spark-nlp 6.0.1__tar.gz → 6.0.2__tar.gz

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.0.1
+Version: 6.0.2
 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
@@ -29,6 +29,13 @@ Classifier: Topic :: Text Processing :: Linguistic
 Classifier: Topic :: Scientific/Engineering
 Classifier: Typing :: Typed
 Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: summary
 
 # Spark NLP: State-of-the-Art Natural Language Processing & LLMs Library
 
@@ -95,7 +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==6.0.1 pyspark==3.3.1
+$ pip install spark-nlp==6.0.2 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -161,7 +168,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *6.0.1* 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 *6.0.2* 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 |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -191,7 +198,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.0.1 has been tested and is compatible with the following runtimes:
+Spark NLP 6.0.2 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -208,7 +215,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.0.1 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.0.2 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/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==6.0.1 pyspark==3.3.1
+$ pip install spark-nlp==6.0.2 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 *6.0.1* 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 *6.0.2* 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 6.0.1 has been tested and is compatible with the following runtimes:
+Spark NLP 6.0.2 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -176,7 +176,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.0.1 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.0.2 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/setup.py

@@ -41,7 +41,7 @@ setup(
     # project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
 
-    version='6.0.1',  # Required
+    version='6.0.2',  # Required
 
     # This is a one-line description or tagline of what your project does. This
     # corresponds to the 'Summary' metadata field:

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/spark_nlp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.0.1
+Version: 6.0.2
 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
@@ -29,6 +29,13 @@ Classifier: Topic :: Text Processing :: Linguistic
 Classifier: Topic :: Scientific/Engineering
 Classifier: Typing :: Typed
 Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: summary
 
 # Spark NLP: State-of-the-Art Natural Language Processing & LLMs Library
 
@@ -95,7 +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==6.0.1 pyspark==3.3.1
+$ pip install spark-nlp==6.0.2 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -161,7 +168,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *6.0.1* 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 *6.0.2* 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 |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -191,7 +198,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.0.1 has been tested and is compatible with the following runtimes:
+Spark NLP 6.0.2 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -208,7 +215,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.0.1 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.0.2 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/spark_nlp.egg-info/SOURCES.txt

@@ -93,7 +93,9 @@ sparknlp/annotator/cv/__init__.py
 sparknlp/annotator/cv/blip_for_question_answering.py
 sparknlp/annotator/cv/clip_for_zero_shot_classification.py
 sparknlp/annotator/cv/convnext_for_image_classification.py
+sparknlp/annotator/cv/florence2_transformer.py
 sparknlp/annotator/cv/gemma3_for_multimodal.py
+sparknlp/annotator/cv/internvl_for_multimodal.py
 sparknlp/annotator/cv/janus_for_multimodal.py
 sparknlp/annotator/cv/llava_for_multimodal.py
 sparknlp/annotator/cv/mllama_for_multimodal.py
@@ -237,6 +239,10 @@ sparknlp/internal/params_getters_setters.py
 sparknlp/internal/recursive.py
 sparknlp/logging/__init__.py
 sparknlp/logging/comet.py
+sparknlp/partition/__init__.py
+sparknlp/partition/partition.py
+sparknlp/partition/partition_properties.py
+sparknlp/partition/partition_transformer.py
 sparknlp/pretrained/__init__.py
 sparknlp/pretrained/pretrained_pipeline.py
 sparknlp/pretrained/resource_downloader.py

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/sparknlp/__init__.py

@@ -66,6 +66,8 @@ sys.modules['com.johnsnowlabs.ml.ai'] = annotator
 annotators = annotator
 embeddings = annotator
 
+__version__ = "6.0.2"
+
 
 def start(gpu=False,
           apple_silicon=False,
@@ -132,7 +134,7 @@ def start(gpu=False,
         The initiated Spark session.
 
     """
-    current_version = "6.0.1"
+    current_version = __version__
 
     if params is None:
         params = {}
@@ -316,4 +318,4 @@ def version():
     str
         The current Spark NLP version.
     """
-    return '6.0.1'
+    return __version__

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/sparknlp/annotator/cv/__init__.py

@@ -25,3 +25,5 @@ from sparknlp.annotator.cv.phi3_vision_for_multimodal import *
 from sparknlp.annotator.cv.smolvlm_transformer import *
 from sparknlp.annotator.cv.paligemma_for_multimodal import *
 from sparknlp.annotator.cv.gemma3_for_multimodal import *
+from sparknlp.annotator.cv.internvl_for_multimodal import *
+from sparknlp.annotator.cv.florence2_transformer import *

spark_nlp-6.0.2/sparknlp/annotator/cv/florence2_transformer.py

@@ -0,0 +1,180 @@
+#  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.
+
+from sparknlp.common import *
+
+class Florence2Transformer(AnnotatorModel,
+                 HasBatchedAnnotateImage,
+                 HasImageFeatureProperties,
+                 HasEngine):
+    """Florence2Transformer can load Florence-2 models for a variety of vision and vision-language tasks using prompt-based inference.
+
+    The model supports image captioning, object detection, segmentation, OCR, and more, using prompt tokens as described in the Florence-2 documentation.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion object:
+
+    >>> florence2 = Florence2Transformer.pretrained() \
+    ...     .setInputCols(["image_assembler"]) \
+    ...     .setOutputCol("answer")
+
+    The default model is ``"florence2_base_ft_int4"``, if no name is provided.
+
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models?task=Vision+Tasks>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``IMAGE``              ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more memory, by default 2
+    maxOutputLength
+        Maximum length of output text, by default 200
+    minOutputLength
+        Minimum length of the sequence to be generated, by default 10
+    doSample
+        Whether or not to use sampling; use greedy decoding otherwise, by default False
+    temperature
+        The value used to module the next token probabilities, by default 1.0
+    topK
+        The number of highest probability vocabulary tokens to keep for top-k-filtering, by default 50
+    topP
+        If set to float < 1, only the most probable tokens with probabilities that add up to ``top_p`` or higher are kept for generation, by default 1.0
+    repetitionPenalty
+        The parameter for repetition penalty. 1.0 means no penalty, by default 1.0
+    noRepeatNgramSize
+        If set to int > 0, all ngrams of that size can only occur once, by default 3
+    ignoreTokenIds
+        A list of token ids which are ignored in the decoder's output, by default []
+    beamSize
+        The Number of beams for beam search, by default 1
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> image_df = spark.read.format("image").load(path=images_path)
+    >>> test_df = image_df.withColumn("text", lit("<OD>"))
+    >>> imageAssembler = ImageAssembler() \
+    ...     .setInputCol("image") \
+    ...     .setOutputCol("image_assembler")
+    >>> florence2 = Florence2Transformer.pretrained() \
+    ...     .setInputCols(["image_assembler"]) \
+    ...     .setOutputCol("answer")
+    >>> pipeline = Pipeline().setStages([
+    ...     imageAssembler,
+    ...     florence2
+    ... ])
+    >>> result = pipeline.fit(test_df).transform(test_df)
+    >>> result.select("image_assembler.origin", "answer.result").show(False)
+    """
+
+    name = "Florence2Transformer"
+
+    inputAnnotatorTypes = [AnnotatorType.IMAGE]
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    minOutputLength = Param(Params._dummy(), "minOutputLength", "Minimum length of the sequence to be generated", typeConverter=TypeConverters.toInt)
+    maxOutputLength = Param(Params._dummy(), "maxOutputLength", "Maximum length of output text", typeConverter=TypeConverters.toInt)
+    doSample = Param(Params._dummy(), "doSample", "Whether or not to use sampling; use greedy decoding otherwise", typeConverter=TypeConverters.toBoolean)
+    temperature = Param(Params._dummy(), "temperature", "The value used to module the next token probabilities", typeConverter=TypeConverters.toFloat)
+    topK = Param(Params._dummy(), "topK", "The number of highest probability vocabulary tokens to keep for top-k-filtering", typeConverter=TypeConverters.toInt)
+    topP = Param(Params._dummy(), "topP", "If set to float < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation", typeConverter=TypeConverters.toFloat)
+    repetitionPenalty = Param(Params._dummy(), "repetitionPenalty", "The parameter for repetition penalty. 1.0 means no penalty.", typeConverter=TypeConverters.toFloat)
+    noRepeatNgramSize = Param(Params._dummy(), "noRepeatNgramSize", "If set to int > 0, all ngrams of that size can only occur once", typeConverter=TypeConverters.toInt)
+    ignoreTokenIds = Param(Params._dummy(), "ignoreTokenIds", "A list of token ids which are ignored in the decoder's output", typeConverter=TypeConverters.toListInt)
+    beamSize = Param(Params._dummy(), "beamSize", "The Number of beams for beam search.", typeConverter=TypeConverters.toInt)
+    batchSize = Param(Params._dummy(), "batchSize", "Batch size. Large values allows faster processing but requires more memory", typeConverter=TypeConverters.toInt)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.cv.Florence2Transformer", java_model=None):
+        super(Florence2Transformer, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=2,
+            minOutputLength=10,
+            maxOutputLength=200,
+            doSample=False,
+            temperature=1.0,
+            topK=50,
+            topP=1.0,
+            repetitionPenalty=1.0,
+            noRepeatNgramSize=3,
+            ignoreTokenIds=[],
+            beamSize=1,
+        )
+
+    def setMinOutputLength(self, value):
+        """Sets minimum length of the sequence to be generated."""
+        return self._set(minOutputLength=value)
+
+    def setMaxOutputLength(self, value):
+        """Sets maximum length of output text."""
+        return self._set(maxOutputLength=value)
+
+    def setDoSample(self, value):
+        """Sets whether or not to use sampling; use greedy decoding otherwise."""
+        return self._set(doSample=value)
+
+    def setTemperature(self, value):
+        """Sets the value used to module the next token probabilities."""
+        return self._set(temperature=value)
+
+    def setTopK(self, value):
+        """Sets the number of highest probability vocabulary tokens to keep for top-k-filtering."""
+        return self._set(topK=value)
+
+    def setTopP(self, value):
+        """Sets the top cumulative probability for vocabulary tokens."""
+        return self._set(topP=value)
+
+    def setRepetitionPenalty(self, value):
+        """Sets the parameter for repetition penalty. 1.0 means no penalty."""
+        return self._set(repetitionPenalty=value)
+
+    def setNoRepeatNgramSize(self, value):
+        """Sets size of n-grams that can only occur once."""
+        return self._set(noRepeatNgramSize=value)
+
+    def setIgnoreTokenIds(self, value):
+        """A list of token ids which are ignored in the decoder's output."""
+        return self._set(ignoreTokenIds=value)
+
+    def setBeamSize(self, value):
+        """Sets the number of beams for beam search."""
+        return self._set(beamSize=value)
+
+    def setBatchSize(self, value):
+        """Sets the batch size."""
+        return self._set(batchSize=value)
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session, use_openvino=False):
+        """Loads a locally saved model."""
+        from sparknlp.internal import _Florence2TransformerLoader
+        jModel = _Florence2TransformerLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
+        return Florence2Transformer(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="florence2_base_ft_int4", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model."""
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(Florence2Transformer, name, lang, remote_loc) 

{spark_nlp-6.0.1 → spark_nlp-6.0.2}/sparknlp/annotator/cv/gemma3_for_multimodal.py

@@ -83,23 +83,18 @@ class Gemma3ForMultiModal(AnnotatorModel,
     >>> from sparknlp.annotator import *
     >>> from pyspark.ml import Pipeline
     >>> from pyspark.sql.functions import lit
-    >>> 
     >>> imageDF = spark.read.format("image").load(images_path)
-    >>> testDF = imageDF.withColumn("text", lit("<bos><start_of_turn>user\nYou are a helpful assistant.\n\n<start_of_image>Describe this image in detail.<end_of_turn>\n<start_of_turn>model\n"))
-    >>> 
-    >>> imageAssembler = ImageAssembler() \
-    ...     .setInputCol("image") \
+    >>> testDF = imageDF.withColumn("text", lit("<bos><start_of_turn>user\\nYou are a helpful assistant.\\n\\n<start_of_image>Describe this image in detail.<end_of_turn>\\n<start_of_turn>model\\n"))
+    >>> imageAssembler = ImageAssembler() \\
+    ...     .setInputCol("image") \\
     ...     .setOutputCol("image_assembler")
-    >>> 
-    >>> visualQA = Gemma3ForMultiModal.pretrained() \
-    ...     .setInputCols("image_assembler") \
+    >>> visualQA = Gemma3ForMultiModal.pretrained() \\
+    ...     .setInputCols("image_assembler") \\
     ...     .setOutputCol("answer")
-    >>> 
     >>> pipeline = Pipeline().setStages([
     ...     imageAssembler,
     ...     visualQA
     ... ])
-    >>> 
     >>> result = pipeline.fit(testDF).transform(testDF)
     >>> result.select("image_assembler.origin", "answer.result").show(truncate=False)
     """