spark-nlp 5.5.2__py2.py3-none-any.whl → 5.5.3__py2.py3-none-any.whl

{spark_nlp-5.5.2.dist-info → spark_nlp-5.5.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spark-nlp
-Version: 5.5.2
+Version: 5.5.3
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs
@@ -95,7 +95,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==5.5.2 pyspark==3.3.1
+$ pip install spark-nlp==5.5.3 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -161,7 +161,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *5.5.2* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *5.5.3* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -189,7 +189,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following runtimes:
+Spark NLP 5.5.3 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -206,7 +206,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following EMR releases:
+Spark NLP 5.5.3 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|
@@ -237,7 +237,7 @@ deployed to Maven central. To add any of our packages as a dependency in your ap
 from our official documentation.
 
 If you are interested, there is a simple SBT project for Spark NLP to guide you on how to use it in your
-projects [Spark NLP SBT S5.5.2r](https://github.com/maziyarpanahi/spark-nlp-starter)
+projects [Spark NLP SBT S5.5.3r](https://github.com/maziyarpanahi/spark-nlp-starter)
 
 ### Python
 
@@ -282,7 +282,7 @@ In Spark NLP we can define S3 locations to:
 
 Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integration) from our official documentation.
 
-## Document5.5.2
+## Document5.5.3
 
 ### Examples
 
@@ -315,7 +315,7 @@ the Spark NLP library:
     keywords = {Spark, Natural language processing, Deep learning, Tensorflow, Cluster},
     abstract = {Spark NLP is a Natural Language Processing (NLP) library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines that can scale easily in a distributed environment. Spark NLP comes with 1100+ pretrained pipelines and models in more than 192+ languages. It supports nearly all the NLP tasks and modules that can be used seamlessly in a cluster. Downloaded more than 2.7 million times and experiencing 9x growth since January 2020, Spark NLP is used by 54% of healthcare organizations as the world’s most widely used NLP library in the enterprise.}
     }
-}5.5.2
+}5.5.3
 ```
 
 ## Community support

{spark_nlp-5.5.2.dist-info → spark_nlp-5.5.3.dist-info}/RECORD

@@ -3,7 +3,7 @@ com/johnsnowlabs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 com/johnsnowlabs/ml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 com/johnsnowlabs/ml/ai/__init__.py,sha256=YQiK2M7U4d8y5irPy_HB8ae0mSpqS9583MH44pnKJXc,295
 com/johnsnowlabs/nlp/__init__.py,sha256=DPIVXtONO5xXyOk-HB0-sNiHAcco17NN13zPS_6Uw8c,294
-sparknlp/__init__.py,sha256=cdvKsW7Cb_LLCaot-GsMcb8n0RUXqr9NRpsallJamq0,13783
+sparknlp/__init__.py,sha256=Wmw9AZuFatQEjZ0WucHWPO4yF4HTsEZOVZ27IaEAbok,13783
 sparknlp/annotation.py,sha256=I5zOxG5vV2RfPZfqN9enT1i4mo6oBcn3Lrzs37QiOiA,5635
 sparknlp/annotation_audio.py,sha256=iRV_InSVhgvAwSRe9NTbUH9v6OGvTM-FPCpSAKVu0mE,1917
 sparknlp/annotation_image.py,sha256=xhCe8Ko-77XqWVuuYHFrjKqF6zPd8Z-RY_rmZXNwCXU,2547
@@ -90,7 +90,7 @@ sparknlp/annotator/embeddings/albert_embeddings.py,sha256=6Rd1LIn8oFIpq_ALcJh-RU
 sparknlp/annotator/embeddings/auto_gguf_embeddings.py,sha256=ngqjiXUqkL3xOrmt42bY8pp7azgbIWqXGfbKud1CijM,19981
 sparknlp/annotator/embeddings/bert_embeddings.py,sha256=HVUjkg56kBcpGZCo-fmPG5uatMDF3swW_lnbpy1SgSI,8463
 sparknlp/annotator/embeddings/bert_sentence_embeddings.py,sha256=NQy9KuXT9aKsTpYCR5RAeoFWI2YqEGorbdYrf_0KKmw,9148
-sparknlp/annotator/embeddings/bge_embeddings.py,sha256=hXFFd9HOru1w2L9N5YGSZlaKyxqMsZccpaI4Z8-bNUE,7919
+sparknlp/annotator/embeddings/bge_embeddings.py,sha256=Y4b6QzRJGc_Z9_R6SYq-P5NxcvI9XzJlBzwCLLHJpRo,8103
 sparknlp/annotator/embeddings/camembert_embeddings.py,sha256=dBTXas-2Tas_JUR9Xt_GtHLcyqi_cdvT5EHRnyVrSSQ,8817
 sparknlp/annotator/embeddings/chunk_embeddings.py,sha256=WUmkJimSuFkdcLJnvcxOV0QlCLgGlhub29ZTrZb70WE,6052
 sparknlp/annotator/embeddings/deberta_embeddings.py,sha256=_b5nzLb7heFQNN-uT2oBNO6-YmM8bHmAdnGXg47HOWw,8649
@@ -199,7 +199,7 @@ sparknlp/common/annotator_properties.py,sha256=7B1os7pBUfHo6b7IPQAXQ-nir0u3tQLzD
 sparknlp/common/annotator_type.py,sha256=ash2Ip1IOOiJamPVyy_XQj8Ja_DRHm0b9Vj4Ni75oKM,1225
 sparknlp/common/coverage_result.py,sha256=No4PSh1HSs3PyRI1zC47x65tWgfirqPI290icHQoXEI,823
 sparknlp/common/match_strategy.py,sha256=kt1MUPqU1wCwk5qCdYk6jubHbU-5yfAYxb9jjAOrdnY,1678
-sparknlp/common/properties.py,sha256=454BAfebYhg_l7lfjXSCKPWzmCgmU3IT-r2yLGG22DI,22912
+sparknlp/common/properties.py,sha256=TMUpY0EQ3b-GXO9iuctkKrunLhRYePqu2fbmHfocr2w,23870
 sparknlp/common/read_as.py,sha256=imxPGwV7jr4Li_acbo0OAHHRGCBbYv-akzEGaBWEfcY,1226
 sparknlp/common/recursive_annotator_approach.py,sha256=vqugBw22cE3Ff7PIpRlnYFuOlchgL0nM26D8j-NdpqU,1449
 sparknlp/common/storage.py,sha256=D91H3p8EIjNspjqAYu6ephRpCUtdcAir4_PrAbkIQWE,4842
@@ -217,7 +217,7 @@ sparknlp/pretrained/pretrained_pipeline.py,sha256=lquxiaABuA68Rmu7csamJPqBoRJqMU
 sparknlp/pretrained/resource_downloader.py,sha256=8_-rpvO2LsX_Lq4wMPif2ca3RlJZWEabt8pDm2xymiI,7806
 sparknlp/pretrained/utils.py,sha256=T1MrvW_DaWk_jcOjVLOea0NMFE9w8fe0ZT_5urZ_nEY,1099
 sparknlp/reader/__init__.py,sha256=-Toj3AIBki-zXPpV8ezFTI2LX1yP_rK2bhpoa8nBkTw,685
-sparknlp/reader/sparknlp_reader.py,sha256=SLQ5KCWbHnR4S0DwdjRQw_NvaUTchrE0gVCHs__xAy8,17054
+sparknlp/reader/sparknlp_reader.py,sha256=cMliB2zDcmhxp44mu8aRcm5nFK2BXeFCuGgVUkhI8YQ,3825
 sparknlp/training/__init__.py,sha256=qREi9u-5Vc2VjpL6-XZsyvu5jSEIdIhowW7_kKaqMqo,852
 sparknlp/training/conll.py,sha256=wKBiSTrjc6mjsl7Nyt6B8f4yXsDJkZb-sn8iOjix9cE,6961
 sparknlp/training/conllu.py,sha256=8r3i-tmyrLsyk1DtZ9uo2mMDCWb1yw2Y5W6UsV13MkY,4953
@@ -248,8 +248,8 @@ sparknlp/training/_tf_graph_builders_1x/ner_dl/dataset_encoder.py,sha256=R4yHFN3
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model.py,sha256=EoCSdcIjqQ3wv13MAuuWrKV8wyVBP0SbOEW41omHlR0,23189
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model_saver.py,sha256=k5CQ7gKV6HZbZMB8cKLUJuZxoZWlP_DFWdZ--aIDwsc,2356
 sparknlp/training/_tf_graph_builders_1x/ner_dl/sentence_grouper.py,sha256=pAxjWhjazSX8Vg0MFqJiuRVw1IbnQNSs-8Xp26L4nko,870
-spark_nlp-5.5.2.dist-info/.uuid,sha256=1f6hF51aIuv9yCvh31NU9lOpS34NE-h3a0Et7R9yR6A,36
-spark_nlp-5.5.2.dist-info/METADATA,sha256=iFDm_OdynA95nwoWm1vbJcF3i7uuRSnn7S9eU1t5_3c,19156
-spark_nlp-5.5.2.dist-info/WHEEL,sha256=bb2Ot9scclHKMOLDEHY6B2sicWOgugjFKaJsT7vwMQo,110
-spark_nlp-5.5.2.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
-spark_nlp-5.5.2.dist-info/RECORD,,
+spark_nlp-5.5.3.dist-info/.uuid,sha256=1f6hF51aIuv9yCvh31NU9lOpS34NE-h3a0Et7R9yR6A,36
+spark_nlp-5.5.3.dist-info/METADATA,sha256=rZJcS1xIcl3Vota-hC2wHauvrHO45e9c8Y86MjVt4go,19156
+spark_nlp-5.5.3.dist-info/WHEEL,sha256=bb2Ot9scclHKMOLDEHY6B2sicWOgugjFKaJsT7vwMQo,110
+spark_nlp-5.5.3.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
+spark_nlp-5.5.3.dist-info/RECORD,,

sparknlp/__init__.py

@@ -132,7 +132,7 @@ def start(gpu=False,
         The initiated Spark session.
 
     """
-    current_version = "5.5.2"
+    current_version = "5.5.3"
 
     if params is None:
         params = {}
@@ -316,4 +316,4 @@ def version():
     str
         The current Spark NLP version.
     """
-    return '5.5.2'
+    return '5.5.3'

sparknlp/annotator/embeddings/bge_embeddings.py

@@ -21,7 +21,8 @@ class BGEEmbeddings(AnnotatorModel,
                     HasCaseSensitiveProperties,
                     HasStorageRef,
                     HasBatchedAnnotate,
-                    HasMaxSentenceLengthLimit):
+                    HasMaxSentenceLengthLimit,
+                    HasClsTokenProperties):
     """Sentence embeddings using BGE.
 
    BGE, or BAAI General Embeddings, a model that can map any text to a low-dimensional dense 
@@ -60,6 +61,8 @@ class BGEEmbeddings(AnnotatorModel,
         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
 
     References
     ----------
@@ -148,6 +151,7 @@ class BGEEmbeddings(AnnotatorModel,
             batchSize=8,
             maxSentenceLength=512,
             caseSensitive=False,
+            useCLSToken=True
         )
 
     @staticmethod
@@ -171,13 +175,13 @@ class BGEEmbeddings(AnnotatorModel,
         return BGEEmbeddings(java_model=jModel)
 
     @staticmethod
-    def pretrained(name="bge_base", lang="en", remote_loc=None):
+    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_base"
+            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

sparknlp/common/properties.py

@@ -67,6 +67,33 @@ class HasCaseSensitiveProperties:
         return self.getOrDefault(self.caseSensitive)
 
 
+class HasClsTokenProperties:
+    useCLSToken = Param(Params._dummy(),
+                        "useCLSToken",
+                        "Whether to use CLS token for pooling (true) or attention-based average pooling (false)",
+                        typeConverter=TypeConverters.toBoolean)
+
+    def setUseCLSToken(self, value):
+        """Sets whether to ignore case in tokens for embeddings matching.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to use CLS token for pooling (true) or attention-based average pooling (false)
+        """
+        return self._set(useCLSToken=value)
+
+    def getUseCLSToken(self):
+        """Gets whether to use CLS token for pooling (true) or attention-based average pooling (false)
+
+        Returns
+        -------
+        bool
+            Whether to use CLS token for pooling (true) or attention-based average pooling (false)
+        """
+        return self.getOrDefault(self.useCLSToken)
+
+
 class HasClassifierActivationProperties:
     activation = Param(Params._dummy(),
                        "activation",

sparknlp/reader/sparknlp_reader.py

@@ -15,82 +15,19 @@ from sparknlp.internal import ExtendedJavaWrapper
 
 
 class SparkNLPReader(ExtendedJavaWrapper):
-    """Instantiates class to read HTML files.
+    """Instantiates class to read HTML, email, and document files.
 
-    Two types of input paths are supported,
+    Two types of input paths are supported:
 
-    htmlPath: this is a path to a directory of HTML files or a path to an HTML file
-    E.g. "path/html/files"
-
-    url: this is the URL or set of URLs of a website  . E.g., "https://www.wikipedia.org"
+    - `htmlPath`: A path to a directory of HTML files or a single HTML file (e.g., `"path/html/files"`).
+    - `url`: A single URL or a set of URLs (e.g., `"https://www.wikipedia.org"`).
 
     Parameters
     ----------
-    params : spark
-        Spark session
+    spark : SparkSession
+        The active Spark session.
     params : dict, optional
-        Parameter with custom configuration
-
-    Examples
-    --------
-    >>> from sparknlp.reader import SparkNLPReader
-    >>> html_df = SparkNLPReader().html(spark, "https://www.wikipedia.org")
-
-    You can use SparkNLP for one line of code
-    >>> import sparknlp
-    >>> html_df = sparknlp.read().html("https://www.wikipedia.org")
-    >>> html_df.show(truncate=False)
-
-    +--------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |url                 |html                                                                                                                                                                                                                                                                                                                            |
-    +--------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |https://example.com/|[{Title, Example Domain, {pageNumber -> 1}}, {NarrativeText, 0, This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission., {pageNumber -> 1}}, {NarrativeText, 0, More information... More information..., {pageNumber -> 1}}]   |
-    +--------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    >>> html_df.printSchema()
-
-    root
-     |-- url: string (nullable = true)
-     |-- html: array (nullable = true)
-     |    |-- element: struct (containsNull = true)
-     |    |    |-- elementType: string (nullable = true)
-     |    |    |-- content: string (nullable = true)
-     |    |    |-- metadata: map (nullable = true)
-     |    |    |    |-- key: string
-     |    |    |    |-- value: string (valueContainsNull = true)
-
-
-
-    Instantiates class to read email files.
-
-    emailPath: this is a path to a directory of HTML files or a path to an HTML file E.g.
-    "path/html/emails"
-
-    Examples
-    --------
-    >>> from sparknlp.reader import SparkNLPReader
-    >>> email_df = SparkNLPReader().email(spark, "home/user/emails-directory")
-
-    You can use SparkNLP for one line of code
-    >>> import sparknlp
-    >>> email_df = sparknlp.read().email("home/user/emails-directory")
-    >>> email_df.show(truncate=False)
-    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |email                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
-    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |[{Title, Email Text Attachments, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>}}, {NarrativeText, Email  test with two text attachments\r\n\r\nCheers,\r\n\r\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/plain}}, {NarrativeText, <html>\r\n<head>\r\n<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">\r\n<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>\r\n</head>\r\n<body dir="ltr">\r\n<span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Email&nbsp; test with two text attachments</span>\r\n<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">\r\n<br>\r\n</div>\r\n<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">\r\nCheers,</div>\r\n<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">\r\n<br>\r\n</div>\r\n</body>\r\n</html>\r\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/html}}, {Attachment, filename.txt, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, contentType -> text/plain; name="filename.txt"}}, {NarrativeText, This is the content of the file.\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/plain}}, {Attachment, filename2.txt, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, contentType -> text/plain; name="filename2.txt"}}, {NarrativeText, This is an additional content file.\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/plain}}]|
-    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    email_df.printSchema()
-    root
-     |-- path: string (nullable = true)
-     |-- content: array (nullable = true)
-     |-- email: array (nullable = true)
-     |    |-- element: struct (containsNull = true)
-     |    |    |-- elementType: string (nullable = true)
-     |    |    |-- content: string (nullable = true)
-     |    |    |-- metadata: map (nullable = true)
-     |    |    |    |-- key: string
-     |    |    |    |-- value: string (valueContainsNull = true)
-
+        A dictionary with custom configurations.
     """
 
     def __init__(self, spark, params=None):
@@ -100,22 +37,77 @@ class SparkNLPReader(ExtendedJavaWrapper):
         self.spark = spark
 
     def html(self, htmlPath):
+        """Reads HTML files or URLs and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        htmlPath : str or list of str
+            Path(s) to HTML file(s) or a list of URLs.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing the parsed HTML content.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> html_df = SparkNLPReader(spark).html("https://www.wikipedia.org")
+
+        You can also use SparkNLP to simplify the process:
+
+        >>> import sparknlp
+        >>> html_df = sparknlp.read().html("https://www.wikipedia.org")
+        >>> html_df.show(truncate=False)
+        """
         if not isinstance(htmlPath, (str, list)) or (isinstance(htmlPath, list) and not all(isinstance(item, str) for item in htmlPath)):
             raise TypeError("htmlPath must be a string or a list of strings")
         jdf = self._java_obj.html(htmlPath)
-        dataframe = self.getDataFrame(self.spark, jdf)
-        return dataframe
+        return self.getDataFrame(self.spark, jdf)
 
     def email(self, filePath):
+        """Reads email files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        filePath : str
+            Path to an email file or a directory containing emails.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed email data.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> email_df = SparkNLPReader(spark).email("home/user/emails-directory")
+
+        Using SparkNLP:
+
+        >>> import sparknlp
+        >>> email_df = sparknlp.read().email("home/user/emails-directory")
+        >>> email_df.show(truncate=False)
+        """
         if not isinstance(filePath, str):
             raise TypeError("filePath must be a string")
         jdf = self._java_obj.email(filePath)
-        dataframe = self.getDataFrame(self.spark, jdf)
-        return dataframe
+        return self.getDataFrame(self.spark, jdf)
 
     def doc(self, docPath):
+        """Reads document files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        docPath : str
+            Path to a document file.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed document content.
+        """
         if not isinstance(docPath, str):
             raise TypeError("docPath must be a string")
         jdf = self._java_obj.doc(docPath)
-        dataframe = self.getDataFrame(self.spark, jdf)
-        return dataframe
+        return self.getDataFrame(self.spark, jdf)