spark-nlp 2.6.3rc1__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/annotator/embeddings/bert_embeddings.py

@@ -0,0 +1,208 @@
+#  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 BertEmbeddings."""
+
+from sparknlp.common import *
+
+
+class BertEmbeddings(AnnotatorModel,
+                     HasEmbeddingsProperties,
+                     HasCaseSensitiveProperties,
+                     HasStorageRef,
+                     HasBatchedAnnotate,
+                     HasMaxSentenceLengthLimit):
+    """Token-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 Transformer architecture.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> embeddings = BertEmbeddings.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("bert_embeddings")
+
+
+    The default model is ``"small_bert_L2_768"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?task=Embeddings>`__.
+
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/dl-ner/ner_bert.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>`_.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT, TOKEN``    ``WORD_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 128
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+
+    References
+    ----------
+    `BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding <https://arxiv.org/abs/1810.04805>`__
+
+    https://github.com/google-research/bert
+
+    **Paper abstract**
+
+    *We introduce a new language representation model called BERT, which stands
+    for Bidirectional Encoder Representations from Transformers. Unlike recent
+    language representation models, BERT is designed to pre-train deep
+    bidirectional representations from unlabeled text by jointly conditioning on
+    both left and right context in all layers. As a result, the pre-trained BERT
+    model can be fine-tuned with just one additional output layer to create
+    state-of-the-art models for a wide range of tasks, such as question
+    answering and language inference, without substantial task-specific
+    architecture modifications. BERT is conceptually simple and empirically
+    powerful. It obtains new state-of-the-art results on eleven natural language
+    processing tasks, including pushing the GLUE score to 80.5% (7.7% point
+    absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute
+    improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point
+    absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute
+    improvement).*
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> tokenizer = Tokenizer() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("token")
+    >>> embeddings = BertEmbeddings.pretrained("small_bert_L2_128", "en") \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("bert_embeddings")
+    >>> embeddingsFinisher = EmbeddingsFinisher() \\
+    ...     .setInputCols(["bert_embeddings"]) \\
+    ...     .setOutputCols("finished_embeddings") \\
+    ...     .setOutputAsVector(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     tokenizer,
+    ...     embeddings,
+    ...     embeddingsFinisher
+    ... ])
+    >>> data = spark.createDataFrame([["This is a sentence."]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+    +--------------------------------------------------------------------------------+
+    |                                                                          result|
+    +--------------------------------------------------------------------------------+
+    |[-2.3497989177703857,0.480538547039032,-0.3238905668258667,-1.612930893898010...|
+    |[-2.1357314586639404,0.32984697818756104,-0.6032363176345825,-1.6791689395904...|
+    |[-1.8244884014129639,-0.27088963985443115,-1.059438943862915,-0.9817547798156...|
+    |[-1.1648050546646118,-0.4725411534309387,-0.5938255786895752,-1.5780693292617...|
+    |[-0.9125322699546814,0.4563939869403839,-0.3975459933280945,-1.81611204147338...|
+    +--------------------------------------------------------------------------------+
+    """
+
+    name = "BertEmbeddings"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.TOKEN]
+
+    outputAnnotatorType = AnnotatorType.WORD_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.BertEmbeddings", java_model=None):
+        super(BertEmbeddings, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            dimension=768,
+            batchSize=8,
+            maxSentenceLength=128,
+            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
+        -------
+        BertEmbeddings
+            The restored model
+        """
+        from sparknlp.internal import _BertLoader
+        jModel = _BertLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
+        return BertEmbeddings(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="small_bert_L2_768", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "small_bert_L2_768"
+        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
+        -------
+        BertEmbeddings
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(BertEmbeddings, name, lang, remote_loc)

sparknlp/annotator/embeddings/bert_sentence_embeddings.py

@@ -0,0 +1,224 @@
+#  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 BertSentenceEmbeddings."""
+
+from sparknlp.common import *
+
+
+class BertSentenceEmbeddings(AnnotatorModel,
+                                  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
+    Transformer architecture.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>>embeddings = BertSentenceEmbeddings.pretrained() \\
+    ...    .setInputCols(["sentence"]) \\
+    ...    .setOutputCol("sentence_bert_embeddings")
+
+
+    The default model is ``"sent_small_bert_L2_768"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?task=Embeddings>`__.
+
+    For extended examples of usage, see the
+    `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
+    ====================== =======================
+    ``DOCUMENT``           ``SENTENCE_EMBEDDINGS``
+    ====================== =======================
+
+    Parameters
+    ----------
+    batchSize
+        Size of every batch, by default 8
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default
+        False
+    dimension
+        Number of embedding dimensions, by default 768
+    maxSentenceLength
+        Max sentence length to process, by default 128
+    isLong
+        Use Long type instead of Int type for inputs buffer - Some Bert models
+        require Long instead of Int.
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+
+    References
+    ----------
+    `BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding <https://arxiv.org/abs/1810.04805>`__
+
+    https://github.com/google-research/bert
+
+    **Paper abstract**
+
+    *We introduce a new language representation model called BERT, which stands
+    for Bidirectional Encoder Representations from Transformers. Unlike recent
+    language representation models, BERT is designed to pre-train deep
+    bidirectional representations from unlabeled text by jointly conditioning on
+    both left and right context in all layers. As a result, the pre-trained BERT
+    model can be fine-tuned with just one additional output layer to create
+    state-of-the-art models for a wide range of tasks, such as question
+    answering and language inference, without substantial task-specific
+    architecture modifications. BERT is conceptually simple and empirically
+    powerful. It obtains new state-of-the-art results on eleven natural language
+    processing tasks, including pushing the GLUE score to 80.5% (7.7% point
+    absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute
+    improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point
+    absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute
+    improvement).*
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> sentence = SentenceDetector() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("sentence")
+    >>> embeddings = BertSentenceEmbeddings.pretrained("sent_small_bert_L2_128") \\
+    ...     .setInputCols(["sentence"]) \\
+    ...     .setOutputCol("sentence_bert_embeddings")
+    >>> embeddingsFinisher = EmbeddingsFinisher() \\
+    ...     .setInputCols(["sentence_bert_embeddings"]) \\
+    ...     .setOutputCols("finished_embeddings") \\
+    ...     .setOutputAsVector(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     sentence,
+    ...     embeddings,
+    ...     embeddingsFinisher
+    ... ])
+    >>> data = spark.createDataFrame([["John loves apples. Mary loves oranges. John loves Mary."]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+    +--------------------------------------------------------------------------------+
+    |                                                                          result|
+    +--------------------------------------------------------------------------------+
+    |[-0.8951074481010437,0.13753940165042877,0.3108254075050354,-1.65693199634552...|
+    |[-0.6180210709571838,-0.12179657071828842,-0.191165953874588,-1.4497021436691...|
+    |[-0.822715163230896,0.7568016648292542,-0.1165061742067337,-1.59048593044281,...|
+    +--------------------------------------------------------------------------------+
+    """
+
+    name = "BertSentenceEmbeddings"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
+
+    isLong = Param(Params._dummy(),
+                   "isLong",
+                   "Use Long type instead of Int type for inputs buffer - Some Bert models require Long instead of Int.",
+                   typeConverter=TypeConverters.toBoolean)
+
+    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)
+
+    def setIsLong(self, value):
+        """Sets whether to use Long type instead of Int type for inputs buffer.
+
+        Some Bert models require Long instead of Int.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to use Long type instead of Int type for inputs buffer
+        """
+        return self._set(isLong=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.BertSentenceEmbeddings", java_model=None):
+        super(BertSentenceEmbeddings, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            dimension=768,
+            batchSize=8,
+            maxSentenceLength=128,
+            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
+        -------
+        BertSentenceEmbeddings
+            The restored model
+        """
+        from sparknlp.internal import _BertSentenceLoader
+        jModel = _BertSentenceLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
+        return BertSentenceEmbeddings(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="sent_small_bert_L2_768", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "sent_small_bert_L2_768"
+        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
+        -------
+        BertSentenceEmbeddings
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(BertSentenceEmbeddings, name, lang, remote_loc)

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)