spark-nlp 5.5.0rc1__py2.py3-none-any.whl → 5.5.2__py2.py3-none-any.whl

sparknlp/annotator/classifier_dl/bert_for_multiple_choice.py

@@ -0,0 +1,161 @@
+#  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 BertForMultipleChoice(AnnotatorModel,
+                            HasCaseSensitiveProperties,
+                            HasBatchedAnnotate,
+                            HasEngine,
+                            HasMaxSentenceLengthLimit):
+    """BertForMultipleChoice can load BERT Models with a multiple choice classification head on top
+    (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> spanClassifier = BertForMultipleChoice.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"bert_base_uncased_multiple_choice"``, if no name is
+    provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Multiple+Choice>`__.
+
+    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, DOCUMENT``    ``CHUNK``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more
+        memory, by default 8
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default
+        False
+    maxSentenceLength
+        Max sentence length to process, by default 512
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = MultiDocumentAssembler() \\
+    ...     .setInputCols(["question", "context"]) \\
+    ...     .setOutputCols(["document_question", "document_context"])
+    >>> questionAnswering = BertForMultipleChoice.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer") \\
+    ...     .setCaseSensitive(False)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     questionAnswering
+    ... ])
+    >>> data = spark.createDataFrame([["The Eiffel Tower is located in which country??", "Germany, France, Italy"]]).toDF("question", "context")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("answer.result").show(truncate=False)
+    +--------------------+
+    |result              |
+    +--------------------+
+    |[France]             |
+    +--------------------+
+    """
+    name = "BertForMultipleChoice"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    choicesDelimiter = Param(Params._dummy(),
+                         "choicesDelimiter",
+                         "Delimiter character use to split the choices",
+                         TypeConverters.toString)
+
+    def setChoicesDelimiter(self, value):
+        """Sets delimiter character use to split the choices
+
+        Parameters
+        ----------
+        value : string
+            Delimiter character use to split the choices
+        """
+        return self._set(caseSensitive=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.BertForMultipleChoice",
+                 java_model=None):
+        super(BertForMultipleChoice, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=4,
+            maxSentenceLength=512,
+            caseSensitive=False,
+            choicesDelimiter = ","
+        )
+
+    @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
+        -------
+        BertForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.internal import _BertMultipleChoiceLoader
+        jModel = _BertMultipleChoiceLoader(folder, spark_session._jsparkSession)._java_obj
+        return BertForMultipleChoice(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="bert_base_uncased_multiple_choice", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "bert_base_uncased_multiple_choice"
+        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
+        -------
+        BertForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(BertForMultipleChoice, name, lang, remote_loc)

sparknlp/annotator/cv/__init__.py

@@ -16,3 +16,4 @@ from sparknlp.annotator.cv.swin_for_image_classification import *
 from sparknlp.annotator.cv.convnext_for_image_classification import *
 from sparknlp.annotator.cv.vision_encoder_decoder_for_image_captioning import *
 from sparknlp.annotator.cv.clip_for_zero_shot_classification import *
+from sparknlp.annotator.cv.blip_for_question_answering import *

sparknlp/annotator/cv/blip_for_question_answering.py

@@ -0,0 +1,172 @@
+#  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 BLIPForQuestionAnswering(AnnotatorModel,
+                               HasBatchedAnnotateImage,
+                               HasImageFeatureProperties,
+                               HasEngine,
+                               HasCandidateLabelsProperties,
+                               HasRescaleFactor):
+    """BLIPForQuestionAnswering can load BLIP models  for visual question answering.
+    The model consists of a vision encoder, a text encoder as well as a text decoder.
+    The vision encoder will encode the input image, the text encoder will encode the input question together
+    with the encoding of the image, and the text decoder will output the answer to the question.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> visualQAClassifier = BLIPForQuestionAnswering.pretrained() \\
+    ...     .setInputCols(["image_assembler"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"blip_vqa_base"``, if no name is
+    provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Question+Answering>`__.
+
+    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
+    ====================== ======================
+    ``IMAGE``              ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more
+        memory, by default 2
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    maxSentenceLength
+        Max sentence length to process, by default 50
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> image_df = SparkSessionForTest.spark.read.format("image").load(path=images_path)
+    >>> test_df = image_df.withColumn("text", lit("What's this picture about?"))
+    >>> imageAssembler = ImageAssembler() \\
+    ...     .setInputCol("image") \\
+    ...     .setOutputCol("image_assembler")
+    >>> visualQAClassifier = BLIPForQuestionAnswering.pretrained() \\
+    ...     .setInputCols("image_assembler") \\
+    ...     .setOutputCol("answer") \\
+    ...     .setSize(384)
+    >>> pipeline = Pipeline().setStages([
+    ...     imageAssembler,
+    ...     visualQAClassifier
+    ... ])
+    >>> result = pipeline.fit(test_df).transform(test_df)
+    >>> result.select("image_assembler.origin", "answer.result").show(false)
+    +--------------------------------------+------+
+    |origin                                |result|
+    +--------------------------------------+------+
+    |[file:///content/images/cat_image.jpg]|[cats]|
+    +--------------------------------------+------+
+    """
+
+    name = "BLIPForQuestionAnswering"
+
+    inputAnnotatorTypes = [AnnotatorType.IMAGE]
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with "
+                             "config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    maxSentenceLength = Param(Params._dummy(),
+                            "maxSentenceLength",
+                            "Maximum sentence length that the annotator will process. Above this, the sentence is skipped",
+                            typeConverter=TypeConverters.toInt)
+
+    def setMaxSentenceSize(self, value):
+        """Sets Maximum sentence length that the annotator will process, by
+        default 50.
+
+        Parameters
+        ----------
+        value : int
+            Maximum sentence length that the annotator will process
+        """
+        return self._set(maxSentenceLength=value)
+
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.cv.BLIPForQuestionAnswering",
+                 java_model=None):
+        super(BLIPForQuestionAnswering, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=2,
+            size=384,
+            maxSentenceLength=50
+        )
+
+    @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
+        -------
+        CLIPForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.internal import _BLIPForQuestionAnswering
+        jModel = _BLIPForQuestionAnswering(folder, spark_session._jsparkSession)._java_obj
+        return BLIPForQuestionAnswering(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="blip_vqa_base", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "blip_vqa_tf"
+        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
+        -------
+        CLIPForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(BLIPForQuestionAnswering, name, lang, remote_loc)

sparknlp/annotator/embeddings/__init__.py

@@ -40,3 +40,4 @@ from sparknlp.annotator.embeddings.uae_embeddings import *
 from sparknlp.annotator.embeddings.mxbai_embeddings import *
 from sparknlp.annotator.embeddings.snowflake_embeddings import *
 from sparknlp.annotator.embeddings.nomic_embeddings import *
+from sparknlp.annotator.embeddings.auto_gguf_embeddings import *