spark-nlp 6.1.3rc1__tar.gz → 6.1.4__tar.gz

{spark_nlp-6.1.3rc1 → spark_nlp-6.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.3rc1
+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-6.1.3rc1 → spark_nlp-6.1.4}/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==6.1.3 pyspark==3.3.1
+$ pip install spark-nlp==6.1.4 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 *6.1.3* 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 |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -159,7 +159,7 @@ 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**            |
 |--------------------|--------------------|
@@ -177,7 +177,7 @@ 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-6.1.3rc1 → spark_nlp-6.1.4}/setup.py

@@ -41,7 +41,7 @@ setup(
     # project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
 
-    version='6.1.3rc1',  # Required
+    version='6.1.4',  # Required
 
     # This is a one-line description or tagline of what your project does. This
     # corresponds to the 'Summary' metadata field:

{spark_nlp-6.1.3rc1 → spark_nlp-6.1.4}/spark_nlp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.3rc1
+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-6.1.3rc1 → spark_nlp-6.1.4}/spark_nlp.egg-info/SOURCES.txt

@@ -158,6 +158,7 @@ sparknlp/annotator/ner/ner_approach.py
 sparknlp/annotator/ner/ner_converter.py
 sparknlp/annotator/ner/ner_crf.py
 sparknlp/annotator/ner/ner_dl.py
+sparknlp/annotator/ner/ner_dl_graph_checker.py
 sparknlp/annotator/ner/ner_overwriter.py
 sparknlp/annotator/ner/zero_shot_ner_model.py
 sparknlp/annotator/openai/__init__.py
@@ -214,6 +215,7 @@ sparknlp/base/doc2_chunk.py
 sparknlp/base/document_assembler.py
 sparknlp/base/embeddings_finisher.py
 sparknlp/base/finisher.py
+sparknlp/base/gguf_ranking_finisher.py
 sparknlp/base/graph_finisher.py
 sparknlp/base/has_recursive_fit.py
 sparknlp/base/has_recursive_transform.py
@@ -256,6 +258,7 @@ sparknlp/reader/__init__.py
 sparknlp/reader/enums.py
 sparknlp/reader/pdf_to_text.py
 sparknlp/reader/reader2doc.py
+sparknlp/reader/reader2image.py
 sparknlp/reader/reader2table.py
 sparknlp/reader/sparknlp_reader.py
 sparknlp/training/__init__.py

{spark_nlp-6.1.3rc1 → spark_nlp-6.1.4}/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,

{spark_nlp-6.1.3rc1 → spark_nlp-6.1.4}/sparknlp/annotator/ner/__init__.py

@@ -16,5 +16,6 @@ from sparknlp.annotator.ner.ner_approach import *
 from sparknlp.annotator.ner.ner_converter import *
 from sparknlp.annotator.ner.ner_crf import *
 from sparknlp.annotator.ner.ner_dl import *
+from sparknlp.annotator.ner.ner_dl_graph_checker import *
 from sparknlp.annotator.ner.ner_overwriter import *
 from sparknlp.annotator.ner.zero_shot_ner_model import *

spark_nlp-6.1.4/sparknlp/annotator/ner/ner_dl_graph_checker.py

@@ -0,0 +1,237 @@
+#  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.
+"""Contains classes for NerDL."""
+
+from sparknlp.common import *
+import sparknlp.internal as _internal
+from pyspark.ml.util import JavaMLWritable
+from pyspark.ml.wrapper import JavaEstimator
+
+
+class NerDLGraphChecker(
+    JavaEstimator,
+    JavaMLWritable,
+    _internal.ParamsGettersSetters,
+):
+    """Checks whether a suitable NerDL graph is available for the given training dataset, before any
+    computations/training is done. This annotator is useful for custom training cases, where
+    specialized graphs are needed.
+
+    Important: This annotator should be used or positioned before any embedding or NerDLApproach
+    annotators in the pipeline and will process the whole dataset to extract the required graph parameters.
+
+    This annotator requires a dataset with at least two columns: one with tokens and one with the
+    labels. In addition, it requires the used embedding annotator in the pipeline to extract the
+    suitable embedding dimension.
+
+    For extended examples of usage, see the`Examples 
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master//home/ducha/Workspace/scala/spark-nlp-feature/examples/python/training/english/dl-ner/ner_dl_graph_checker.ipynb>`__ 
+    and the `NerDLGraphCheckerTestSpec 
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/annotators/ner/dl/NerDLGraphCheckerTestSpec.scala>`__.
+
+    ==================================== ======================
+    Input Annotation types               Output Annotation type
+    ==================================== ======================
+    ``DOCUMENT, TOKEN``                  `NONE`
+    ==================================== ======================
+
+    Parameters
+    ----------
+    inputCols
+        Column names of input annotations
+    labelColumn
+        Column name for data labels
+    embeddingsDim
+        Dimensionality of embeddings
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+
+    This CoNLL dataset already includes a sentence, token and label
+    column with their respective annotator types. If a custom dataset is used,
+    these need to be defined with for example:
+
+    >>> conll = CoNLL()
+    >>> trainingData = conll.readDataset(spark, "src/test/resources/conll2003/eng.train")
+    >>> embeddings = BertEmbeddings \\
+    ...     .pretrained() \\
+    ...     .setInputCols(["sentence", "token"]) \\
+    ...     .setOutputCol("embeddings")
+    
+    This annotatorr requires the data for NerDLApproach graphs: text, tokens, labels and the embedding model
+
+    >>> nerDLGraphChecker = NerDLGraphChecker() \\
+    ...     .setInputCols(["sentence", "token"]) \\
+    ...     .setLabelColumn("label") \\
+    ...     .setEmbeddingsModel(embeddings)
+    >>> nerTagger = NerDLApproach() \\
+    ...     .setInputCols(["sentence", "token", "embeddings"]) \\
+    ...     .setLabelColumn("label") \\
+    ...     .setOutputCol("ner") \\
+    ...     .setMaxEpochs(1) \\
+    ...     .setRandomSeed(0) \\
+    ...     .setVerbose(0)
+    >>> pipeline = Pipeline().setStages([nerDLGraphChecker, embeddings, nerTagger])
+    
+    If we now fit the model with a graph missing, then an exception is raised.
+
+    >>> pipelineModel = pipeline.fit(trainingData)
+    """
+
+    inputCols = Param(
+        Params._dummy(),
+        "inputCols",
+        "Input columns",
+        typeConverter=TypeConverters.toListString,
+    )
+
+    def setInputCols(self, *value):
+        """Sets column names of input annotations.
+
+        Parameters
+        ----------
+        *value : List[str]
+            Input columns for the annotator
+        """
+        if type(value[0]) == str or type(value[0]) == list:
+            # self.inputColsValidation(value)
+            if len(value) == 1 and type(value[0]) == list:
+                return self._set(inputCols=value[0])
+            else:
+                return self._set(inputCols=list(value))
+        else:
+            raise TypeError(
+                "InputCols datatype not supported. It must be either str or list"
+            )
+
+    labelColumn = Param(
+        Params._dummy(),
+        "labelColumn",
+        "Column with label per each token",
+        typeConverter=TypeConverters.toString,
+    )
+
+    def setLabelColumn(self, value):
+        """Sets name of column for data labels.
+
+        Parameters
+        ----------
+        value : str
+            Column for data labels
+        """
+        return self._set(labelColumn=value)
+
+    embeddingsDim = Param(
+        Params._dummy(),
+        "embeddingsDim",
+        "Dimensionality of embeddings",
+        typeConverter=TypeConverters.toInt,
+    )
+
+    def setEmbeddingsDim(self, value: int):
+        """Sets Dimensionality of embeddings
+
+        Parameters
+        ----------
+        value : int
+            Dimensionality of embeddings
+        """
+        return self._set(embeddingsDim=value)
+
+    def setEmbeddingsModel(self, model: HasEmbeddingsProperties):
+        """
+        Get embeddingsDim from a given embeddings model, if possible.
+        Falls back to setEmbeddingsDim if dimension cannot be obtained automatically.
+        """
+        # Try Python API first
+        if hasattr(model, "getDimension"):
+            dim = model.getDimension()
+            return self.setEmbeddingsDim(int(dim))
+        # Try JVM side if available
+        if hasattr(model, "_java_obj") and hasattr(model._java_obj, "getDimension"):
+            dim = int(model._java_obj.getDimension())
+            return self.setEmbeddingsDim(dim)
+        raise ValueError(
+            "Could not infer embeddings dimension from provided model. "
+            "Use setEmbeddingsDim(dim) explicitly."
+        )
+
+    inputAnnotatorTypes = [
+        AnnotatorType.DOCUMENT,
+        AnnotatorType.TOKEN,
+    ]
+
+    graphFolder = Param(
+        Params._dummy(),
+        "graphFolder",
+        "Folder path that contain external graph files",
+        TypeConverters.toString,
+    )
+
+    def setGraphFolder(self, p):
+        """Sets folder path that contain external graph files.
+
+        Parameters
+        ----------
+        p : str
+            Folder path that contain external graph files
+        """
+        return self._set(graphFolder=p)
+
+    @keyword_only
+    def __init__(self):
+        _internal.ParamsGettersSetters.__init__(self)
+        classname = "com.johnsnowlabs.nlp.annotators.ner.dl.NerDLGraphChecker"
+        self.__class__._java_class_name = classname
+        self._java_obj = self._new_java_obj(classname, self.uid)
+        # self._setDefault()
+
+    def _create_model(self, java_model):
+        return NerDLGraphCheckerModel()
+
+
+class NerDLGraphCheckerModel(
+    JavaModel,
+    JavaMLWritable,
+    _internal.ParamsGettersSetters,
+):
+    """
+    Resulting model from NerDLGraphChecker, that does not perform any transformations, as the
+    checks are done during the ``fit`` phase. It acts as the identity.
+
+    This annotator should never be used directly.
+    """
+
+    inputAnnotatorTypes = [
+        AnnotatorType.DOCUMENT,
+        AnnotatorType.TOKEN,
+    ]
+
+    @keyword_only
+    def __init__(
+        self,
+        classname="com.johnsnowlabs.nlp.annotators.ner.dl.NerDLGraphCheckerModel",
+        java_model=None,
+    ):
+        super(NerDLGraphCheckerModel, self).__init__(java_model=java_model)
+        if classname and not java_model:
+            self.__class__._java_class_name = classname
+            self._java_obj = self._new_java_obj(classname, self.uid)
+        if java_model is not None:
+            self._transfer_params_from_java()
+        # self._setDefault(lazyAnnotator=False)

{spark_nlp-6.1.3rc1 → spark_nlp-6.1.4}/sparknlp/annotator/seq2seq/auto_gguf_reranker.py

@@ -47,7 +47,7 @@ class AutoGGUFReranker(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties
     ...     .setOutputCol("reranked_documents") \\
     ...     .setQuery("A man is eating pasta.")
 
-    The default model is ``"bge-reranker-v2-m3-Q4_K_M"``, if no name is provided.
+    The default model is ``"bge_reranker_v2_m3_Q4_K_M"``, if no name is provided.
 
     For extended examples of usage, see the
     `AutoGGUFRerankerTest <https://github.com/JohnSnowLabs/spark-nlp/tree/master/src/test/scala/com/johnsnowlabs/nlp/annotators/seq2seq/AutoGGUFRerankerTest.scala>`__
@@ -222,7 +222,7 @@ class AutoGGUFReranker(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties
     >>> document = DocumentAssembler() \\
     ...     .setInputCol("text") \\
     ...     .setOutputCol("document")
-    >>> reranker = AutoGGUFReranker.pretrained("bge-reranker-v2-m3-Q4_K_M") \\
+    >>> reranker = AutoGGUFReranker.pretrained() \\
     ...     .setInputCols(["document"]) \\
     ...     .setOutputCol("reranked_documents") \\
     ...     .setBatchSize(4) \\
@@ -307,13 +307,13 @@ class AutoGGUFReranker(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties
         return AutoGGUFReranker(java_model=jModel)
 
     @staticmethod
-    def pretrained(name="bge-reranker-v2-m3-Q4_K_M", lang="en", remote_loc=None):
+    def pretrained(name="bge_reranker_v2_m3_Q4_K_M", lang="en", remote_loc=None):
         """Downloads and loads a pretrained model.
 
         Parameters
         ----------
         name : str, optional
-            Name of the pretrained model, by default "bge-reranker-v2-m3-Q4_K_M"
+            Name of the pretrained model, by default "bge_reranker_v2_m3_Q4_K_M"
         lang : str, optional
             Language of the pretrained model, by default "en"
         remote_loc : str, optional

{spark_nlp-6.1.3rc1 → spark_nlp-6.1.4}/sparknlp/base/__init__.py

@@ -17,6 +17,7 @@ from sparknlp.base.document_assembler import *
 from sparknlp.base.multi_document_assembler import *
 from sparknlp.base.embeddings_finisher import *
 from sparknlp.base.finisher import *
+from sparknlp.base.gguf_ranking_finisher import *
 from sparknlp.base.graph_finisher import *
 from sparknlp.base.has_recursive_fit import *
 from sparknlp.base.has_recursive_transform import *