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

sparknlp/annotator/embeddings/bert_sentence_embeddings.py

@@ -17,11 +17,12 @@ from sparknlp.common import *
 
 
 class BertSentenceEmbeddings(AnnotatorModel,
-                             HasEmbeddingsProperties,
-                             HasCaseSensitiveProperties,
-                             HasStorageRef,
-                             HasBatchedAnnotate,
-                             HasEngine):
+                                  HasEmbeddingsProperties,
+                                  HasCaseSensitiveProperties,
+                                  HasStorageRef,
+                                  HasBatchedAnnotate,
+                                  HasEngine,
+                                  HasMaxSentenceLengthLimit):
     """Sentence-level embeddings using BERT. BERT (Bidirectional Encoder
     Representations from Transformers) provides dense vector representations for
     natural language by using a deep, pre-trained neural network with the
@@ -38,10 +39,10 @@ class BertSentenceEmbeddings(AnnotatorModel,
     The default model is ``"sent_small_bert_L2_768"``, 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>`__.
 
     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-%20BERT%20Sentence.ipynb>`__.
+    `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/transformers/HuggingFace%20in%20Spark%20NLP%20-%20BERT%20Sentence.ipynb>`__.
 
     ====================== =======================
     Input Annotation types Output Annotation type
@@ -133,11 +134,6 @@ class BertSentenceEmbeddings(AnnotatorModel,
 
     outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
 
-    maxSentenceLength = Param(Params._dummy(),
-                              "maxSentenceLength",
-                              "Max sentence length to process",
-                              typeConverter=TypeConverters.toInt)
-
     isLong = Param(Params._dummy(),
                    "isLong",
                    "Use Long type instead of Int type for inputs buffer - Some Bert models require Long instead of Int.",
@@ -158,16 +154,6 @@ class BertSentenceEmbeddings(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)
-
     def setIsLong(self, value):
         """Sets whether to use Long type instead of Int type for inputs buffer.
 
@@ -194,7 +180,7 @@ class BertSentenceEmbeddings(AnnotatorModel,
         )
 
     @staticmethod
-    def loadSavedModel(folder, spark_session):
+    def loadSavedModel(folder, spark_session, use_openvino=False):
         """Loads a locally saved model.
 
         Parameters
@@ -203,6 +189,8 @@ class BertSentenceEmbeddings(AnnotatorModel,
             Folder of the saved model
         spark_session : pyspark.sql.SparkSession
             The current SparkSession
+        use_openvino: bool
+            Use OpenVINO backend
 
         Returns
         -------
@@ -210,7 +198,7 @@ class BertSentenceEmbeddings(AnnotatorModel,
             The restored model
         """
         from sparknlp.internal import _BertSentenceLoader
-        jModel = _BertSentenceLoader(folder, spark_session._jsparkSession)._java_obj
+        jModel = _BertSentenceLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
         return BertSentenceEmbeddings(java_model=jModel)
 
     @staticmethod

sparknlp/annotator/embeddings/bge_embeddings.py

@@ -0,0 +1,199 @@
+#  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 BGEEmbeddings."""
+
+from sparknlp.common import *
+
+
+class BGEEmbeddings(AnnotatorModel,
+                    HasEmbeddingsProperties,
+                    HasCaseSensitiveProperties,
+                    HasStorageRef,
+                    HasBatchedAnnotate,
+                    HasMaxSentenceLengthLimit,
+                    HasClsTokenProperties):
+    """Sentence embeddings using BGE.
+
+   BGE, or BAAI General Embeddings, a model that can map any text to a low-dimensional dense 
+  vector which can be used for tasks like retrieval, classification, clustering, or semantic search.
+
+  Note that this annotator is only supported for Spark Versions 3.4 and up.
+  
+  Pretrained models can be loaded with `pretrained` of the companion object:
+
+    >>> embeddings = BGEEmbeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("bge_embeddings")
+
+
+    The default model is ``"bge_base"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?q=BGE>`__.
+
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT``            ``SENTENCE_EMBEDDINGS``
+    ====================== ======================
+
+    
+    **References**
+    
+    `C-Pack: Packaged Resources To Advance General Chinese Embedding <https://arxiv.org/pdf/2309.07597>`__
+    `BGE Github Repository <https://github.com/FlagOpen/FlagEmbedding>`__
+
+    **Paper abstract**
+
+    *We introduce C-Pack, a package of resources that significantly advance the field of general
+    Chinese embeddings. C-Pack includes three critical resources. 
+    1) C-MTEB is a comprehensive benchmark for Chinese text embeddings covering 6 tasks and 35 datasets.
+    2) C-MTP is a massive text embedding dataset curated from labeled and unlabeled Chinese corpora
+    for training embedding models.
+    3) C-TEM is a family of embedding models covering multiple sizes.
+    Our models outperform all prior Chinese text embeddings on C-MTEB by up to +10% upon the 
+    time of the release. We also integrate and optimize the entire suite of training methods for
+    C-TEM. Along with our resources on general Chinese embedding, we release our data and models for
+    English text embeddings. The English models achieve stateof-the-art performance on the MTEB
+    benchmark; meanwhile, our released English data is 2 times larger than the Chinese data. All
+    these resources are made publicly available at https://github.com/FlagOpen/FlagEmbedding.*
+
+
+    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.
+    useCLSToken
+        Whether to use the CLS token for sentence embeddings, by default True
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> embeddings = BGEEmbeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("bge_embeddings")
+    >>> embeddingsFinisher = EmbeddingsFinisher() \\
+    ...     .setInputCols(["bge_embeddings"]) \\
+    ...     .setOutputCols("finished_embeddings") \\
+    ...     .setOutputAsVector(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     embeddings,
+    ...     embeddingsFinisher
+    ... ])
+    >>> data = spark.createDataFrame([["query: how much protein should a female eat",
+    ... "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day." + \\
+    ... "But, as you can see from this chart, you'll need to increase that if you're expecting or training for a" + \\
+    ... "marathon. Check out the chart below to see how much protein you should be eating each day.",
+    ... ]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+    +--------------------------------------------------------------------------------+
+    |                                                                          result|
+    +--------------------------------------------------------------------------------+
+    |[[8.0190285E-4, -0.005974853, -0.072875895, 0.007944068, 0.026059335, -0.0080...|
+    |[[0.050514214, 0.010061974, -0.04340176, -0.020937217, 0.05170225, 0.01157857...|
+    +--------------------------------------------------------------------------------+
+    """
+
+    name = "BGEEmbeddings"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.BGEEmbeddings", java_model=None):
+        super(BGEEmbeddings, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            dimension=768,
+            batchSize=8,
+            maxSentenceLength=512,
+            caseSensitive=False,
+            useCLSToken=True
+        )
+
+    @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
+        -------
+        BGEEmbeddings
+            The restored model
+        """
+        from sparknlp.internal import _BGELoader
+        jModel = _BGELoader(folder, spark_session._jsparkSession)._java_obj
+        return BGEEmbeddings(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="bge_small_en_v1.5", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "bge_small_en_v1.5"
+        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
+        -------
+        BGEEmbeddings
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(BGEEmbeddings, name, lang, remote_loc)

sparknlp/annotator/embeddings/camembert_embeddings.py

@@ -21,7 +21,8 @@ class CamemBertEmbeddings(AnnotatorModel,
                           HasCaseSensitiveProperties,
                           HasStorageRef,
                           HasBatchedAnnotate,
-                          HasEngine):
+                          HasEngine,
+                          HasMaxSentenceLengthLimit):
     """The CamemBERT model was proposed in CamemBERT: a Tasty French Language Model by
         Louis Martin, Benjamin Muller, Pedro Javier Ortiz Suárez, Yoann Dupont, Laurent
         Romary, Éric Villemonte de la Clergerie, Djamé Seddah, and Benoît Sagot.
@@ -39,10 +40,10 @@ class CamemBertEmbeddings(AnnotatorModel,
         The default model is ``"camembert_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>`__.
 
         For extended examples of usage, see the
-        `Spark NLP Workshop <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/blogposts/3.NER_with_BERT.ipynb>`__
+        `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/dl-ner/ner_bert.ipynb>`__
         and the
         `CamemBertEmbeddingsTestSpec <https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/embeddings/CamemBertEmbeddingsTestSpec.scala>`__.
 
@@ -143,13 +144,6 @@ class CamemBertEmbeddings(AnnotatorModel,
         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.
 
@@ -160,16 +154,6 @@ class CamemBertEmbeddings(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.CamemBertEmbeddings", java_model=None):
         super(CamemBertEmbeddings, self).__init__(

sparknlp/annotator/embeddings/chunk_embeddings.py

@@ -21,7 +21,7 @@ class ChunkEmbeddings(AnnotatorModel):
     chunk embeddings from either Chunker, NGramGenerator, or NerConverter
     outputs.
 
-    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/annotation/text/english/embeddings/ChunkEmbeddings.ipynb>`__.
 
     ========================== ======================
     Input Annotation types     Output Annotation type
@@ -147,4 +147,3 @@ class ChunkEmbeddings(AnnotatorModel):
             aggregation/pooling.
         """
         return self._set(skipOOV=value)
-

sparknlp/annotator/embeddings/deberta_embeddings.py

@@ -20,7 +20,8 @@ class DeBertaEmbeddings(AnnotatorModel,
                         HasCaseSensitiveProperties,
                         HasStorageRef,
                         HasBatchedAnnotate,
-                        HasEngine):
+                        HasEngine,
+                        HasMaxSentenceLengthLimit):
     """The DeBERTa model was proposed in DeBERTa: Decoding-enhanced BERT with
     Disentangled Attention by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu
     Chen It is based on Google’s BERT model released in 2018 and Facebook’s
@@ -141,11 +142,6 @@ class DeBertaEmbeddings(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.
 
@@ -156,16 +152,6 @@ class DeBertaEmbeddings(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.DeBertaEmbeddings", java_model=None):
         super(DeBertaEmbeddings, self).__init__(

sparknlp/annotator/embeddings/distil_bert_embeddings.py

@@ -21,7 +21,8 @@ class DistilBertEmbeddings(AnnotatorModel,
                            HasCaseSensitiveProperties,
                            HasStorageRef,
                            HasBatchedAnnotate,
-                           HasEngine):
+                           HasEngine,
+                           HasMaxSentenceLengthLimit):
     """DistilBERT is a small, fast, cheap and light Transformer model trained by
     distilling BERT base. It has 40% less parameters than ``bert-base-uncased``,
     runs 60% faster while preserving over 95% of BERT's performances as measured
@@ -37,10 +38,10 @@ class DistilBertEmbeddings(AnnotatorModel,
 
     The default model is ``"distilbert_base_cased"``, 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>`__.
 
-    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-%20DistilBERT.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-%20DistilBERT.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>`_.
@@ -149,11 +150,6 @@ class DistilBertEmbeddings(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()",
@@ -169,16 +165,6 @@ class DistilBertEmbeddings(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.DistilBertEmbeddings", java_model=None):
         super(DistilBertEmbeddings, self).__init__(

sparknlp/annotator/embeddings/doc2vec.py

@@ -31,7 +31,7 @@ class Doc2VecApproach(AnnotatorApproach, HasStorageRef, HasEnableCachingProperti
 
     For instantiated/pretrained models, see :class:`.Doc2VecModel`.
 
-    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
@@ -344,3 +344,9 @@ class Doc2VecModel(AnnotatorModel, HasStorageRef, HasEmbeddingsProperties):
         from sparknlp.pretrained import ResourceDownloader
         return ResourceDownloader.downloadModel(Doc2VecModel, 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/e5_embeddings.py

@@ -0,0 +1,195 @@
+#  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 E5Embeddings."""
+
+from sparknlp.common import *
+
+
+class E5Embeddings(AnnotatorModel,
+                           HasEmbeddingsProperties,
+                           HasCaseSensitiveProperties,
+                           HasStorageRef,
+                           HasBatchedAnnotate,
+                           HasMaxSentenceLengthLimit):
+    """Sentence embeddings using E5.
+
+    E5, a weakly supervised text embedding model that can generate text embeddings tailored to any task (e.g., classification, retrieval, clustering, text evaluation, etc.)
+    Note that this annotator is only supported for Spark Versions 3.4 and up.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> embeddings = E5Embeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("e5_embeddings")
+
+
+    The default model is ``"e5_small"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?q=E5>`__.
+
+
+    ====================== ======================
+    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
+    ----------
+    `Text Embeddings by Weakly-Supervised Contrastive Pre-training <https://arxiv.org/pdf/2212.03533>`__
+
+    https://github.com/microsoft/unilm/tree/master/e5
+
+    **Paper abstract**
+
+    *This paper presents E5, a family of state-of-the-art text embeddings that transfer
+    well to a wide range of tasks. The model is trained in a contrastive manner with
+    weak supervision signals from our curated large-scale text pair dataset (called
+    CCPairs). E5 can be readily used as a general-purpose embedding model for any
+    tasks requiring a single-vector representation of texts such as retrieval, clustering,
+    and classification, achieving strong performance in both zero-shot and fine-tuned
+    settings. We conduct extensive evaluations on 56 datasets from the BEIR and
+    MTEB benchmarks. For zero-shot settings, E5 is the first model that outperforms
+    the strong BM25 baseline on the BEIR retrieval benchmark without using any
+    labeled data. When fine-tuned, E5 obtains the best results on the MTEB benchmark,
+    beating existing embedding models with 40× more parameters.*
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> embeddings = E5Embeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("e5_embeddings")
+    >>> embeddingsFinisher = EmbeddingsFinisher() \\
+    ...     .setInputCols(["e5_embeddings"]) \\
+    ...     .setOutputCols("finished_embeddings") \\
+    ...     .setOutputAsVector(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     embeddings,
+    ...     embeddingsFinisher
+    ... ])
+    >>> data = spark.createDataFrame([["query: how much protein should a female eat",
+    ... "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day." + \
+    ... "But, as you can see from this chart, you'll need to increase that if you're expecting or training for a" + \
+    ... "marathon. Check out the chart below to see how much protein you should be eating each day.",
+    ... ]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+    +--------------------------------------------------------------------------------+
+    |                                                                          result|
+    +--------------------------------------------------------------------------------+
+    |[[8.0190285E-4, -0.005974853, -0.072875895, 0.007944068, 0.026059335, -0.0080...|
+    |[[0.050514214, 0.010061974, -0.04340176, -0.020937217, 0.05170225, 0.01157857...|
+    +--------------------------------------------------------------------------------+
+    """
+
+    name = "E5Embeddings"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.E5Embeddings", java_model=None):
+        super(E5Embeddings, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            dimension=768,
+            batchSize=8,
+            maxSentenceLength=512,
+            caseSensitive=False,
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session, use_openvino=False):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+        use_openvino : bool
+            Use OpenVINO backend
+
+        Returns
+        -------
+        E5Embeddings
+            The restored model
+        """
+        from sparknlp.internal import _E5Loader
+        jModel = _E5Loader(folder, spark_session._jsparkSession, use_openvino)._java_obj
+        return E5Embeddings(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="e5_small", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "e5_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
+        -------
+        E5Embeddings
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(E5Embeddings, name, lang, remote_loc)