spark-nlp 4.2.6__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/annotator/embeddings/sentence_embeddings.py

@@ -25,8 +25,8 @@ class SentenceEmbeddings(AnnotatorModel, HasEmbeddingsProperties, HasStorageRef)
     This can be configured with :meth:`.setPoolingStrategy`, which either be
     ``"AVERAGE"`` or ``"SUM"``.
 
-    For more extended examples see the `Spark NLP Workshop
-    <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Public/5.1_Text_classification_examples_in_SparkML_SparkNLP.ipynb>`__..
+    For more extended examples see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/text/english/text-similarity/Spark_NLP_Spark_ML_Text_Similarity.ipynb>`__..
 
     ============================= =======================
     Input Annotation types        Output Annotation type
@@ -132,4 +132,3 @@ class SentenceEmbeddings(AnnotatorModel, HasEmbeddingsProperties, HasStorageRef)
             return self._set(poolingStrategy=strategy)
         else:
             return self._set(poolingStrategy="AVERAGE")
-

sparknlp/annotator/embeddings/snowflake_embeddings.py

@@ -0,0 +1,202 @@
+#  Copyright 2017-2022 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 SnowFlakeEmbeddings."""
+
+from sparknlp.common import *
+
+
+class SnowFlakeEmbeddings(AnnotatorModel,
+					HasEmbeddingsProperties,
+					HasCaseSensitiveProperties,
+					HasStorageRef,
+					HasBatchedAnnotate,
+					HasMaxSentenceLengthLimit):
+	"""Sentence embeddings using SnowFlake.
+
+    snowflake-arctic-embed is a suite of text embedding models that focuses on creating
+    high-quality retrieval models optimized for performance.
+
+	Pretrained models can be loaded with :meth:`.pretrained` of the companion
+	object:
+
+	>>> embeddings = SnowFlakeEmbeddings.pretrained() \\
+	...     .setInputCols(["document"]) \\
+	...     .setOutputCol("SnowFlake_embeddings")
+
+
+	The default model is ``"snowflake_artic_m"``, if no name is provided.
+
+	For available pretrained models please see the
+	`Models Hub <https://sparknlp.org/models?q=SnowFlake>`__.
+
+
+	====================== ======================
+	Input Annotation types Output Annotation type
+	====================== ======================
+	``DOCUMENT``            ``SENTENCE_EMBEDDINGS``
+	====================== ======================
+
+	**References**
+
+	`Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models <https://arxiv.org/abs/2405.05374>`__
+	`Snowflake Arctic-Embed Models <https://github.com/Snowflake-Labs/arctic-embed>`__
+
+	**Paper abstract**
+
+	*The models are trained by leveraging existing open-source text representation models, such
+     as bert-base-uncased, and are trained in a multi-stage pipeline to optimize their retrieval
+     performance. First, the models are trained with large batches of query-document pairs where
+     negatives are derived in-batch—pretraining leverages about 400m samples of a mix of public
+     datasets and proprietary web search data. Following pretraining models are further optimized
+     with long training on a smaller dataset (about 1m samples) of triplets of query, positive
+     document, and negative document derived from hard harmful mining. Mining of the negatives and
+     data curation is crucial to retrieval accuracy. A detailed technical report will be available
+     shortly. *
+
+	Parameters
+	----------
+	batchSize
+		Size of every batch , by default 8
+	dimension
+		Number of embedding dimensions, by default 768
+	caseSensitive
+		Whether to ignore case in tokens for embeddings matching, by default False
+	maxSentenceLength
+		Max sentence length to process, by default 512
+	configProtoBytes
+		ConfigProto from tensorflow, serialized into byte array.
+
+
+	Examples
+	--------
+	>>> import sparknlp
+	>>> from sparknlp.base import *
+	>>> from sparknlp.annotator import *
+	>>> from pyspark.ml import Pipeline
+	>>> documentAssembler = DocumentAssembler() \\
+	...     .setInputCol("text") \\
+	...     .setOutputCol("document")
+	>>> embeddings = SnowFlakeEmbeddings.pretrained() \\
+	...     .setInputCols(["document"]) \\
+	...     .setOutputCol("embeddings")
+	>>> embeddingsFinisher = EmbeddingsFinisher() \\
+	...     .setInputCols("embeddings") \\
+	...     .setOutputCols("finished_embeddings") \\
+	...     .setOutputAsVector(True)
+	>>> pipeline = Pipeline().setStages([
+	...     documentAssembler,
+	...     embeddings,
+	...     embeddingsFinisher
+	... ])
+	>>> data = spark.createDataFrame([["hello world", "hello moon"]]).toDF("text")
+	>>> result = pipeline.fit(data).transform(data)
+	>>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+	+--------------------------------------------------------------------------------+
+	|                                                                          result|
+	+--------------------------------------------------------------------------------+
+	|[0.50387806, 0.5861606, 0.35129607, -0.76046336, -0.32446072, -0.117674336, 0...|
+	|[0.6660665, 0.961762, 0.24854276, -0.1018044, -0.6569202, 0.027635604, 0.1915...|
+	+--------------------------------------------------------------------------------+
+	"""
+
+	name = "SnowFlakeEmbeddings"
+
+	inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+	outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
+	poolingStrategy = Param(Params._dummy(),
+							"poolingStrategy",
+							"Pooling strategy to use for sentence embeddings",
+							TypeConverters.toString)
+
+	def setPoolingStrategy(self, value):
+		"""Pooling strategy to use for sentence embeddings.
+
+		Available pooling strategies for sentence embeddings are:
+		  - `"cls"`: leading `[CLS]` token
+		  - `"cls_avg"`: leading `[CLS]` token + mean of all other tokens
+		  - `"last"`: embeddings of the last token in the sequence
+		  - `"avg"`: mean of all tokens
+		  - `"max"`: max of all embedding features of the entire token sequence
+		  - `"int"`: An integer number, which represents the index of the token to use as the
+			embedding
+
+		Parameters
+		----------
+		value : str
+			Pooling strategy to use for sentence embeddings
+		"""
+
+		valid_strategies = {"cls", "cls_avg", "last", "avg", "max"}
+		if value in valid_strategies or value.isdigit():
+			return self._set(poolingStrategy=value)
+		else:
+			raise ValueError(f"Invalid pooling strategy: {value}. "
+							 f"Valid strategies are: {', '.join(self.valid_strategies)} or an integer.")
+
+	@keyword_only
+	def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.SnowFlakeEmbeddings", java_model=None):
+		super(SnowFlakeEmbeddings, self).__init__(
+			classname=classname,
+			java_model=java_model
+		)
+		self._setDefault(
+			dimension=1024,
+			batchSize=8,
+			maxSentenceLength=512,
+			caseSensitive=False,
+			poolingStrategy="cls"
+		)
+
+	@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
+		-------
+		SnowFlakeEmbeddings
+			The restored model
+		"""
+		from sparknlp.internal import _SnowFlakeEmbeddingsLoader
+		jModel = _SnowFlakeEmbeddingsLoader(folder, spark_session._jsparkSession)._java_obj
+		return SnowFlakeEmbeddings(java_model=jModel)
+
+	@staticmethod
+	def pretrained(name="snowflake_artic_m", lang="en", remote_loc=None):
+		"""Downloads and loads a pretrained model.
+
+		Parameters
+		----------
+		name : str, optional
+			Name of the pretrained model, by default "snowflake_artic_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
+		-------
+		SnowFlakeEmbeddings
+			The restored model
+		"""
+		from sparknlp.pretrained import ResourceDownloader
+		return ResourceDownloader.downloadModel(SnowFlakeEmbeddings, name, lang, remote_loc)

sparknlp/annotator/embeddings/uae_embeddings.py

@@ -0,0 +1,211 @@
+#  Copyright 2017-2022 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 UAEEmbeddings."""
+
+from sparknlp.common import *
+
+
+class UAEEmbeddings(AnnotatorModel,
+                    HasEmbeddingsProperties,
+                    HasCaseSensitiveProperties,
+                    HasStorageRef,
+                    HasBatchedAnnotate,
+                    HasMaxSentenceLengthLimit):
+    """Sentence embeddings using Universal AnglE Embedding (UAE).
+
+    UAE is a novel angle-optimized text embedding model, designed to improve semantic textual
+    similarity tasks, which are crucial for Large Language Model (LLM) applications. By
+    introducing angle optimization in a complex space, AnglE effectively mitigates saturation of
+    the cosine similarity function.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> embeddings = UAEEmbeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("UAE_embeddings")
+
+
+    The default model is ``"uae_large_v1"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?q=UAE>`__.
+
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT``            ``SENTENCE_EMBEDDINGS``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Size of every batch , by default 8
+    dimension
+        Number of embedding dimensions, by default 768
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default False
+    maxSentenceLength
+        Max sentence length to process, by default 512
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+
+    References
+    ----------
+
+    `AnglE-optimized Text Embeddings <https://arxiv.org/abs/2309.12871>`__
+    `UAE Github Repository <https://github.com/baochi0212/uae-embedding>`__
+
+    **Paper abstract**
+
+    *High-quality text embedding is pivotal in improving semantic textual similarity (STS) tasks,
+    which are crucial components in Large Language Model (LLM) applications. However, a common
+    challenge existing text embedding models face is the problem of vanishing gradients, primarily
+    due to their reliance on the cosine function in the optimization objective, which has
+    saturation zones. To address this issue, this paper proposes a novel angle-optimized text
+    embedding model called AnglE. The core idea of AnglE is to introduce angle optimization in a
+    complex space. This novel approach effectively mitigates the adverse effects of the saturation
+    zone in the cosine function, which can impede gradient and hinder optimization processes. To
+    set up a comprehensive STS evaluation, we experimented on existing short-text STS datasets and
+    a newly collected long-text STS dataset from GitHub Issues. Furthermore, we examine
+    domain-specific STS scenarios with limited labeled data and explore how AnglE works with
+    LLM-annotated data. Extensive experiments were conducted on various tasks including short-text
+    STS, long-text STS, and domain-specific STS tasks. The results show that AnglE outperforms the
+    state-of-the-art (SOTA) STS models that ignore the cosine saturation zone. These findings
+    demonstrate the ability of AnglE to generate high-quality text embeddings and the usefulness
+    of angle optimization in STS.*
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> embeddings = UAEEmbeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("embeddings")
+    >>> embeddingsFinisher = EmbeddingsFinisher() \\
+    ...     .setInputCols("embeddings") \\
+    ...     .setOutputCols("finished_embeddings") \\
+    ...     .setOutputAsVector(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     embeddings,
+    ...     embeddingsFinisher
+    ... ])
+    >>> data = spark.createDataFrame([["hello world", "hello moon"]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+    +--------------------------------------------------------------------------------+
+    |                                                                          result|
+    +--------------------------------------------------------------------------------+
+    |[0.50387806, 0.5861606, 0.35129607, -0.76046336, -0.32446072, -0.117674336, 0...|
+    |[0.6660665, 0.961762, 0.24854276, -0.1018044, -0.6569202, 0.027635604, 0.1915...|
+    +--------------------------------------------------------------------------------+
+    """
+
+    name = "UAEEmbeddings"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
+    poolingStrategy = Param(Params._dummy(),
+                            "poolingStrategy",
+                            "Pooling strategy to use for sentence embeddings",
+                            TypeConverters.toString)
+
+    def setPoolingStrategy(self, value):
+        """Pooling strategy to use for sentence embeddings.
+
+        Available pooling strategies for sentence embeddings are:
+          - `"cls"`: leading `[CLS]` token
+          - `"cls_avg"`: leading `[CLS]` token + mean of all other tokens
+          - `"last"`: embeddings of the last token in the sequence
+          - `"avg"`: mean of all tokens
+          - `"max"`: max of all embedding features of the entire token sequence
+          - `"int"`: An integer number, which represents the index of the token to use as the
+            embedding
+
+        Parameters
+        ----------
+        value : str
+            Pooling strategy to use for sentence embeddings
+        """
+
+        valid_strategies = {"cls", "cls_avg", "last", "avg", "max"}
+        if value in valid_strategies or value.isdigit():
+            return self._set(poolingStrategy=value)
+        else:
+            raise ValueError(f"Invalid pooling strategy: {value}. "
+                             f"Valid strategies are: {', '.join(self.valid_strategies)} or an integer.")
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.UAEEmbeddings", java_model=None):
+        super(UAEEmbeddings, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            dimension=1024,
+            batchSize=8,
+            maxSentenceLength=512,
+            caseSensitive=False,
+            poolingStrategy="cls"
+        )
+
+    @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
+        -------
+        UAEEmbeddings
+            The restored model
+        """
+        from sparknlp.internal import _UAEEmbeddingsLoader
+        jModel = _UAEEmbeddingsLoader(folder, spark_session._jsparkSession)._java_obj
+        return UAEEmbeddings(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="uae_large_v1", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "UAE_small"
+        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
+        -------
+        UAEEmbeddings
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(UAEEmbeddings, name, lang, remote_loc)

sparknlp/annotator/embeddings/universal_sentence_encoder.py

@@ -35,10 +35,10 @@ class UniversalSentenceEncoder(AnnotatorModel,
 
     The default model is ``"tfhub_use"``, if no name is provided. For available
     pretrained models please see the `Models Hub
-    <https://nlp.johnsnowlabs.com/models?task=Embeddings>`__.
+    <https://sparknlp.org/models?task=Embeddings>`__.
 
-    For extended examples of usage, see the `Spark NLP Workshop
-    <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Public/3.SparkNLP_Pretrained_Models.ipynb>`__.
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/classification/ClassifierDL_Train_multi_class_news_category_classifier.ipynb>`__.
 
     ====================== =======================
     Input Annotation types Output Annotation type

sparknlp/annotator/embeddings/word2vec.py

@@ -32,7 +32,7 @@ class Word2VecApproach(AnnotatorApproach, HasStorageRef, HasEnableCachingPropert
 
     For instantiated/pretrained models, see :class:`.Word2VecModel`.
 
-    For available pretrained models please see the `Models Hub <https://nlp.johnsnowlabs.com/models>`__.
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models>`__.
 
     ====================== =======================
     Input Annotation types Output Annotation type
@@ -345,3 +345,9 @@ class Word2VecModel(AnnotatorModel, HasStorageRef, HasEmbeddingsProperties):
         from sparknlp.pretrained import ResourceDownloader
         return ResourceDownloader.downloadModel(Word2VecModel, name, lang, remote_loc)
 
+    def getVectors(self):
+        """
+        Returns the vector representation of the words as a dataframe
+        with two fields, word and vector.
+        """
+        return self._call_java("getVectors")

sparknlp/annotator/embeddings/word_embeddings.py

@@ -41,8 +41,8 @@ class WordEmbeddings(AnnotatorApproach, HasEmbeddingsProperties, HasStorage):
     :meth:`WordEmbeddingsModel.overallCoverage()
     <sparknlp.annotator.WordEmbeddingsModel.overallCoverage>`.
 
-    For extended examples of usage, see the `Spark NLP Workshop
-    <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Public/3.SparkNLP_Pretrained_Models.ipynb>`__.
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/scala/training/NerDL/win/customNerDlPipeline/CustomForNerDLPipeline.java>`__.
 
     ====================== ======================
     Input Annotation types Output Annotation type
@@ -177,9 +177,9 @@ class WordEmbeddingsModel(AnnotatorModel, HasEmbeddingsProperties, HasStorageMod
 
     The default model is ``"glove_100d"``, if no name is provided. For available
     pretrained models please see the `Models Hub
-    <https://nlp.johnsnowlabs.com/models?task=Embeddings>`__.
+    <https://sparknlp.org/models?task=Embeddings>`__.
 
-    For extended examples of usage, see the `Spark NLP Workshop <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Public/3.SparkNLP_Pretrained_Models.ipynb>`__.
+    For extended examples of usage, see the `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/quick_start_offline.ipynb>`__.
 
     ====================== ======================
     Input Annotation types Output Annotation type
@@ -383,4 +383,3 @@ class WordEmbeddingsModel(AnnotatorModel, HasEmbeddingsProperties, HasStorageMod
             Identifiers for the model parameters
         """
         HasStorageModel.loadStorages(path, spark, storage_ref, WordEmbeddingsModel.databases)
-

sparknlp/annotator/embeddings/xlm_roberta_embeddings.py

@@ -21,7 +21,8 @@ class XlmRoBertaEmbeddings(AnnotatorModel,
                            HasCaseSensitiveProperties,
                            HasStorageRef,
                            HasBatchedAnnotate,
-                           HasEngine):
+                           HasEngine,
+                           HasMaxSentenceLengthLimit):
     """The XLM-RoBERTa model was proposed in `Unsupervised Cross-lingual
     Representation Learning at Scale` by Alexis Conneau, Kartikay Khandelwal,
     Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzman, Edouard
@@ -40,10 +41,10 @@ class XlmRoBertaEmbeddings(AnnotatorModel,
     The default model is ``"xlm_roberta_base"``, default language is ``"xx"``
     (meaning multi-lingual), if no values are provided. For available pretrained
     models please see the `Models Hub
-    <https://nlp.johnsnowlabs.com/models?task=Embeddings>`__.
+    <https://sparknlp.org/models?task=Embeddings>`__.
 
-    For extended examples of usage, see the `Spark NLP Workshop
-    <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/jupyter/transformers/HuggingFace%20in%20Spark%20NLP%20-%20XLM-RoBERTa.ipynb>`__.
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/transformers/HuggingFace%20in%20Spark%20NLP%20-%20XLM-RoBERTa.ipynb>`__.
     To see which models are compatible and how to import them see
     `Import Transformers into Spark NLP 🚀
     <https://github.com/JohnSnowLabs/spark-nlp/discussions/5669>`_.
@@ -151,11 +152,6 @@ class XlmRoBertaEmbeddings(AnnotatorModel,
 
     outputAnnotatorType = AnnotatorType.WORD_EMBEDDINGS
 
-    maxSentenceLength = Param(Params._dummy(),
-                              "maxSentenceLength",
-                              "Max sentence length to process",
-                              typeConverter=TypeConverters.toInt)
-
     configProtoBytes = Param(Params._dummy(),
                              "configProtoBytes",
                              "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
@@ -171,16 +167,6 @@ class XlmRoBertaEmbeddings(AnnotatorModel,
         """
         return self._set(configProtoBytes=b)
 
-    def setMaxSentenceLength(self, value):
-        """Sets max sentence length to process.
-
-        Parameters
-        ----------
-        value : int
-            Max sentence length to process
-        """
-        return self._set(maxSentenceLength=value)
-
     @keyword_only
     def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.XlmRoBertaEmbeddings", java_model=None):
         super(XlmRoBertaEmbeddings, self).__init__(
@@ -195,7 +181,7 @@ class XlmRoBertaEmbeddings(AnnotatorModel,
         )
 
     @staticmethod
-    def loadSavedModel(folder, spark_session):
+    def loadSavedModel(folder, spark_session, use_openvino=False):
         """Loads a locally saved model.
 
         Parameters
@@ -204,6 +190,8 @@ class XlmRoBertaEmbeddings(AnnotatorModel,
             Folder of the saved model
         spark_session : pyspark.sql.SparkSession
             The current SparkSession
+        use_openvino: bool
+            Use OpenVINO backend
 
         Returns
         -------
@@ -211,7 +199,7 @@ class XlmRoBertaEmbeddings(AnnotatorModel,
             The restored model
         """
         from sparknlp.internal import _XlmRoBertaLoader
-        jModel = _XlmRoBertaLoader(folder, spark_session._jsparkSession)._java_obj
+        jModel = _XlmRoBertaLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
         return XlmRoBertaEmbeddings(java_model=jModel)
 
     @staticmethod

sparknlp/annotator/embeddings/xlm_roberta_sentence_embeddings.py

@@ -17,11 +17,12 @@ from sparknlp.common import *
 
 
 class XlmRoBertaSentenceEmbeddings(AnnotatorModel,
-                                   HasEmbeddingsProperties,
-                                   HasCaseSensitiveProperties,
-                                   HasStorageRef,
-                                   HasBatchedAnnotate,
-                                   HasEngine):
+                                        HasEmbeddingsProperties,
+                                        HasCaseSensitiveProperties,
+                                        HasStorageRef,
+                                        HasBatchedAnnotate,
+                                        HasEngine,
+                                        HasMaxSentenceLengthLimit):
     """Sentence-level embeddings using XLM-RoBERTa. The XLM-RoBERTa model was proposed in Unsupervised Cross-lingual
     Representation Learning at Scale  by Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary,
     Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer and Veselin Stoyanov. It is based
@@ -39,7 +40,7 @@ class XlmRoBertaSentenceEmbeddings(AnnotatorModel,
     The default model is ``"sent_xlm_roberta_base"``, if no name is provided.
 
     For available pretrained models please see the
-    `Models Hub <https://nlp.johnsnowlabs.com/models?task=Embeddings>`__.
+    `Models Hub <https://sparknlp.org/models?task=Embeddings>`__.
 
     ====================== =======================
     Input Annotation types Output Annotation type
@@ -122,11 +123,6 @@ class XlmRoBertaSentenceEmbeddings(AnnotatorModel,
 
     outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
 
-    maxSentenceLength = Param(Params._dummy(),
-                              "maxSentenceLength",
-                              "Max sentence length to process",
-                              typeConverter=TypeConverters.toInt)
-
     configProtoBytes = Param(Params._dummy(),
                              "configProtoBytes",
                              "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
@@ -142,16 +138,6 @@ class XlmRoBertaSentenceEmbeddings(AnnotatorModel,
         """
         return self._set(configProtoBytes=b)
 
-    def setMaxSentenceLength(self, value):
-        """Sets max sentence length to process.
-
-        Parameters
-        ----------
-        value : int
-            Max sentence length to process
-        """
-        return self._set(maxSentenceLength=value)
-
     @keyword_only
     def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.XlmRoBertaSentenceEmbeddings", java_model=None):
         super(XlmRoBertaSentenceEmbeddings, self).__init__(

sparknlp/annotator/embeddings/xlnet_embeddings.py

@@ -21,7 +21,8 @@ class XlnetEmbeddings(AnnotatorModel,
                       HasCaseSensitiveProperties,
                       HasStorageRef,
                       HasBatchedAnnotate,
-                      HasEngine):
+                      HasEngine,
+                      HasMaxSentenceLengthLimit):
     """XlnetEmbeddings (XLNet): Generalized Autoregressive Pretraining for
     Language Understanding
 
@@ -53,8 +54,8 @@ class XlnetEmbeddings(AnnotatorModel,
 
     The default model is ``"xlnet_base_cased"``, if no name is provided.
 
-    For extended examples of usage, see the `Spark NLP Workshop
-    <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/jupyter/training/english/dl-ner/ner_xlnet.ipynb>`__.
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/dl-ner/ner_xlnet.ipynb>`__.
     To see which models are compatible and how to import them see
     `Import Transformers into Spark NLP 🚀
     <https://github.com/JohnSnowLabs/spark-nlp/discussions/5669>`_.
@@ -160,11 +161,6 @@ class XlnetEmbeddings(AnnotatorModel,
                              "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
                              TypeConverters.toListInt)
 
-    maxSentenceLength = Param(Params._dummy(),
-                              "maxSentenceLength",
-                              "Max sentence length to process",
-                              typeConverter=TypeConverters.toInt)
-
     def setConfigProtoBytes(self, b):
         """Sets configProto from tensorflow, serialized into byte array.
 
@@ -175,16 +171,6 @@ class XlnetEmbeddings(AnnotatorModel,
         """
         return self._set(configProtoBytes=b)
 
-    def setMaxSentenceLength(self, value):
-        """Sets max sentence length to process.
-
-        Parameters
-        ----------
-        value : int
-            Max sentence length to process
-        """
-        return self._set(maxSentenceLength=value)
-
     @keyword_only
     def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.XlnetEmbeddings", java_model=None):
         super(XlnetEmbeddings, self).__init__(