise.
+        """
+        return self._set(onlyPageNum=value)
+
+    textStripper = Param(
+        Params._dummy(),
+        "textStripper",
+        "Text stripper type used for output layout and formatting.",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setTextStripper(self, value: str):
+        """Sets text stripper type.
+
+        Parameters
+        ----------
+        value : str
+            Text stripper type for layout and formatting.
+        """
+        return self._set(textStripper=value)
+
+    sort = Param(
+        Params._dummy(),
+        "sort",
+        "Enable/disable sorting content on the page.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setSort(self, value: bool):
+        """Sets whether to sort content on the page.
+
+        Parameters
+        ----------
+        value : bool
+            True to sort content, False otherwise.
+        """
+        return self._set(sort=value)
+
+    extractCoordinates = Param(
+        Params._dummy(),
+        "extractCoordinates",
+        "Force extract coordinates of text.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setExtractCoordinates(self, value: bool):
+        """Sets whether to extract coordinates of text.
+
+        Parameters
+        ----------
+        value : bool
+            True to extract coordinates, False otherwise.
+        """
+        return self._set(extractCoordinates=value)
+
+    normalizeLigatures = Param(
+        Params._dummy(),
+        "normalizeLigatures",
+        "Whether to convert ligature chars such as 'fl' into its corresponding chars (e.g., {'f', 'l'}).",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setNormalizeLigatures(self, value: bool):
+        """Sets whether to normalize ligatures (e.g., fl → f + l).
+
+        Parameters
+        ----------
+        value : bool
+            True to normalize ligatures, False otherwise.
+        """
+        return self._set(normalizeLigatures=value)
+
+    readAsImage = Param(
+        Params._dummy(),
+        "readAsImage",
+        "Read PDF pages as images.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setReadAsImage(self, value: bool):
+        """Sets whether to read PDF pages as images.
+
+        Parameters
+        ----------
+        value : bool
+            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)

sparknlp/reader/reader2doc.py

@@ -21,9 +21,10 @@ from sparknlp.partition.partition_properties import *
 
 class Reader2Doc(
     AnnotatorTransformer,
+    HasReaderProperties,
+    HasHTMLReaderProperties,
     HasEmailReaderProperties,
     HasExcelReaderProperties,
-    HasHTMLReaderProperties,
     HasPowerPointProperties,
     HasTextReaderProperties
 ):
@@ -73,33 +74,6 @@ class Reader2Doc(
     name = "Reader2Doc"
     outputAnnotatorType = AnnotatorType.DOCUMENT
 
-    contentPath = Param(
-        Params._dummy(),
-        "contentPath",
-        "contentPath path to files to read",
-        typeConverter=TypeConverters.toString
-    )
-
-    outputCol = Param(
-        Params._dummy(),
-        "outputCol",
-        "output column name",
-        typeConverter=TypeConverters.toString
-    )
-
-    contentType = Param(
-        Params._dummy(),
-        "contentType",
-        "Set the content type to load following MIME specification",
-        typeConverter=TypeConverters.toString
-    )
-
-    explodeDocs = Param(
-        Params._dummy(),
-        "explodeDocs",
-        "whether to explode the documents into separate rows",
-        typeConverter=TypeConverters.toBoolean
-    )
 
     flattenOutput = Param(
         Params._dummy(),
@@ -115,13 +89,6 @@ class Reader2Doc(
         typeConverter=TypeConverters.toFloat
     )
 
-    outputFormat = Param(
-        Params._dummy(),
-        "outputFormat",
-        "Output format for the table content. Options are 'plain-text' or 'html-table'. Default is 'json-table'.",
-        typeConverter=TypeConverters.toString
-    )
-
     outputAsDocument = Param(
         Params._dummy(),
         "outputAsDocument",
@@ -151,47 +118,6 @@ class Reader2Doc(
         kwargs = self._input_kwargs
         return self._set(**kwargs)
 
-    def setContentPath(self, value):
-        """Sets content path.
-
-        Parameters
-        ----------
-        value : str
-            contentPath path to files to read
-        """
-        return self._set(contentPath=value)
-
-    def setContentType(self, value):
-        """
-        Set the content type to load following MIME specification
-
-        Parameters
-        ----------
-        value : str
-            content type to load following MIME specification
-        """
-        return self._set(contentType=value)
-
-    def setExplodeDocs(self, value):
-        """Sets whether to explode the documents into separate rows.
-
-
-        Parameters
-        ----------
-        value : boolean
-        Whether to explode the documents into separate rows
-        """
-        return self._set(explodeDocs=value)
-
-    def setOutputCol(self, value):
-        """Sets output column name.
-
-        Parameters
-        ----------
-        value : str
-            Name of the Output Column
-        """
-        return self._set(outputCol=value)
 
     def setFlattenOutput(self, value):
         """Sets whether to flatten the output to plain text with minimal metadata.
@@ -213,16 +139,6 @@ class Reader2Doc(
         """
         return self._set(titleThreshold=value)
 
-    def setOutputFormat(self, value):
-        """Sets the output format for the table content.
-
-        Parameters
-        ----------
-        value : str
-            Output format for the table content. Options are 'plain-text' or 'html-table'. Default is 'json-table'.
-        """
-        return self._set(outputFormat=value)
-
     def setOutputAsDocument(self, value):
         """Sets whether to return all sentences joined into a single document.
 

sparknlp/reader/reader2image.py

@@ -0,0 +1,136 @@
+#  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 pyspark.ml.param import TypeConverters, Params, Param
+
+from sparknlp.common import AnnotatorType
+from sparknlp.internal import AnnotatorTransformer
+from sparknlp.partition.partition_properties import *
+
+class Reader2Image(
+    AnnotatorTransformer,
+    HasReaderProperties,
+    HasHTMLReaderProperties,
+    HasPdfProperties
+):
+    """
+    The Reader2Image annotator allows you to use the reading files with images more smoothly within existing
+    Spark NLP workflows, enabling seamless reuse of your pipelines. Reader2Image can be used for
+    extracting structured image content from various document types using Spark NLP readers. It supports
+    reading from many file types and returns parsed output as a structured Spark DataFrame.
+
+    Supported formats include HTML and Markdown.
+
+    == Example ==
+    This example demonstrates how to load HTML files with images and process them into a structured
+    Spark DataFrame using Reader2Image.
+
+    Expected output:
+    +-------------------+--------------------+
+    |           fileName|               image|
+    +-------------------+--------------------+
+    |example-images.html|[{image, example-...|
+    |example-images.html|[{image, example-...|
+    +-------------------+--------------------+
+
+    Schema:
+    root
+     |-- fileName: string (nullable = true)
+     |-- image: array (nullable = false)
+     |    |-- element: struct (containsNull = true)
+     |    |    |-- annotatorType: string (nullable = true)
+     |    |    |-- origin: string (nullable = true)
+     |    |    |-- height: integer (nullable = false)
+     |    |    |-- width: integer (nullable = false)
+     |    |    |-- nChannels: integer (nullable = false)
+     |    |    |-- mode: integer (nullable = false)
+     |    |    |-- result: binary (nullable = true)
+     |    |    |-- metadata: map (nullable = true)
+     |    |    |    |-- key: string
+     |    |    |    |-- value: string (valueContainsNull = true)
+     |    |    |-- text: string (nullable = true)
+    """
+
+    name = "Reader2Image"
+    outputAnnotatorType = AnnotatorType.IMAGE
+
+    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(Reader2Image, self).__init__(classname="com.johnsnowlabs.reader.Reader2Image")
+        self._setDefault(
+            contentType="",
+            outputFormat="image",
+            explodeDocs=True,
+            userMessage="Describe this image",
+            promptTemplate="qwen2vl-chat",
+            readAsImage=True,
+            customPromptTemplate="",
+            ignoreExceptions=True
+        )
+
+    @keyword_only
+    def setParams(self):
+        kwargs = self._input_kwargs
+        return self._set(**kwargs)
+
+    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)

sparknlp/reader/reader2table.py

@@ -13,14 +13,15 @@
 #  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
 from sparknlp.partition.partition_properties import *
 
+
 class Reader2Table(
     AnnotatorTransformer,
+    HasReaderProperties,
     HasEmailReaderProperties,
     HasExcelReaderProperties,
     HasHTMLReaderProperties,
@@ -31,34 +32,6 @@ class Reader2Table(
 
     outputAnnotatorType = AnnotatorType.DOCUMENT
 
-    contentPath = Param(
-        Params._dummy(),
-        "contentPath",
-        "contentPath path to files to read",
-        typeConverter=TypeConverters.toString
-    )
-
-    outputCol = Param(
-        Params._dummy(),
-        "outputCol",
-        "output column name",
-        typeConverter=TypeConverters.toString
-    )
-
-    contentType = Param(
-        Params._dummy(),
-        "contentType",
-        "Set the content type to load following MIME specification",
-        typeConverter=TypeConverters.toString
-    )
-
-    explodeDocs = Param(
-        Params._dummy(),
-        "explodeDocs",
-        "whether to explode the documents into separate rows",
-        typeConverter=TypeConverters.toBoolean
-    )
-
     flattenOutput = Param(
         Params._dummy(),
         "flattenOutput",
@@ -73,13 +46,6 @@ class Reader2Table(
         typeConverter=TypeConverters.toFloat
     )
 
-    outputFormat = Param(
-        Params._dummy(),
-        "outputFormat",
-        "Output format for the table content. Options are 'plain-text' or 'html-table'. Default is 'json-table'.",
-        typeConverter=TypeConverters.toString
-    )
-
     @keyword_only
     def __init__(self):
         super(Reader2Table, self).__init__(classname="com.johnsnowlabs.reader.Reader2Table")
@@ -90,48 +56,6 @@ class Reader2Table(
         kwargs = self._input_kwargs
         return self._set(**kwargs)
 
-    def setContentPath(self, value):
-        """Sets content path.
-
-        Parameters
-        ----------
-        value : str
-            contentPath path to files to read
-        """
-        return self._set(contentPath=value)
-
-    def setContentType(self, value):
-        """
-        Set the content type to load following MIME specification
-
-        Parameters
-        ----------
-        value : str
-            content type to load following MIME specification
-        """
-        return self._set(contentType=value)
-
-    def setExplodeDocs(self, value):
-        """Sets whether to explode the documents into separate rows.
-
-
-        Parameters
-        ----------
-        value : boolean
-        Whether to explode the documents into separate rows
-        """
-        return self._set(explodeDocs=value)
-
-    def setOutputCol(self, value):
-        """Sets output column name.
-
-        Parameters
-        ----------
-        value : str
-            Name of the Output Column
-        """
-        return self._set(outputCol=value)
-
     def setFlattenOutput(self, value):
         """Sets whether to flatten the output to plain text with minimal metadata.
 
@@ -151,13 +75,3 @@ class Reader2Table(
             Minimum font size threshold for title detection in PDF docs
         """
         return self._set(titleThreshold=value)
-
-    def setOutputFormat(self, value):
-        """Sets the output format for the table content.
-
-        Parameters
-        ----------
-        value : str
-            Output format for the table content. Options are 'plain-text' or 'html-table'. Default is 'json-table'.
-        """
-        return self._set(outputFormat=value)