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

spark_nlp-5.5.2.dist-info/METADATA

@@ -0,0 +1,345 @@
+Metadata-Version: 2.1
+Name: spark-nlp
+Version: 5.5.2
+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
+Keywords: NLP spark vision speech deep learning transformer tensorflow BERT GPT-2 Wav2Vec2 ViT
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Software Development :: Internationalization
+Classifier: Topic :: Software Development :: Localization
+Classifier: Topic :: Software Development :: Build Tools
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Topic :: Scientific/Engineering
+Classifier: Typing :: Typed
+Description-Content-Type: text/markdown
+
+# Spark NLP: State-of-the-Art Natural Language Processing & LLMs Library
+
+<p align="center">
+    <a href="https://github.com/JohnSnowLabs/spark-nlp/actions" alt="build">
+        <img src="https://github.com/JohnSnowLabs/spark-nlp/workflows/build/badge.svg" /></a>
+    <a href="https://github.com/JohnSnowLabs/spark-nlp/releases" alt="Current Release Version">
+        <img src="https://img.shields.io/github/v/release/JohnSnowLabs/spark-nlp.svg?style=flat-square&logo=github" /></a>
+    <a href="https://search.maven.org/artifact/com.johnsnowlabs.nlp/spark-nlp_2.12" alt="Maven Central">
+        <img src="https://maven-badges.herokuapp.com/maven-central/com.johnsnowlabs.nlp/spark-nlp_2.12/badge.svg" /></a>
+    <a href="https://badge.fury.io/py/spark-nlp" alt="PyPI version">
+        <img src="https://badge.fury.io/py/spark-nlp.svg" /></a>
+    <a href="https://anaconda.org/JohnSnowLabs/spark-nlp" alt="Anaconda-Cloud">
+        <img src="https://anaconda.org/johnsnowlabs/spark-nlp/badges/version.svg" /></a>
+    <a href="https://github.com/JohnSnowLabs/spark-nlp/blob/master/LICENSE" alt="License">
+        <img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" /></a>
+    <a href="https://pypi.org/project/spark-nlp/" alt="PyPi downloads">
+        <img src="https://static.pepy.tech/personalized-badge/spark-nlp?period=total&units=international_system&left_color=grey&right_color=orange&left_text=pip%20downloads" /></a>
+</p>
+
+Spark NLP is a state-of-the-art Natural Language Processing library built on top of Apache Spark. It provides **simple**, **performant** & **accurate** NLP annotations for machine learning pipelines that **scale** easily in a distributed environment.
+
+Spark NLP comes with **83000+** pretrained **pipelines** and **models** in more than **200+** languages.
+It also offers tasks such as **Tokenization**, **Word Segmentation**, **Part-of-Speech Tagging**, Word and Sentence **Embeddings**, **Named Entity Recognition**, **Dependency Parsing**, **Spell Checking**, **Text Classification**, **Sentiment Analysis**, **Token Classification**, **Machine Translation** (+180 languages), **Summarization**, **Question Answering**, **Table Question Answering**, **Text Generation**, **Image Classification**, **Image to Text (captioning)**, **Automatic Speech Recognition**, **Zero-Shot Learning**, and many more [NLP tasks](#features).
+
+**Spark NLP** is the only open-source NLP library in **production** that offers state-of-the-art transformers such as **BERT**, **CamemBERT**, **ALBERT**, **ELECTRA**, **XLNet**, **DistilBERT**, **RoBERTa**, **DeBERTa**, **XLM-RoBERTa**, **Longformer**, **ELMO**, **Universal Sentence Encoder**, **Llama-2**, **M2M100**, **BART**, **Instructor**, **E5**, **Google T5**, **MarianMT**, **OpenAI GPT2**, **Vision Transformers (ViT)**, **OpenAI Whisper**, **Llama**, **Mistral**, **Phi**, **Qwen2**, and many more not only to **Python** and **R**, but also to **JVM** ecosystem (**Java**, **Scala**, and **Kotlin**) at **scale** by extending **Apache Spark** natively.
+
+## Model Importing Support
+
+Spark NLP provides easy support for importing models from various popular frameworks:
+
+- **TensorFlow**
+- **ONNX**
+- **OpenVINO**
+- **Llama.cpp (GGUF)**
+
+This wide range of support allows you to seamlessly integrate models from different sources into your Spark NLP workflows, enhancing flexibility and compatibility with existing machine learning ecosystems.
+
+## Project's website
+
+Take a look at our official Spark NLP page: [https://sparknlp.org/](https://sparknlp.org/) for user
+documentation and examples
+
+## Features
+
+- [Text Preprocessing](https://sparknlp.org/docs/en/features#text-preproccesing)
+- [Parsing and Analysis](https://sparknlp.org/docs/en/features#parsing-and-analysis)
+- [Sentiment and Classification](https://sparknlp.org/docs/en/features#sentiment-and-classification)
+- [Embeddings](https://sparknlp.org/docs/en/features#embeddings)
+- [Classification and Question Answering](https://sparknlp.org/docs/en/features#classification-and-question-answering-models)
+- [Machine Translation and Generation](https://sparknlp.org/docs/en/features#machine-translation-and-generation)
+- [Image and Speech](https://sparknlp.org/docs/en/features#image-and-speech)
+- [Integration and Interoperability (ONNX, OpenVINO)](https://sparknlp.org/docs/en/features#integration-and-interoperability)
+- [Pre-trained Models (36000+ in +200 languages)](https://sparknlp.org/docs/en/features#pre-trained-models)
+- [Multi-lingual Support](https://sparknlp.org/docs/en/features#multi-lingual-support)
+
+## Quick Start
+
+This is a quick example of how to use Spark NLP pre-trained pipeline in Python and PySpark:
+
+```sh
+$ java -version
+# should be Java 8 or 11 (Oracle or OpenJDK)
+$ 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
+```
+
+In Python console or Jupyter `Python3` kernel:
+
+```python
+# Import Spark NLP
+from sparknlp.base import *
+from sparknlp.annotator import *
+from sparknlp.pretrained import PretrainedPipeline
+import sparknlp
+
+# Start SparkSession with Spark NLP
+# start() functions has 3 parameters: gpu, apple_silicon, and memory
+# sparknlp.start(gpu=True) will start the session with GPU support
+# sparknlp.start(apple_silicon=True) will start the session with macOS M1 & M2 support
+# sparknlp.start(memory="16G") to change the default driver memory in SparkSession
+spark = sparknlp.start()
+
+# Download a pre-trained pipeline
+pipeline = PretrainedPipeline('explain_document_dl', lang='en')
+
+# Your testing dataset
+text = """
+The Mona Lisa is a 16th century oil painting created by Leonardo.
+It's held at the Louvre in Paris.
+"""
+
+# Annotate your testing dataset
+result = pipeline.annotate(text)
+
+# What's in the pipeline
+list(result.keys())
+Output: ['entities', 'stem', 'checked', 'lemma', 'document',
+         'pos', 'token', 'ner', 'embeddings', 'sentence']
+
+# Check the results
+result['entities']
+Output: ['Mona Lisa', 'Leonardo', 'Louvre', 'Paris']
+```
+
+For more examples, you can visit our dedicated [examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples) to showcase all Spark NLP use cases!
+
+### Packages Cheatsheet
+
+This is a cheatsheet for corresponding Spark NLP Maven package to Apache Spark / PySpark major version:
+
+| Apache Spark            | Spark NLP on CPU   | Spark NLP on GPU           | Spark NLP on AArch64 (linux)   | Spark NLP on Apple Silicon           |
+|-------------------------|--------------------|----------------------------|--------------------------------|--------------------------------------|
+| 3.0/3.1/3.2/3.3/3.4/3.5 | `spark-nlp`        | `spark-nlp-gpu`            | `spark-nlp-aarch64`            | `spark-nlp-silicon`                  |
+| Start Function          | `sparknlp.start()` | `sparknlp.start(gpu=True)` | `sparknlp.start(aarch64=True)` | `sparknlp.start(apple_silicon=True)` |
+
+NOTE: `M1/M2` and `AArch64` are under `experimental` support. Access and support to these architectures are limited by the
+community and we had to build most of the dependencies by ourselves to make them compatible. We support these two
+architectures, however, they may not work in some environments.
+
+## Pipelines and Models
+
+For a quick example of using pipelines and models take a look at our official [documentation](https://sparknlp.org/docs/en/install#pipelines-and-models)
+
+#### Please check out our Models Hub for the full list of [pre-trained models](https://sparknlp.org/models) with examples, demo, benchmark, and more
+
+## Platform and Ecosystem Support
+
+### 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 | 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 |
+|-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
+| 5.5.x     | YES                | YES                | YES                | YES                | YES                | YES                | NO                 | NO                 |
+| 5.4.x     | YES                | YES                | YES                | YES                | YES                | YES                | NO                 | NO                 |
+| 5.3.x     | YES                | YES                | YES                | YES                | YES                | YES                | NO                 | NO                 |
+| 5.2.x     | YES                | YES                | YES                | YES                | YES                | YES                | NO                 | NO                 |
+| 5.1.x     | Partially          | YES                | YES                | YES                | YES                | YES                | NO                 | NO                 |
+| 5.0.x     | YES                | YES                | YES                | YES                | YES                | YES                | NO                 | NO                 |
+
+Find out more about `Spark NLP` versions from our [release notes](https://github.com/JohnSnowLabs/spark-nlp/releases).
+
+### Scala and Python Support
+
+| Spark NLP | Python 3.6 | Python 3.7 | Python 3.8 | Python 3.9 | Python 3.10| Scala 2.11 | Scala 2.12 |
+|-----------|------------|------------|------------|------------|------------|------------|------------|
+| 5.5.x     | NO         | YES        | YES        | YES        | YES        | NO         | YES        |
+| 5.4.x     | NO         | YES        | YES        | YES        | YES        | NO         | YES        |
+| 5.3.x     | NO         | YES        | YES        | YES        | YES        | NO         | YES        |
+| 5.2.x     | NO         | YES        | YES        | YES        | YES        | NO         | YES        |
+| 5.1.x     | NO         | YES        | YES        | YES        | YES        | NO         | YES        |
+| 5.0.x     | NO         | YES        | YES        | YES        | YES        | NO         | YES        |
+
+Find out more about 4.x `SparkNLP` versions in our official [documentation](https://sparknlp.org/docs/en/install#apache-spark-support)
+
+### Databricks Support
+
+Spark NLP 5.5.2 has been tested and is compatible with the following runtimes:
+
+| **CPU**            | **GPU**            |
+|--------------------|--------------------|
+| 14.1 / 14.1 ML     | 14.1 ML & GPU      |
+| 14.2 / 14.2 ML     | 14.2 ML & GPU      |
+| 14.3 / 14.3 ML     | 14.3 ML & GPU      |
+| 15.0 / 15.0 ML     | 15.0 ML & GPU      |
+| 15.1 / 15.0 ML     | 15.1 ML & GPU      |
+| 15.2 / 15.0 ML     | 15.2 ML & GPU      |
+| 15.3 / 15.0 ML     | 15.3 ML & GPU      |
+| 15.4 / 15.0 ML     | 15.4 ML & GPU      |
+
+We are compatible with older runtimes. For a full list check databricks support in our official [documentation](https://sparknlp.org/docs/en/install#databricks-support)
+
+### EMR Support
+
+Spark NLP 5.5.2 has been tested and is compatible with the following EMR releases:
+
+| **EMR Release**    |
+|--------------------|
+| emr-6.13.0         |
+| emr-6.14.0         |
+| emr-6.15.0         |
+| emr-7.0.0          |
+| emr-7.1.0          |
+| emr-7.2.0          |
+
+We are compatible with older EMR releases. For a full list check EMR support in our official [documentation](https://sparknlp.org/docs/en/install#emr-support)
+
+Full list of [Amazon EMR 6.x releases](https://docs.aws.amazon.com/emr/latest/ReleaseGuide/emr-release-6x.html)
+Full list of [Amazon EMR 7.x releases](https://docs.aws.amazon.com/emr/latest/ReleaseGuide/emr-release-7x.html)
+
+NOTE: The EMR 6.1.0 and 6.1.1 are not supported.
+
+## Installation
+
+### Command line (requires internet connection)
+
+To install spark-nlp packages through command line follow [these instructions](https://sparknlp.org/docs/en/install#command-line) from our official documentation
+
+### Scala
+
+Spark NLP supports Scala 2.12.15 if you are using Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, and 3.4.x versions. Our packages are
+deployed to Maven central. To add any of our packages as a dependency in your application you can follow [these instructions](https://sparknlp.org/docs/en/install#scala-and-java)
+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)
+
+### Python
+
+Spark NLP supports Python 3.7.x and above depending on your major PySpark version.
+Check all available installations for Python in our official [documentation](https://sparknlp.org/docs/en/install#python)
+
+### Compiled JARs
+
+To compile the jars from source follow [these instructions](https://sparknlp.org/docs/en/compiled#jars) from our official documenation
+
+## Platform-Specific Instructions
+
+For detailed instructions on how to use Spark NLP on supported platforms, please refer to our official documentation:
+
+| Platform                | Supported Language(s) |
+|-------------------------|-----------------------|
+| [Apache Zeppelin](https://sparknlp.org/docs/en/install#apache-zeppelin)      | Scala, Python         |
+| [Jupyter Notebook](https://sparknlp.org/docs/en/install#jupter-notebook) | Python                |
+| [Google Colab Notebook](https://sparknlp.org/docs/en/install#google-colab-notebook) | Python                |
+| [Kaggle Kernel](https://sparknlp.org/docs/en/install#kaggle-kernel)        | Python                |
+| [Databricks Cluster](https://sparknlp.org/docs/en/install#databricks-cluster)    | Scala, Python         |
+| [EMR Cluster](https://sparknlp.org/docs/en/install#emr-cluster)           | Scala, Python         |
+| [GCP Dataproc Cluster](https://sparknlp.org/docs/en/install#gcp-dataproc) | Scala, Python         |
+
+### Offline
+
+Spark NLP library and all the pre-trained models/pipelines can be used entirely offline with no access to the Internet.
+Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integration) from our official documentation
+to use Spark NLP offline
+
+## Advanced Settings
+
+You can change Spark NLP configurations via Spark properties configuration.
+Please check [these instructions](https://sparknlp.org/docs/en/install#sparknlp-properties) from our official documentation.
+
+### S3 Integration
+
+In Spark NLP we can define S3 locations to:
+
+- Export log files of training models
+- Store tensorflow graphs used in `NerDLApproach`
+
+Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integration) from our official documentation.
+
+## Document5.5.2
+
+### Examples
+
+Need more **examples**? Check out our dedicated [Spark NLP Examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
+repository to showcase all Spark NLP use cases!
+
+Also, don't forget to check [Spark NLP in Action](https://sparknlp.org/demo) built by Streamlit.
+
+#### All examples: [spark-nlp/examples](https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples)
+
+### FAQ
+
+[Check our Articles and Videos page here](https://sparknlp.org/learn)
+
+### Citation
+
+We have published a [paper](https://www.sciencedirect.com/science/article/pii/S2665963821000063) that you can cite for
+the Spark NLP library:
+
+```bibtex
+@article{KOCAMAN2021100058,
+    title = {Spark NLP: Natural language understanding at scale},
+    journal = {Software Impacts},
+    pages = {100058},
+    year = {2021},
+    issn = {2665-9638},
+    doi = {https://doi.org/10.1016/j.simpa.2021.100058},
+    url = {https://www.sciencedirect.com/science/article/pii/S2665963.2.300063},
+    author = {Veysel Kocaman and David Talby},
+    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
+```
+
+## Community support
+
+- [Slack](https://join.slack.com/t/spark-nlp/shared_invite/zt-198dipu77-L3UWNe_AJ8xqDk0ivmih5Q) For live discussion with the Spark NLP community and the team
+- [GitHub](https://github.com/JohnSnowLabs/spark-nlp) Bug reports, feature requests, and contributions
+- [Discussions](https://github.com/JohnSnowLabs/spark-nlp/discussions) Engage with other community members, share ideas,
+  and show off how you use Spark NLP!
+- [Medium](https://medium.com/spark-nlp) Spark NLP articles
+- [YouTube](https://www.youtube.com/channel/UCmFOjlpYEhxf_wJUDuz6xxQ/videos) Spark NLP video tutorials
+
+## Contributing
+
+We appreciate any sort of contributions:
+
+- ideas
+- feedback
+- documentation
+- bug reports
+- NLP training and testing corpora
+- Development and testing
+
+Clone the repo and submit your pull-requests! Or directly create issues in this repo.
+
+## John Snow Labs
+
+[http://johnsnowlabs.com](http://johnsnowlabs.com)

{spark_nlp-5.5.0rc1.dist-info → spark_nlp-5.5.2.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=KDifiXnwBik4d6cz2zhtUwi3nicSAxEoD1Pht3ELBo0,13646
+sparknlp/__init__.py,sha256=cdvKsW7Cb_LLCaot-GsMcb8n0RUXqr9NRpsallJamq0,13783
 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
@@ -30,12 +30,13 @@ sparknlp/annotator/audio/__init__.py,sha256=dXjtvi5c0aTZFq1Q_JciUd1uFTBVSJoUdcq0
 sparknlp/annotator/audio/hubert_for_ctc.py,sha256=76PfwPZZvOHU5kfDqLueCFbmqa4W8pMNRGoCvOqjsEA,7859
 sparknlp/annotator/audio/wav2vec2_for_ctc.py,sha256=K78P1U6vA4O1UufsLYzy0H7arsKNmwPcIV7kzDFsA5Q,6210
 sparknlp/annotator/audio/whisper_for_ctc.py,sha256=uII51umuohqwnAW0Q7VdxEFyr_j5LMnfpcRlf8TbetA,9800
-sparknlp/annotator/classifier_dl/__init__.py,sha256=Oa5v2kInquQXLy3_Qs0bJAS_JJiTgqy9W0zeBF6y3B4,3933
+sparknlp/annotator/classifier_dl/__init__.py,sha256=4v2_3kSWQFFBc_KzaJ0gEC6ANVJpy5tsHa6CJGc4nCw,4005
 sparknlp/annotator/classifier_dl/albert_for_question_answering.py,sha256=LG2dL6Fky1T35yXTUZBfIihIIGnkRFQ7ECQ3HRXXEG8,6517
 sparknlp/annotator/classifier_dl/albert_for_sequence_classification.py,sha256=kWx7f9pcKE2qw319gn8FN0Md5dX38gbmfeoY9gWCLNk,7842
 sparknlp/annotator/classifier_dl/albert_for_token_classification.py,sha256=5rdsjWnsAVmtP-idU7ATKJ8lkH2rtlKZLnpi4Mq27eI,6839
 sparknlp/annotator/classifier_dl/albert_for_zero_shot_classification.py,sha256=_TgV6EiIOiD_djA3fxfoz-o37mzMeKbn6iL2kZ6GzO0,8366
 sparknlp/annotator/classifier_dl/bart_for_zero_shot_classification.py,sha256=yqQeDdpLbNOKuSZejZjSAjT8ydYyxsTVf2aFDgSSDfc,8767
+sparknlp/annotator/classifier_dl/bert_for_multiple_choice.py,sha256=Ew_NGBj7F5ApgK3SyQh2HIfjD7ZTqTs0LZEQxjwoyto,5936
 sparknlp/annotator/classifier_dl/bert_for_question_answering.py,sha256=2euY_RAdMPA4IHJXZAd5MkQojFOtFNhB_hSc1iVQ5DQ,6433
 sparknlp/annotator/classifier_dl/bert_for_sequence_classification.py,sha256=AzD3RQcRuQc0DDTbL6vGiacTtHlZnbAqksNvRQq7EQE,7800
 sparknlp/annotator/classifier_dl/bert_for_token_classification.py,sha256=uJXoDLPfPWiRmKqtw_3lLBvneIirj87S2JWwfd33zq8,6668
@@ -74,7 +75,8 @@ sparknlp/annotator/classifier_dl/xlnet_for_sequence_classification.py,sha256=CI9
 sparknlp/annotator/classifier_dl/xlnet_for_token_classification.py,sha256=SndQpIfslsSYEOX-myLjpUS6-wVIeDG8MOhJYcu2_7M,6739
 sparknlp/annotator/coref/__init__.py,sha256=SG8MAaVxQpoYYAsyKaoOlvlHjorDzj3DHt4nnEdBWm8,53
 sparknlp/annotator/coref/spanbert_coref.py,sha256=AXWJhvVquY2uoApO_Np1fz7_KyJhxnZB4i-xk78sBfc,8407
-sparknlp/annotator/cv/__init__.py,sha256=LYbR0X-Wl-NkoWpSzovmhSQzk8zcCBAhqZfVd6YLnKs,943
+sparknlp/annotator/cv/__init__.py,sha256=194aJ5N5eE3HOYRzAAdroHTTQ0o1qyCrgyRLddvqBp0,1006
+sparknlp/annotator/cv/blip_for_question_answering.py,sha256=At7L5pPBNDR1r-JGLKM5b3dTrq5Ecz9r0M1gToUVZTs,6551
 sparknlp/annotator/cv/clip_for_zero_shot_classification.py,sha256=_1pLc9BiFrFN10eJPCDJLJT-vdnTSG9OnB25Y_kKJIA,7528
 sparknlp/annotator/cv/convnext_for_image_classification.py,sha256=KzaAlYW5M2l73zUozzgg8_p14eGDz9k9PYVAUZLN25k,11874
 sparknlp/annotator/cv/swin_for_image_classification.py,sha256=iZ1KY0GInbQmGzkmuNbds4PGPwCheLXc-Syv2HRmqug,10694
@@ -83,8 +85,9 @@ sparknlp/annotator/cv/vit_for_image_classification.py,sha256=D2V3pxAd3rBi1817lxV
 sparknlp/annotator/dependency/__init__.py,sha256=eV43oXAGaYl2N1XKIEAAZJLNP8gpHm8VxuXDeDlQzR4,774
 sparknlp/annotator/dependency/dependency_parser.py,sha256=SxyvHPp8Hs1Xnm5X1nLTMi095XoQMtfL8pbys15mYAI,11212
 sparknlp/annotator/dependency/typed_dependency_parser.py,sha256=60vPdYkbFk9MPGegg3m9Uik9cMXpMZd8tBvXG39gNww,12456
-sparknlp/annotator/embeddings/__init__.py,sha256=WifjEILUN6lZs4_WIX80xl5hrrsSrBK-4oVaLh-tONc,2343
+sparknlp/annotator/embeddings/__init__.py,sha256=KHDCHb8SMlkSGGSu69SfKneUDDUlBdMGdMzDrYp_cis,2408
 sparknlp/annotator/embeddings/albert_embeddings.py,sha256=6Rd1LIn8oFIpq_ALcJh-RUjPEO7Ht8wsHY6JHSFyMkw,9995
+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
@@ -99,7 +102,7 @@ sparknlp/annotator/embeddings/instructor_embeddings.py,sha256=CTKmbuBOx_KBM4JM-Y
 sparknlp/annotator/embeddings/longformer_embeddings.py,sha256=jS4fxB5O0-d9ta9VKv8ai-17n5YHt5rML8QxUw7K4Io,8754
 sparknlp/annotator/embeddings/mpnet_embeddings.py,sha256=7d6E4lS7jjkppDPvty1UHNNrbykkriFiysrxZ_RzL0U,7875
 sparknlp/annotator/embeddings/mxbai_embeddings.py,sha256=kCaYcM3lLYJjhElLK5isdxzJqIvoGZlUKKNkySMUkE8,6017
-sparknlp/annotator/embeddings/nomic_embeddings.py,sha256=SfiTTpx0MqeHGC_nyoFNxJbfEQL4v-PrNH6hAOFsd8c,7338
+sparknlp/annotator/embeddings/nomic_embeddings.py,sha256=WTllH3htx9wDD2Le8pZgKVPM_U8XNmroJb6f4PeVeP8,7347
 sparknlp/annotator/embeddings/roberta_embeddings.py,sha256=q_WHby2lDcPc5bVHkGc6X_GwT3qyDUBLUVz5ZW4HCSY,9229
 sparknlp/annotator/embeddings/roberta_sentence_embeddings.py,sha256=KVrD4z_tIU-sphK6dmbbnHBBt8-Y89C_BFQAkN99kZo,8181
 sparknlp/annotator/embeddings/sentence_embeddings.py,sha256=azuA1FKMtTJ9suwJqTEHeWHumT6kYdfURTe_1fsqcB8,5402
@@ -145,19 +148,19 @@ sparknlp/annotator/sentiment/__init__.py,sha256=Lq3vKaZS1YATLMg0VNXSVtkWL5q5G9ta
 sparknlp/annotator/sentiment/sentiment_detector.py,sha256=m545NGU0Xzg_PO6_qIfpli1uZj7JQcyFgqe9R6wAPFI,8154
 sparknlp/annotator/sentiment/vivekn_sentiment.py,sha256=4rpXWDgzU6ddnbrSCp9VdLb2epCc9oZ3c6XcqxEw8nk,9655
 sparknlp/annotator/seq2seq/__init__.py,sha256=Fdz1zsxpB6vM2a0sKuGCSMD1ZgqeVqAez0-AtppMGB4,1541
-sparknlp/annotator/seq2seq/auto_gguf_model.py,sha256=YSWr2doOp9pwiodW_7qWgnQ2xdnl_WNEECBwxI6uq_c,39396
+sparknlp/annotator/seq2seq/auto_gguf_model.py,sha256=pTQq3KztHQq3fybdCmXEq5wTlb0t-5ANCfdQ_-7oQRg,38343
 sparknlp/annotator/seq2seq/bart_transformer.py,sha256=I1flM4yeCzEAKOdQllBC30XuedxVJ7ferkFhZ6gwEbE,18481
-sparknlp/annotator/seq2seq/cpm_transformer.py,sha256=zRbw_xAsaRnhuyYAW8UAGhz7mIyhpqk09nCsJb8-7rg,13298
+sparknlp/annotator/seq2seq/cpm_transformer.py,sha256=0CnBFMlxMu0pD2QZMHyoGtIYgXqfUQm68vr6zEAa6Eg,13290
 sparknlp/annotator/seq2seq/gpt2_transformer.py,sha256=Oz95R_NRR4tWHu_bW6Ak2832ZILXycp3ify7LfRSi8o,15310
 sparknlp/annotator/seq2seq/llama2_transformer.py,sha256=3LzTR0VerFdFmOizsrs2Q7HTnjELJ5WtfUgx5XnOqGM,13898
 sparknlp/annotator/seq2seq/llama3_transformer.py,sha256=dA3rIEVOLmlnJwhqkYmL_GrrcRVpoUY_i7QIyA5N2jM,14920
 sparknlp/annotator/seq2seq/m2m100_transformer.py,sha256=uIL9RZuuryTIdAy9TbJf9wbz6RekhW8S079bJhaB6i4,16116
 sparknlp/annotator/seq2seq/marian_transformer.py,sha256=mQ4Ylh7ZzXAOue8f-x0gqzfS3vAz3XUdD7eQ2XhcEs4,13781
 sparknlp/annotator/seq2seq/mistral_transformer.py,sha256=PJegrSQts_58rkt96xaHlqU1fKIaz8hxt7DTPkGS10A,14254
-sparknlp/annotator/seq2seq/nllb_transformer.py,sha256=hbE2k5YDAZUWPk0qyx6-5xIZi3nBFeFqLcr6lEU9LZ8,19474
+sparknlp/annotator/seq2seq/nllb_transformer.py,sha256=hOmdJOgl_-_PxoADrV-tVYmlfFrqNwvn6Vn2RC4siZM,19534
 sparknlp/annotator/seq2seq/phi2_transformer.py,sha256=WwKCUOH8qGFv62YF63HjuT7bMVldh06gHvaZH3tbSDk,13787
-sparknlp/annotator/seq2seq/phi3_transformer.py,sha256=rIFSS0sit9kUazUvMvwGFSRRsIuFNqpLH28bVKkFzx4,14219
-sparknlp/annotator/seq2seq/qwen_transformer.py,sha256=UmxF84gQsqFVyofuki9TxaPTS_fP71WTj-ylCMLKsYY,14624
+sparknlp/annotator/seq2seq/phi3_transformer.py,sha256=arIcw5NDMv3ubBwWz3KYRdLMsspTiEI8vk4s00lyq1c,14293
+sparknlp/annotator/seq2seq/qwen_transformer.py,sha256=cOpOlz5r_apmVHZgp7uFjybSzVj2yxv8QYlYcGwFyKg,14645
 sparknlp/annotator/seq2seq/starcoder_transformer.py,sha256=BTXbSMRpXnDvrfh-6iFS5k6g6EcPV9zBl4U-SSC19wA,14293
 sparknlp/annotator/seq2seq/t5_transformer.py,sha256=wDVxNLluIU1HGZFqaKKc4YTt4l-elPlAtQ7EEa0f5tg,17308
 sparknlp/annotator/similarity/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -173,7 +176,7 @@ sparknlp/annotator/token/regex_tokenizer.py,sha256=FG2HvFwMb1G_4grfyIQaeBpaAgKv_
 sparknlp/annotator/token/tokenizer.py,sha256=Me3P3wogUKUJ7O7_2wLdPzF00vKpp_sHuiztpGWRVpU,19939
 sparknlp/annotator/ws/__init__.py,sha256=-l8bnl8Z6lGXWOBdRIBZ6958fzTHt4o87QhhLHIFF8A,693
 sparknlp/annotator/ws/word_segmenter.py,sha256=rrbshwn5wzXIHpCCDji6ZcsmiARpuA82_p_6TgNHfRc,16365
-sparknlp/base/__init__.py,sha256=iC4b4NzTDsqEu3eE_f5QL8JD-uoig4Pn2h1ZMyPHR6Q,1266
+sparknlp/base/__init__.py,sha256=fCL-kReIavZceUa1OC99pSRH7MsXzqGB8BXgzVS_f7s,1311
 sparknlp/base/audio_assembler.py,sha256=HKa9mXvmuMUrjTihUZkppGj-WJjcUrm2BGapNuPifyI,3320
 sparknlp/base/doc2_chunk.py,sha256=TyvbdJNkVo9favHlOEoH5JwKbjpk5ZVJ75p8Cilp9jM,6551
 sparknlp/base/document_assembler.py,sha256=zl-SXWMTR3B0EZ8z6SWYchCwEo-61FhU6u7dHUKDIOg,6697
@@ -182,9 +185,10 @@ sparknlp/base/finisher.py,sha256=V4wkMm9Ug09q4zTQc9T9Wr-awmu2Hu-eNaJ039YgZXM,858
 sparknlp/base/graph_finisher.py,sha256=a8fxk3ei2YQw6s0Y9Yy8oMOF1i1XUrgqaiwVE0VPt4w,4834
 sparknlp/base/has_recursive_fit.py,sha256=P55rSHLIXhihXWS2bOC_DskcQTc3njieVD1JkjS2bcA,849
 sparknlp/base/has_recursive_transform.py,sha256=UkGNgo4LMsjQC-Coeefg4bJcg7FoPcPiG382zEa6Ywk,841
-sparknlp/base/image_assembler.py,sha256=HytRoYJTLMqGtvScHoFnp6CasG9IVNYAHYiT2_rrmeE,3719
-sparknlp/base/light_pipeline.py,sha256=Jk2DLpT4PLHCANlOo_WetTdPba_5lYs3ywiyY3lM-PE,16577
+sparknlp/base/image_assembler.py,sha256=HH7ZJ-iZCXnBXVXekQLb1ei_HJuVxhYNVb94OrVLmeY,4068
+sparknlp/base/light_pipeline.py,sha256=2lOstyyK0o6L3BHPIZWQBpIKtJ7LcSz3Pvgo6eZDs5U,17023
 sparknlp/base/multi_document_assembler.py,sha256=4htET1fRAeOB6zhsNXsBq5rKZvn-LGD4vrFRjPZeqow,7070
+sparknlp/base/prompt_assembler.py,sha256=ysU4Vbmnuv2UBHK0JBkYrxiZiJ7_GTcVMip1-QRmheI,11570
 sparknlp/base/recursive_pipeline.py,sha256=V9rTnu8KMwgjoceykN9pF1mKGtOkkuiC_n9v8dE3LDk,4279
 sparknlp/base/table_assembler.py,sha256=Kxu3R2fY6JgCxEc07ibsMsjip6dgcPDHLiWAZ8gC_d8,5102
 sparknlp/base/token_assembler.py,sha256=qiHry07L7mVCqeHSH6hHxLygv1AsfZIE4jy1L75L3Do,5075
@@ -200,7 +204,7 @@ sparknlp/common/read_as.py,sha256=imxPGwV7jr4Li_acbo0OAHHRGCBbYv-akzEGaBWEfcY,12
 sparknlp/common/recursive_annotator_approach.py,sha256=vqugBw22cE3Ff7PIpRlnYFuOlchgL0nM26D8j-NdpqU,1449
 sparknlp/common/storage.py,sha256=D91H3p8EIjNspjqAYu6ephRpCUtdcAir4_PrAbkIQWE,4842
 sparknlp/common/utils.py,sha256=Yne6yYcwKxhOZC-U4qfYoDhWUP_6BIaAjI5X_P_df1E,1306
-sparknlp/internal/__init__.py,sha256=nK-9lncAVRXmyP8ATbiMwRnLJVe4IEd_r5Z3gEqDK3g,33672
+sparknlp/internal/__init__.py,sha256=BttGS21n2-LGjx8udi7f4_nNt_BeUnfif9WpeZchuFE,34502
 sparknlp/internal/annotator_java_ml.py,sha256=UGPoThG0rGXUOXGSQnDzEDW81Mu1s5RPF29v7DFyE3c,1187
 sparknlp/internal/annotator_transformer.py,sha256=fXmc2IWXGybqZpbEU9obmbdBYPc798y42zvSB4tqV9U,1448
 sparknlp/internal/extended_java_wrapper.py,sha256=hwP0133-hDiDf5sBF-P3MtUsuuDj1PpQbtGZQIRwzfk,2240
@@ -212,6 +216,8 @@ sparknlp/pretrained/__init__.py,sha256=GV-x9UBK8F2_IR6zYatrzFcVJtkSUIMbxqWsxRUeP
 sparknlp/pretrained/pretrained_pipeline.py,sha256=lquxiaABuA68Rmu7csamJPqBoRJqMUO0oNHsmEZDAIs,5740
 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/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
@@ -242,8 +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-5.5.0rc1.dist-info/.uuid,sha256=1f6hF51aIuv9yCvh31NU9lOpS34NE-h3a0Et7R9yR6A,36
-spark_nlp-5.5.0rc1.dist-info/METADATA,sha256=c9a30g4ogelUAj-Np3naOPq4lWx6mGRgXD59IjQlr1M,55774
-spark_nlp-5.5.0rc1.dist-info/WHEEL,sha256=bb2Ot9scclHKMOLDEHY6B2sicWOgugjFKaJsT7vwMQo,110
-spark_nlp-5.5.0rc1.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
-spark_nlp-5.5.0rc1.dist-info/RECORD,,
+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,,

sparknlp/__init__.py

@@ -12,17 +12,20 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-import sys
 import subprocess
+import sys
 import threading
+
+from pyspark.conf import SparkConf
+from pyspark.context import SparkContext
+from pyspark.java_gateway import launch_gateway
 from pyspark.sql import SparkSession
+
 from sparknlp import annotator
 # Must be declared here one by one or else PretrainedPipeline will fail with AttributeError
 from sparknlp.base import DocumentAssembler, MultiDocumentAssembler, Finisher, EmbeddingsFinisher, TokenAssembler, \
     Doc2Chunk, AudioAssembler, GraphFinisher, ImageAssembler, TableAssembler
-from pyspark.conf import SparkConf
-from pyspark.context import SparkContext
-from pyspark.java_gateway import launch_gateway
+from sparknlp.reader import SparkNLPReader
 
 sys.modules['com.johnsnowlabs.nlp.annotators'] = annotator
 sys.modules['com.johnsnsowlabs.nlp.annotators.tokenizer'] = annotator
@@ -129,7 +132,7 @@ def start(gpu=False,
         The initiated Spark session.
 
     """
-    current_version = "5.5.0-rc1"
+    current_version = "5.5.2"
 
     if params is None:
         params = {}
@@ -301,6 +304,9 @@ def start(gpu=False,
         spark_session = start_without_realtime_output()
         return spark_session
 
+def read(params=None):
+    spark_session = start()
+    return SparkNLPReader(spark_session, params)
 
 def version():
     """Returns the current Spark NLP version.
@@ -310,4 +316,4 @@ def version():
     str
         The current Spark NLP version.
     """
-    return '5.5.0-rc1'
+    return '5.5.2'

sparknlp/annotator/classifier_dl/__init__.py

@@ -54,3 +54,4 @@ from sparknlp.annotator.classifier_dl.mpnet_for_question_answering import *
 from sparknlp.annotator.classifier_dl.mpnet_for_token_classification import *
 from sparknlp.annotator.classifier_dl.albert_for_zero_shot_classification import *
 from sparknlp.annotator.classifier_dl.camembert_for_zero_shot_classification import *
+from sparknlp.annotator.classifier_dl.bert_for_multiple_choice import *