spark-nlp 6.1.2rc1__py2.py3-none-any.whl → 6.1.3__py2.py3-none-any.whl

{spark_nlp-6.1.2rc1.dist-info → spark_nlp-6.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.2rc1
+Version: 6.1.3
 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==6.1.1 pyspark==3.3.1
+$ pip install spark-nlp==6.1.3 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 *6.1.1* 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 *6.1.3* 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 | 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 6.1.1 has been tested and is compatible with the following runtimes:
+Spark NLP 6.1.3 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 6.1.1 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.1.3 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.1.2rc1.dist-info → spark_nlp-6.1.3.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=sEwJ50P2C-LGn-MZ8oI6jO6N0OutYSL3b6bCVkOo2wc,13814
+sparknlp/__init__.py,sha256=UR0dRykX67j-Ksuzk5Xe-Mod5qCK24iBjHHa0omOp2w,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
@@ -146,11 +146,12 @@ sparknlp/annotator/matcher/date_matcher.py,sha256=FrjTVoNBq1Z7E4qSJKvfV5rC7Mlm9R
 sparknlp/annotator/matcher/multi_date_matcher.py,sha256=-zCp4HugIpSN6U4-c1uN_dGn7x69xYy6SUoQz6dY34s,4475
 sparknlp/annotator/matcher/regex_matcher.py,sha256=GYhJNjBnCvfeEMv7d2_kDnqjfHtC7Hts--Ttlkjdozs,8380
 sparknlp/annotator/matcher/text_matcher.py,sha256=kpP1-5BEFEW9kantoHvjhcCbX1qsGm4gEDtFHATWOwA,10636
-sparknlp/annotator/ner/__init__.py,sha256=4ni5IHCbGlEmhCgGDw7A61x633qUTvWko2pIixiKO2Q,948
+sparknlp/annotator/ner/__init__.py,sha256=cd13PX6O92BIasE8NWd3JUR6up2fRbe7chRx4lQZRcY,1006
 sparknlp/annotator/ner/ner_approach.py,sha256=4Y4gcusVtDaQpXfBbBe8XMAZ5hw1mvdh5A7g1j_T1KY,2793
 sparknlp/annotator/ner/ner_converter.py,sha256=ANPp_Xe0DaK4z4n-0KujBj3Xp5jIbsFXBXvmp-aCKlM,5924
 sparknlp/annotator/ner/ner_crf.py,sha256=eFylEz3-CENW0dyc6K4jodz9Kig3tnCyfZ3s-KZMvH4,14283
 sparknlp/annotator/ner/ner_dl.py,sha256=ght1W6-ArjLRiNHCv_bKpozkyNd8HVIb8SDGhcbp8Fg,22123
+sparknlp/annotator/ner/ner_dl_graph_checker.py,sha256=KB_BuNj2EPiVaHJEU9N1d40j-qGCn9e2tsTYctsioyc,8227
 sparknlp/annotator/ner/ner_overwriter.py,sha256=en5OxXIP46yTXokIE96YDP9kcHA9oxiRPgwXMo0otew,6798
 sparknlp/annotator/ner/zero_shot_ner_model.py,sha256=DohhnkGSG-JxjW72t8AOx3GY7R_qT-LA3I0KF9TBz-Y,7501
 sparknlp/annotator/openai/__init__.py,sha256=u6SpV_xS8UpBE95WnTl0IefOI5TrTRl7ZHuYoeTetiA,759
@@ -167,8 +168,9 @@ sparknlp/annotator/sentence/sentence_detector_dl.py,sha256=-Osj9Bm9KyZRTAWkOsK9c
 sparknlp/annotator/sentiment/__init__.py,sha256=Lq3vKaZS1YATLMg0VNXSVtkWL5q5G9taGBvdrvSwnfg,766
 sparknlp/annotator/sentiment/sentiment_detector.py,sha256=m545NGU0Xzg_PO6_qIfpli1uZj7JQcyFgqe9R6wAPFI,8154
 sparknlp/annotator/sentiment/vivekn_sentiment.py,sha256=4rpXWDgzU6ddnbrSCp9VdLb2epCc9oZ3c6XcqxEw8nk,9655
-sparknlp/annotator/seq2seq/__init__.py,sha256=Aj43G1MuQE0mW7LakCWPjiTkIGl7iHPAnKIwT_DfdIM,1781
+sparknlp/annotator/seq2seq/__init__.py,sha256=aDiph00Hyq7L8uDY0frtyuHtqFodBqTMbixx_nq4z1I,1841
 sparknlp/annotator/seq2seq/auto_gguf_model.py,sha256=yhZQHMHfp88rQvLHTWyS-8imZrwqp-8RQQwnw6PmHfc,11749
+sparknlp/annotator/seq2seq/auto_gguf_reranker.py,sha256=MS4wCm2A2YiQfkB4HVVZKuN-3A1yGzqSCF69nu7J2rQ,12640
 sparknlp/annotator/seq2seq/auto_gguf_vision_model.py,sha256=swBek2026dW6BOX5O9P8Uq41X2GC71VGW0ADFeUIvs0,15299
 sparknlp/annotator/seq2seq/bart_transformer.py,sha256=I1flM4yeCzEAKOdQllBC30XuedxVJ7ferkFhZ6gwEbE,18481
 sparknlp/annotator/seq2seq/cohere_transformer.py,sha256=43LZBVazZMgJRCsN7HaYjVYfJ5hRMV95QZyxMtXq-m4,13496
@@ -200,12 +202,13 @@ sparknlp/annotator/token/regex_tokenizer.py,sha256=FG2HvFwMb1G_4grfyIQaeBpaAgKv_
 sparknlp/annotator/token/tokenizer.py,sha256=Me3P3wogUKUJ7O7_2wLdPzF00vKpp_sHuiztpGWRVpU,19939
 sparknlp/annotator/ws/__init__.py,sha256=-l8bnl8Z6lGXWOBdRIBZ6958fzTHt4o87QhhLHIFF8A,693
 sparknlp/annotator/ws/word_segmenter.py,sha256=rrbshwn5wzXIHpCCDji6ZcsmiARpuA82_p_6TgNHfRc,16365
-sparknlp/base/__init__.py,sha256=fCL-kReIavZceUa1OC99pSRH7MsXzqGB8BXgzVS_f7s,1311
+sparknlp/base/__init__.py,sha256=ug0e79fv03D67mUqmb-i-a89vOa6EcRx49Z0fS6rT3g,1361
 sparknlp/base/audio_assembler.py,sha256=HKa9mXvmuMUrjTihUZkppGj-WJjcUrm2BGapNuPifyI,3320
 sparknlp/base/doc2_chunk.py,sha256=TyvbdJNkVo9favHlOEoH5JwKbjpk5ZVJ75p8Cilp9jM,6551
 sparknlp/base/document_assembler.py,sha256=zl-SXWMTR3B0EZ8z6SWYchCwEo-61FhU6u7dHUKDIOg,6697
 sparknlp/base/embeddings_finisher.py,sha256=5QU1Okgl2ULrPVf4ze1H0SsRCMYXWGARtUsT7dagBYA,7659
 sparknlp/base/finisher.py,sha256=V4wkMm9Ug09q4zTQc9T9Wr-awmu2Hu-eNaJ039YgZXM,8583
+sparknlp/base/gguf_ranking_finisher.py,sha256=tzoisuD70myfHo3t4WFtBs8i1jwdjkwXCbWknDEXOHk,8315
 sparknlp/base/graph_finisher.py,sha256=a8fxk3ei2YQw6s0Y9Yy8oMOF1i1XUrgqaiwVE0VPt4w,4834
 sparknlp/base/has_recursive_fit.py,sha256=P55rSHLIXhihXWS2bOC_DskcQTc3njieVD1JkjS2bcA,849
 sparknlp/base/has_recursive_transform.py,sha256=UkGNgo4LMsjQC-Coeefg4bJcg7FoPcPiG382zEa6Ywk,841
@@ -228,7 +231,7 @@ sparknlp/common/read_as.py,sha256=imxPGwV7jr4Li_acbo0OAHHRGCBbYv-akzEGaBWEfcY,12
 sparknlp/common/recursive_annotator_approach.py,sha256=vqugBw22cE3Ff7PIpRlnYFuOlchgL0nM26D8j-NdpqU,1449
 sparknlp/common/storage.py,sha256=D91H3p8EIjNspjqAYu6ephRpCUtdcAir4_PrAbkIQWE,4842
 sparknlp/common/utils.py,sha256=Yne6yYcwKxhOZC-U4qfYoDhWUP_6BIaAjI5X_P_df1E,1306
-sparknlp/internal/__init__.py,sha256=f5kxLz6bEX8FCMo6lek30MXbn_lDC-dBTI9s_fARblI,40748
+sparknlp/internal/__init__.py,sha256=m7Y7y-IPkB6aJuGUCM54eOueGOEt65C3ujAzN16hegQ,40995
 sparknlp/internal/annotator_java_ml.py,sha256=UGPoThG0rGXUOXGSQnDzEDW81Mu1s5RPF29v7DFyE3c,1187
 sparknlp/internal/annotator_transformer.py,sha256=fXmc2IWXGybqZpbEU9obmbdBYPc798y42zvSB4tqV9U,1448
 sparknlp/internal/extended_java_wrapper.py,sha256=hwP0133-hDiDf5sBF-P3MtUsuuDj1PpQbtGZQIRwzfk,2240
@@ -247,7 +250,7 @@ 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=LRqfaL9nidhlPkJIwTJo7SnGYmNNfOqwEdrsWYGEdnI,7146
+sparknlp/reader/reader2doc.py,sha256=8x1tvx7Hj2J4xpyRiCUvrG-kmOPBvIE8K1tJZY-e0Xw,8200
 sparknlp/reader/reader2table.py,sha256=GC6Yz0gQ83S6XKOi329TUNQuAvLrBxysqDkDRZPvcYA,4759
 sparknlp/reader/sparknlp_reader.py,sha256=MJs8v_ECYaV1SOabI1L_2MkVYEDVImtwgbYypO7DJSY,20623
 sparknlp/training/__init__.py,sha256=qREi9u-5Vc2VjpL6-XZsyvu5jSEIdIhowW7_kKaqMqo,852
@@ -280,7 +283,7 @@ 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-6.1.2rc1.dist-info/METADATA,sha256=4qK5_LPihfkDmSrLBQgH38R_VE5lzDnsygPpOccUTdc,19777
-spark_nlp-6.1.2rc1.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
-spark_nlp-6.1.2rc1.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
-spark_nlp-6.1.2rc1.dist-info/RECORD,,
+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,,

sparknlp/__init__.py

@@ -66,7 +66,7 @@ sys.modules['com.johnsnowlabs.ml.ai'] = annotator
 annotators = annotator
 embeddings = annotator
 
-__version__ = "6.1.1"
+__version__ = "6.1.3"
 
 
 def start(gpu=False,

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 *

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)

sparknlp/annotator/seq2seq/__init__.py

@@ -32,3 +32,4 @@ from sparknlp.annotator.seq2seq.llama3_transformer import *
 from sparknlp.annotator.seq2seq.cohere_transformer import *
 from sparknlp.annotator.seq2seq.olmo_transformer import *
 from sparknlp.annotator.seq2seq.phi4_transformer import *
+from sparknlp.annotator.seq2seq.auto_gguf_reranker import *

sparknlp/annotator/seq2seq/auto_gguf_reranker.py

@@ -0,0 +1,329 @@
+#  Copyright 2017-2023 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 the AutoGGUFReranker."""
+from typing import List, Dict
+
+from sparknlp.common import *
+
+
+class AutoGGUFReranker(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
+    """
+    Annotator that uses the llama.cpp library to rerank text documents based on their relevance
+    to a given query using GGUF-format reranking models.
+
+    This annotator is specifically designed for text reranking tasks, where multiple documents
+    or text passages are ranked according to their relevance to a query. It uses specialized
+    reranking models in GGUF format that output relevance scores for each input document.
+
+    The reranker takes a query (set via :meth:`.setQuery`) and a list of documents, then returns the
+    same documents with added metadata containing relevance scores. The documents are processed
+    in batches and each receives a ``relevance_score`` in its metadata indicating how relevant
+    it is to the provided query.
+
+    For settable parameters, and their explanations, see the parameters of this class and refer to
+    the llama.cpp documentation of
+    `server.cpp <https://github.com/ggerganov/llama.cpp/tree/7d5e8777ae1d21af99d4f95be10db4870720da91/examples/server>`__
+    for more information.
+
+    If the parameters are not set, the annotator will default to use the parameters provided by
+    the model.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> reranker = AutoGGUFReranker.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .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.
+
+    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>`__
+    and the
+    `example notebook <https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples/python/llama.cpp/llama.cpp_in_Spark_NLP_AutoGGUFReranker.ipynb>`__.
+
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT``           ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    query
+        The query to be used for reranking. If not set, the input text will be used as the query.
+    nThreads
+        Set the number of threads to use during generation
+    nThreadsDraft
+        Set the number of threads to use during draft generation
+    nThreadsBatch
+        Set the number of threads to use during batch and prompt processing
+    nThreadsBatchDraft
+        Set the number of threads to use during batch and prompt processing
+    nCtx
+        Set the size of the prompt context
+    nBatch
+        Set the logical batch size for prompt processing (must be >=32 to use BLAS)
+    nUbatch
+        Set the physical batch size for prompt processing (must be >=32 to use BLAS)
+    nGpuLayers
+        Set the number of layers to store in VRAM (-1 - use default)
+    nGpuLayersDraft
+        Set the number of layers to store in VRAM for the draft model (-1 - use default)
+    gpuSplitMode
+        Set how to split the model across GPUs
+    mainGpu
+        Set the main GPU that is used for scratch and small tensors.
+    tensorSplit
+        Set how split tensors should be distributed across GPUs
+    grpAttnN
+        Set the group-attention factor
+    grpAttnW
+        Set the group-attention width
+    ropeFreqBase
+        Set the RoPE base frequency, used by NTK-aware scaling
+    ropeFreqScale
+        Set the RoPE frequency scaling factor, expands context by a factor of 1/N
+    yarnExtFactor
+        Set the YaRN extrapolation mix factor
+    yarnAttnFactor
+        Set the YaRN scale sqrt(t) or attention magnitude
+    yarnBetaFast
+        Set the YaRN low correction dim or beta
+    yarnBetaSlow
+        Set the YaRN high correction dim or alpha
+    yarnOrigCtx
+        Set the YaRN original context size of model
+    defragmentationThreshold
+        Set the KV cache defragmentation threshold
+    numaStrategy
+        Set optimization strategies that help on some NUMA systems (if available)
+    ropeScalingType
+        Set the RoPE frequency scaling method, defaults to linear unless specified by the model
+    poolingType
+        Set the pooling type for embeddings, use model default if unspecified
+    modelDraft
+        Set the draft model for speculative decoding
+    modelAlias
+        Set a model alias
+    lookupCacheStaticFilePath
+        Set path to static lookup cache to use for lookup decoding (not updated by generation)
+    lookupCacheDynamicFilePath
+        Set path to dynamic lookup cache to use for lookup decoding (updated by generation)
+    flashAttention
+        Whether to enable Flash Attention
+    inputPrefixBos
+        Whether to add prefix BOS to user inputs, preceding the `--in-prefix` string
+    useMmap
+        Whether to use memory-map model (faster load but may increase pageouts if not using mlock)
+    useMlock
+        Whether to force the system to keep model in RAM rather than swapping or compressing
+    noKvOffload
+        Whether to disable KV offload
+    systemPrompt
+        Set a system prompt to use
+    chatTemplate
+        The chat template to use
+    inputPrefix
+        Set the prompt to start generation with
+    inputSuffix
+        Set a suffix for infilling
+    cachePrompt
+        Whether to remember the prompt to avoid reprocessing it
+    nPredict
+        Set the number of tokens to predict
+    topK
+        Set top-k sampling
+    topP
+        Set top-p sampling
+    minP
+        Set min-p sampling
+    tfsZ
+        Set tail free sampling, parameter z
+    typicalP
+        Set locally typical sampling, parameter p
+    temperature
+        Set the temperature
+    dynatempRange
+        Set the dynamic temperature range
+    dynatempExponent
+        Set the dynamic temperature exponent
+    repeatLastN
+        Set the last n tokens to consider for penalties
+    repeatPenalty
+        Set the penalty of repeated sequences of tokens
+    frequencyPenalty
+        Set the repetition alpha frequency penalty
+    presencePenalty
+        Set the repetition alpha presence penalty
+    miroStat
+        Set MiroStat sampling strategies.
+    mirostatTau
+        Set the MiroStat target entropy, parameter tau
+    mirostatEta
+        Set the MiroStat learning rate, parameter eta
+    penalizeNl
+        Whether to penalize newline tokens
+    nKeep
+        Set the number of tokens to keep from the initial prompt
+    seed
+        Set the RNG seed
+    nProbs
+        Set the amount top tokens probabilities to output if greater than 0.
+    minKeep
+        Set the amount of tokens the samplers should return at least (0 = disabled)
+    grammar
+        Set BNF-like grammar to constrain generations
+    penaltyPrompt
+        Override which part of the prompt is penalized for repetition.
+    ignoreEos
+        Set whether to ignore end of stream token and continue generating (implies --logit-bias 2-inf)
+    disableTokenIds
+        Set the token ids to disable in the completion
+    stopStrings
+        Set strings upon seeing which token generation is stopped
+    samplers
+        Set which samplers to use for token generation in the given order
+    useChatTemplate
+        Set whether or not generate should apply a chat template
+
+    Notes
+    -----
+    This annotator is designed for reranking tasks and requires setting a query using ``setQuery``.
+    The query represents the search intent against which documents will be ranked. Each input
+    document receives a relevance score in the output metadata.
+
+    To use GPU inference with this annotator, make sure to use the Spark NLP GPU package and set
+    the number of GPU layers with the `setNGpuLayers` method.
+
+    When using larger models, we recommend adjusting GPU usage with `setNCtx` and `setNGpuLayers`
+    according to your hardware to avoid out-of-memory errors.
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> document = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> reranker = AutoGGUFReranker.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("reranked_documents") \\
+    ...     .setBatchSize(4) \\
+    ...     .setQuery("A man is eating pasta.")
+    >>> pipeline = Pipeline().setStages([document, reranker])
+    >>> data = spark.createDataFrame([
+    ...     ["A man is eating food."],
+    ...     ["A man is eating a piece of bread."],
+    ...     ["The girl is carrying a baby."],
+    ...     ["A man is riding a horse."]
+    ... ]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("reranked_documents").show(truncate = False)
+    # Each document will have a relevance_score in metadata showing how relevant it is to the query
+    """
+
+    name = "AutoGGUFReranker"
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    query = Param(Params._dummy(), "query",
+                  "The query to be used for reranking. If not set, the input text will be used as the query.",
+                  typeConverter=TypeConverters.toString)
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.seq2seq.AutoGGUFReranker", java_model=None):
+        super(AutoGGUFReranker, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            useChatTemplate=True,
+            nCtx=4096,
+            nBatch=512,
+            nGpuLayers=99,
+            systemPrompt="You are a helpful assistant.",
+            query=""
+        )
+
+    def setQuery(self, value: str):
+        """Set the query to be used for reranking.
+        
+        Parameters
+        ----------
+        value : str
+            The query text that documents will be ranked against.
+            
+        Returns
+        -------
+        AutoGGUFReranker
+            This instance for method chaining.
+        """
+        return self._set(query=value)
+
+    def getQuery(self):
+        """Get the current query used for reranking.
+        
+        Returns
+        -------
+        str
+            The current query string.
+        """
+        return self._call_java("getQuery")
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        AutoGGUFReranker
+            The restored model
+        """
+        from sparknlp.internal import _AutoGGUFRerankerLoader
+        jModel = _AutoGGUFRerankerLoader(folder, spark_session._jsparkSession)._java_obj
+        return AutoGGUFReranker(java_model=jModel)
+
+    @staticmethod
+    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"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        AutoGGUFReranker
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(AutoGGUFReranker, name, lang, remote_loc)

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 *

sparknlp/base/gguf_ranking_finisher.py

@@ -0,0 +1,234 @@
+#  Copyright 2017-2024 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 the GGUFRankingFinisher."""
+
+from pyspark import keyword_only
+from pyspark.ml.param import TypeConverters, Params, Param
+from sparknlp.internal import AnnotatorTransformer
+
+
+class GGUFRankingFinisher(AnnotatorTransformer):
+    """Finisher for AutoGGUFReranker outputs that provides ranking capabilities
+    including top-k selection, sorting by relevance score, and score normalization.
+
+    This finisher processes the output of AutoGGUFReranker, which contains documents with
+    relevance scores in their metadata. It provides several options for post-processing:
+
+    - Top-k selection: Select only the top k documents by relevance score
+    - Score thresholding: Filter documents by minimum relevance score
+    - Min-max scaling: Normalize relevance scores to 0-1 range
+    - Sorting: Sort documents by relevance score in descending order
+    - Ranking: Add rank information to document metadata
+
+    The finisher preserves the document annotation structure while adding ranking information
+    to the metadata and optionally filtering/sorting the documents.
+
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/finisher/gguf_ranking_finisher_example.py>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT``           ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    inputCols
+        Name of input annotation columns containing reranked documents
+    outputCol
+        Name of output annotation column containing ranked documents, by default "ranked_documents"
+    topK
+        Maximum number of top documents to return based on relevance score (-1 for no limit), by default -1
+    minRelevanceScore
+        Minimum relevance score threshold for filtering documents, by default Double.MinValue
+    minMaxScaling
+        Whether to apply min-max scaling to normalize relevance scores to 0-1 range, by default False
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> reranker = AutoGGUFReranker.pretrained() \\
+    ...     .setInputCols("document") \\
+    ...     .setOutputCol("reranked_documents") \\
+    ...     .setQuery("A man is eating pasta.")
+    >>> finisher = GGUFRankingFinisher() \\
+    ...     .setInputCols("reranked_documents") \\
+    ...     .setOutputCol("ranked_documents") \\
+    ...     .setTopK(3) \\
+    ...     .setMinMaxScaling(True)
+    >>> pipeline = Pipeline().setStages([documentAssembler, reranker, finisher])
+    >>> data = spark.createDataFrame([
+    ...     ("A man is eating food.",),
+    ...     ("A man is eating a piece of bread.",),
+    ...     ("The girl is carrying a baby.",),
+    ...     ("A man is riding a horse.",)
+    ... ], ["text"])
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("ranked_documents").show(truncate=False)
+    # Documents will be sorted by relevance with rank information in metadata
+    """
+
+    name = "GGUFRankingFinisher"
+
+    inputCols = Param(Params._dummy(),
+                     "inputCols",
+                     "Name of input annotation columns containing reranked documents",
+                     typeConverter=TypeConverters.toListString)
+
+    outputCol = Param(Params._dummy(),
+                     "outputCol", 
+                     "Name of output annotation column containing ranked documents",
+                     typeConverter=TypeConverters.toListString)
+
+    topK = Param(Params._dummy(),
+                 "topK",
+                 "Maximum number of top documents to return based on relevance score (-1 for no limit)",
+                 typeConverter=TypeConverters.toInt)
+
+    minRelevanceScore = Param(Params._dummy(),
+                             "minRelevanceScore",
+                             "Minimum relevance score threshold for filtering documents",
+                             typeConverter=TypeConverters.toFloat)
+
+    minMaxScaling = Param(Params._dummy(),
+                         "minMaxScaling",
+                         "Whether to apply min-max scaling to normalize relevance scores to 0-1 range",
+                         typeConverter=TypeConverters.toBoolean)
+
+    @keyword_only
+    def __init__(self):
+        super(GGUFRankingFinisher, self).__init__(
+            classname="com.johnsnowlabs.nlp.finisher.GGUFRankingFinisher")
+        self._setDefault(
+            topK=-1,
+            minRelevanceScore=float('-inf'),  # Equivalent to Double.MinValue
+            minMaxScaling=False,
+            outputCol=["ranked_documents"]
+        )
+
+    @keyword_only
+    def setParams(self):
+        kwargs = self._input_kwargs
+        return self._set(**kwargs)
+
+    def setInputCols(self, *value):
+        """Sets input annotation column names.
+
+        Parameters
+        ----------
+        value : List[str]
+            Input annotation column names containing reranked documents
+        """
+        if len(value) == 1 and isinstance(value[0], list):
+            return self._set(inputCols=value[0])
+        else:
+            return self._set(inputCols=list(value))
+
+    def getInputCols(self):
+        """Gets input annotation column names.
+
+        Returns
+        -------
+        List[str]
+            Input annotation column names
+        """
+        return self.getOrDefault(self.inputCols)
+
+    def setOutputCol(self, value):
+        """Sets output annotation column name.
+
+        Parameters
+        ----------
+        value : str
+            Output annotation column name
+        """
+        return self._set(outputCol=[value])
+
+    def getOutputCol(self):
+        """Gets output annotation column name.
+
+        Returns
+        -------
+        str
+            Output annotation column name
+        """
+        output_cols = self.getOrDefault(self.outputCol)
+        return output_cols[0] if output_cols else "ranked_documents"
+
+    def setTopK(self, value):
+        """Sets maximum number of top documents to return.
+
+        Parameters
+        ----------
+        value : int
+            Maximum number of top documents to return (-1 for no limit)
+        """
+        return self._set(topK=value)
+
+    def getTopK(self):
+        """Gets maximum number of top documents to return.
+
+        Returns
+        -------
+        int
+            Maximum number of top documents to return
+        """
+        return self.getOrDefault(self.topK)
+
+    def setMinRelevanceScore(self, value):
+        """Sets minimum relevance score threshold.
+
+        Parameters
+        ----------
+        value : float
+            Minimum relevance score threshold
+        """
+        return self._set(minRelevanceScore=value)
+
+    def getMinRelevanceScore(self):
+        """Gets minimum relevance score threshold.
+
+        Returns
+        -------
+        float
+            Minimum relevance score threshold
+        """
+        return self.getOrDefault(self.minRelevanceScore)
+
+    def setMinMaxScaling(self, value):
+        """Sets whether to apply min-max scaling.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to apply min-max scaling to normalize scores
+        """
+        return self._set(minMaxScaling=value)
+
+    def getMinMaxScaling(self):
+        """Gets whether to apply min-max scaling.
+
+        Returns
+        -------
+        bool
+            Whether min-max scaling is enabled
+        """
+        return self.getOrDefault(self.minMaxScaling)

sparknlp/internal/__init__.py

@@ -1191,4 +1191,9 @@ class _Phi4Loader(ExtendedJavaWrapper):
             path,
             jspark,
             use_openvino,
-        )
+        )
+
+class _AutoGGUFRerankerLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark):
+        super(_AutoGGUFRerankerLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.seq2seq.AutoGGUFReranker.loadSavedModel", path, jspark)

sparknlp/reader/reader2doc.py

@@ -122,6 +122,20 @@ class Reader2Doc(
         typeConverter=TypeConverters.toString
     )
 
+    outputAsDocument = Param(
+        Params._dummy(),
+        "outputAsDocument",
+        "Whether to return all sentences joined into a single document",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    excludeNonText = Param(
+        Params._dummy(),
+        "excludeNonText",
+        "Whether to exclude non-text content from the output. Default is False.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
     @keyword_only
     def __init__(self):
         super(Reader2Doc, self).__init__(classname="com.johnsnowlabs.reader.Reader2Doc")
@@ -182,7 +196,7 @@ class Reader2Doc(
     def setFlattenOutput(self, value):
         """Sets whether to flatten the output to plain text with minimal metadata.
 
-        Parameters
+        ParametersF
         ----------
         value : bool
             If true, output is flattened to plain text with minimal metadata
@@ -208,3 +222,23 @@ class Reader2Doc(
             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.
+
+        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)