spark-nlp 6.0.1rc1__py2.py3-none-any.whl → 6.0.3__py2.py3-none-any.whl

{spark_nlp-6.0.1rc1.dist-info → spark_nlp-6.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.0.1rc1
+Version: 6.0.3
 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
@@ -29,6 +29,13 @@ Classifier: Topic :: Text Processing :: Linguistic
 Classifier: Topic :: Scientific/Engineering
 Classifier: Typing :: Typed
 Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: summary
 
 # Spark NLP: State-of-the-Art Natural Language Processing & LLMs Library
 
@@ -95,7 +102,7 @@ $ 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==6.0.1 pyspark==3.3.1
+$ pip install spark-nlp==6.0.3 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -161,7 +168,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *6.0.1* 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 *6.0.3* 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 |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -191,7 +198,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.0.1 has been tested and is compatible with the following runtimes:
+Spark NLP 6.0.3 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -208,7 +215,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.0.1 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.0.3 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.0.1rc1.dist-info → spark_nlp-6.0.3.dist-info}/RECORD

@@ -3,20 +3,20 @@ 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=bmd2osfOpjsl6fkGAziSKpz0F5tFXASPI-9L-0GJatQ,13791
+sparknlp/__init__.py,sha256=wE5XbgWtMI8X1kifJLQ43sFkaUAyfmkZj-wiBtT3YKU,13814
 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
 sparknlp/functions.py,sha256=4cVRyBjlF1YttcMNs5z7gf9NPW7q9qzGb5KOf44Phgs,12120
 sparknlp/upload_to_hub.py,sha256=toULNLeXK3MmTpmza9dR8R8od2QJEw1eTgBDM-O9_I0,6018
-sparknlp/util.py,sha256=PDbD6c9y0IAtzXK5dzhBSqghouKHpXNVnXyWS2Y20UU,1276
+sparknlp/util.py,sha256=2Z499Psal-NuEJ4CHQNgHnAJrS73QQNyCzKPo1MavU8,2279
 sparknlp/annotator/__init__.py,sha256=G746SY8dRM_AOf-gaoSKlh7D-2TKGpqqHhGr4XF-b2A,3534
 sparknlp/annotator/chunk2_doc.py,sha256=IJ3_vQHvzjqono90AZUzZ67QSYjwquuMYbN9_HSOVcg,3141
 sparknlp/annotator/chunker.py,sha256=8nz9B7R_mxKxcfJRfKvz2x_T29W3u4izE9k0wfYPzgE,5174
-sparknlp/annotator/date2_chunk.py,sha256=0Z0ofEVes8ZMxvgnXbGZX91IfGxI3CdYTRMALabsJUc,3152
-sparknlp/annotator/document_character_text_splitter.py,sha256=dFNhik4IM0K9o65S3vHz-Txcv8AswRCYh5o1uEZOvy8,9864
+sparknlp/annotator/date2_chunk.py,sha256=tW3m_LExmhx8LMFWOGXqMyfNRXSr2dnoEHD-6DrnpXI,3153
+sparknlp/annotator/document_character_text_splitter.py,sha256=oNrOKJAKO2h1wr0bEuSqYrrltIU_Y6J6cTHy70yKy6s,9877
 sparknlp/annotator/document_normalizer.py,sha256=hU2fG6vaPfdngQapoeSu-_zS_LiBZNp2tcVBGl6eTpk,10973
-sparknlp/annotator/document_token_splitter.py,sha256=gRpSkZQFhNTvb0c8CII6LlTYOVTLSro1u-luDzxnYps,7483
+sparknlp/annotator/document_token_splitter.py,sha256=-9xbQ9pVAjcKHQQrSk6Cb7f8W1cblCLwWXTNR8kFptA,7499
 sparknlp/annotator/document_token_splitter_test.py,sha256=NWO9mwhAIUJFuxPofB3c39iUm_6vKp4pteDsBOTH8ng,2684
 sparknlp/annotator/graph_extraction.py,sha256=b4SB3B_hFgCJT4e5Jcscyxdzfbvw3ujKTa6UNgX5Lhc,14471
 sparknlp/annotator/lemmatizer.py,sha256=w1nNMln2HgM4O1DOaISo5AGyzzFHuaIDQqWFcr4JmcA,8970
@@ -82,36 +82,39 @@ sparknlp/annotator/cleaners/cleaner.py,sha256=r_0ImrtGT-S-ytOknKoP844FVSv0J9YVKQ
 sparknlp/annotator/cleaners/extractor.py,sha256=nml8mnOToZYPF5fTp9VWdDfnWTXryLDzp3RWfQoJkWY,5805
 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=ySHQ_8pumJFESLUtDqvb0X9oX6He-w_-Jw--Z3ASU5w,1473
+sparknlp/annotator/cv/__init__.py,sha256=hUeHb0iTDBZCS3sDAjypgs8PzU3eMgKtBa8xDkCueWE,1591
 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/gemma3_for_multimodal.py,sha256=dh0KjTJGqpD-yN7d2f2auMbKLwL5w74Rhgai5y0LeHw,13053
-sparknlp/annotator/cv/janus_for_multimodal.py,sha256=-TlAfeZ3A8iMJ23Q05Tx_KObgBfy9-qYAN9gAPCvjbw,14499
-sparknlp/annotator/cv/llava_for_multimodal.py,sha256=kzOcZs08yCnB9AgaogZG28SguGqVUw9sumijhM5YRFU,12064
+sparknlp/annotator/cv/florence2_transformer.py,sha256=jyXTY0om_8J_9GwlH5Dkussb1g6ra642ATzLaqv7TSI,8525
+sparknlp/annotator/cv/gemma3_for_multimodal.py,sha256=475lYkf05Naw3tsdTScTs-tnHgFkbcCab7r6UwEXzvg,13017
+sparknlp/annotator/cv/internvl_for_multimodal.py,sha256=1j_lZwZw4Mt9_EucxemuPo2buq_uj5aIkniE9mbegag,10851
+sparknlp/annotator/cv/janus_for_multimodal.py,sha256=BGkXGvIf-upDai216m12-WHJCUmv-NRQ9ArEW2Wt0V0,14502
+sparknlp/annotator/cv/llava_for_multimodal.py,sha256=okfBIuWgPK7VhRxznZDoPXNIIxc6g_NM0l5aH4yibVY,12068
 sparknlp/annotator/cv/mllama_for_multimodal.py,sha256=e4_bOGycy-gPYrl8en0mOP3eF8p17Xt85nwE5kmez5g,13071
-sparknlp/annotator/cv/paligemma_for_multimodal.py,sha256=nqwGWRG4kc7FJ26DMwwhkN7FnBWGBZsTjL9H-scs69Q,11204
-sparknlp/annotator/cv/phi3_vision_for_multimodal.py,sha256=MPGj07Gi-QCE5Ew5l3_SqUqBIR4Tvhhi1ZVbkuX-ihU,12127
-sparknlp/annotator/cv/qwen2vl_transformer.py,sha256=S2jFwMfh-2iaTl7t8SndH1U1dHSpnlW6E0IQBtw_Xak,12565
-sparknlp/annotator/cv/smolvlm_transformer.py,sha256=JJINJfo_tUvgZ89AG3YqJQ99yjqZpUzJ5vEfISXOeh0,16963
+sparknlp/annotator/cv/paligemma_for_multimodal.py,sha256=C2fRsppihEJK4YK-hoGrirGUyof4fV_r28HWOYb4Yms,11214
+sparknlp/annotator/cv/phi3_vision_for_multimodal.py,sha256=94nlNbcDgJW0zX2QIjJl1cMXi1i6wqQeNG61CdoPLKA,12131
+sparknlp/annotator/cv/qwen2vl_transformer.py,sha256=q2BCs1qA8fyqbMsnW4-6wbGJim4QjVUuDHOXhtMXJcY,12570
+sparknlp/annotator/cv/smolvlm_transformer.py,sha256=g7eypRcMrPW4pYyTHmxBjP8tA_B_4rRwPbUCe3XHz-0,16964
 sparknlp/annotator/cv/swin_for_image_classification.py,sha256=iZ1KY0GInbQmGzkmuNbds4PGPwCheLXc-Syv2HRmqug,10694
 sparknlp/annotator/cv/vision_encoder_decoder_for_image_captioning.py,sha256=rEWJte-qN6PI6ML2cGhsZ37wAzjHUtN_WD5pcKAez7M,10167
 sparknlp/annotator/cv/vit_for_image_classification.py,sha256=D2V3pxAd3rBi1817lxVOqaVvCw4trcVyorQgIPdLNAE,9148
 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=KHDCHb8SMlkSGGSu69SfKneUDDUlBdMGdMzDrYp_cis,2408
+sparknlp/annotator/embeddings/__init__.py,sha256=mp1Nb6xooX6YYyJt9xVpYrSPseuJrEpnNKCpp2QiFWo,2466
 sparknlp/annotator/embeddings/albert_embeddings.py,sha256=6Rd1LIn8oFIpq_ALcJh-RUjPEO7Ht8wsHY6JHSFyMkw,9995
 sparknlp/annotator/embeddings/auto_gguf_embeddings.py,sha256=IlqkPGOH2lmZvxEyDSGX-G90DtTFOe2Rvujfbg5zvlU,20185
 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=Y4b6QzRJGc_Z9_R6SYq-P5NxcvI9XzJlBzwCLLHJpRo,8103
+sparknlp/annotator/embeddings/bge_embeddings.py,sha256=ZGbxssjJFaSfbcgqAPV5hsu81SnC0obgCVNOoJkArDA,8105
 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
 sparknlp/annotator/embeddings/distil_bert_embeddings.py,sha256=4pyMCsbvvXYeTGIMVUir9wCDKR_1f_HKtXZrTDO1Thc,9275
 sparknlp/annotator/embeddings/doc2vec.py,sha256=Xk3MdEkXatX9lRgbFbAdnIDrLgIxzUIGWFBZeo9BTq0,13226
 sparknlp/annotator/embeddings/e5_embeddings.py,sha256=Esuvrq9JlogGaSSzFVVDkOFMwgYwFwr17I62ZiCDm0k,7858
+sparknlp/annotator/embeddings/e5v_embeddings.py,sha256=NFHO2nxDcgVzyKQ6yz1BWyqtjwt9QHwlkKbBXFwhsO8,5951
 sparknlp/annotator/embeddings/elmo_embeddings.py,sha256=KV-KPs0Pq_OpPaHsnqBz2k_S7VdzyFZ4632IeFNKqJ8,9858
 sparknlp/annotator/embeddings/instructor_embeddings.py,sha256=CTKmbuBOx_KBM4JM-Y1U5LyR-6rrnpoBGbgGE_axS1c,8670
 sparknlp/annotator/embeddings/longformer_embeddings.py,sha256=jS4fxB5O0-d9ta9VKv8ai-17n5YHt5rML8QxUw7K4Io,8754
@@ -121,7 +124,7 @@ sparknlp/annotator/embeddings/nomic_embeddings.py,sha256=WTllH3htx9wDD2Le8pZgKVP
 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
-sparknlp/annotator/embeddings/snowflake_embeddings.py,sha256=2k7oxSSgu2Y8U2fkfZCCneG9PQjXzmJsl41BDsD0hfE,7260
+sparknlp/annotator/embeddings/snowflake_embeddings.py,sha256=QzMSzmgSTedEAk0TlpHHBMjV0pPj8efLqVAVJqKgTgs,7253
 sparknlp/annotator/embeddings/uae_embeddings.py,sha256=sqTT67vcegVxcyoATISLPJSmOnA6J_otB6iREKOb6e4,8794
 sparknlp/annotator/embeddings/universal_sentence_encoder.py,sha256=_fTo-K78RjxiIKptpsI32mpW87RFCdXM16epHv4RVQY,8571
 sparknlp/annotator/embeddings/word2vec.py,sha256=UBhA4qUczQOx1t82Eu51lxx1-wJ_RLnCb__ncowSNhk,13229
@@ -149,7 +152,7 @@ sparknlp/annotator/ner/ner_dl.py,sha256=ght1W6-ArjLRiNHCv_bKpozkyNd8HVIb8SDGhcbp
 sparknlp/annotator/ner/ner_overwriter.py,sha256=en5OxXIP46yTXokIE96YDP9kcHA9oxiRPgwXMo0otew,6798
 sparknlp/annotator/ner/zero_shot_ner_model.py,sha256=DohhnkGSG-JxjW72t8AOx3GY7R_qT-LA3I0KF9TBz-Y,7501
 sparknlp/annotator/openai/__init__.py,sha256=u6SpV_xS8UpBE95WnTl0IefOI5TrTRl7ZHuYoeTetiA,759
-sparknlp/annotator/openai/openai_completion.py,sha256=OqDODelDAxlS66a4mAqJqXMFlEhaeiKZD4XBzR98k-g,16859
+sparknlp/annotator/openai/openai_completion.py,sha256=vetyDRGs-ge0pxMojEaNFhVy50Sf7Sm0tsh0I71i2Ss,16867
 sparknlp/annotator/openai/openai_embeddings.py,sha256=i1ABDRmK6vMzzWP1rVxFiWnvXG4zfrTGGDjq4lvWQeE,108802
 sparknlp/annotator/param/__init__.py,sha256=MKBZs6NWRKxrpeof3Jr4PVmoa75wyRSdWzSt0A9lpfY,750
 sparknlp/annotator/param/classifier_encoder.py,sha256=PDyOdUX2GOFVr6MLtB7RUPBdtDrzDNJNRe_r9bY5JpE,3005
@@ -171,20 +174,20 @@ sparknlp/annotator/seq2seq/cpm_transformer.py,sha256=0CnBFMlxMu0pD2QZMHyoGtIYgXq
 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=wmhgWQkO__H1vIGnAMjUU14Gtit4qOcE1m9YpM6YkB4,14950
-sparknlp/annotator/seq2seq/m2m100_transformer.py,sha256=uIL9RZuuryTIdAy9TbJf9wbz6RekhW8S079bJhaB6i4,16116
+sparknlp/annotator/seq2seq/m2m100_transformer.py,sha256=brlOWjvdbDPfycTUMWnXnQjA9qY9I8ljJJpEd1Gwq5Q,16128
 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=hOmdJOgl_-_PxoADrV-tVYmlfFrqNwvn6Vn2RC4siZM,19534
+sparknlp/annotator/seq2seq/mistral_transformer.py,sha256=6lVrhWvW8b_3DaQtpegigFL25tELThRHZQRxxNhZuAU,14250
+sparknlp/annotator/seq2seq/nllb_transformer.py,sha256=1ys01yaC0nVzXETy8oD2wZHyombfLzK1cetKrVGTVyY,19546
 sparknlp/annotator/seq2seq/olmo_transformer.py,sha256=B_zhYkAfYycw5uBq1tVNPmaKuYtpJOxRC6PArit7XiE,13634
 sparknlp/annotator/seq2seq/phi2_transformer.py,sha256=WwKCUOH8qGFv62YF63HjuT7bMVldh06gHvaZH3tbSDk,13787
 sparknlp/annotator/seq2seq/phi3_transformer.py,sha256=arIcw5NDMv3ubBwWz3KYRdLMsspTiEI8vk4s00lyq1c,14293
-sparknlp/annotator/seq2seq/qwen_transformer.py,sha256=cOpOlz5r_apmVHZgp7uFjybSzVj2yxv8QYlYcGwFyKg,14645
+sparknlp/annotator/seq2seq/qwen_transformer.py,sha256=IYxveoHGWWoiwzJ_VMLMgUBe6jr1JSHKSY0PApnTCOI,14640
 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
 sparknlp/annotator/similarity/document_similarity_ranker.py,sha256=BHV2XWA18YvBn_OKOVvR0TmPPnHSgiAgpZpaPz7ar_s,15826
 sparknlp/annotator/spell_check/__init__.py,sha256=sdnPR3f3Q9mHiv-n4g_O7KpRWPRPweyATSF6Tth_Niw,830
-sparknlp/annotator/spell_check/context_spell_checker.py,sha256=OtjN51K3TyQpFmZrhPrvxZwCJsENFwTkeNKQYWrP-Gw,31992
+sparknlp/annotator/spell_check/context_spell_checker.py,sha256=-YFymfJoMr_4yTSoiWMcrPq4JbyygaRONX-tMQXHw9k,31989
 sparknlp/annotator/spell_check/norvig_sweeting.py,sha256=6ET9KnAqXIQDJ5U9px1ixUbC6R63ln_ljruvh_oLiwA,13197
 sparknlp/annotator/spell_check/symmetric_delete.py,sha256=ms8BPrFOITqppShZmEEiqVhjE-pwVb7jI5NSCQ4XM0A,11058
 sparknlp/annotator/token/__init__.py,sha256=cu5njC9peW4_toFOvnHgYzHXsMqxlpPf1p7C4VxoDMk,861
@@ -206,7 +209,7 @@ sparknlp/base/has_recursive_transform.py,sha256=UkGNgo4LMsjQC-Coeefg4bJcg7FoPcPi
 sparknlp/base/image_assembler.py,sha256=-ylzVaDdjJBDQNkTixsCn7WvFB8cqC3_lPdvdiJu0aM,6168
 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/prompt_assembler.py,sha256=_C_9MdHqsxUjSOa3TqCV-6sSfSiRyhfHBQG5m7RlqxY,11578
 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
@@ -217,12 +220,12 @@ 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=vuvF5eUq4H2LxgIhIPsjeS8AF4JJcRDEicmLqyeRgmk,51457
+sparknlp/common/properties.py,sha256=v8PUB0YqeiZRzP8mX3kXSFoQVMZOg_ips0Y5M54hUIc,51493
 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
 sparknlp/common/utils.py,sha256=Yne6yYcwKxhOZC-U4qfYoDhWUP_6BIaAjI5X_P_df1E,1306
-sparknlp/internal/__init__.py,sha256=YtsUXuuHzv4lATbepu7BhWJEc7Vo65OtEgphxEHOa5Q,39168
+sparknlp/internal/__init__.py,sha256=ALwce14xOPRxfAPFhlINH4BVH0w3Mjp4_VWV4hSxNJ8,40146
 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
@@ -230,20 +233,24 @@ sparknlp/internal/params_getters_setters.py,sha256=LtaKAzD8fEupEPy9vYOI2St7A3PcZ
 sparknlp/internal/recursive.py,sha256=YfsjOmUUccFOHxheIXf-rps8yc4PPqFCje94_7dS4iw,2756
 sparknlp/logging/__init__.py,sha256=DoROFF5KLZe4t4Q-OHxqk1nhqbw9NQ-wb64y8icNwgw,642
 sparknlp/logging/comet.py,sha256=_ZBi9-hlilCAnd4lvdYMWiq4Vqsppv8kow3k0cf-NG4,15958
+sparknlp/partition/__init__.py,sha256=L0w-yv_HnnvoKlSX5MzI2GKHW3RLLfGyq8bgWYVeKjU,749
+sparknlp/partition/partition.py,sha256=GXEAUvOea04Vc_JK0z112cAKFrJ4AEpjLJ8xlzZt6Kw,8551
+sparknlp/partition/partition_properties.py,sha256=xhAMhlsTBg-WS6KWDyVbRPwO7IzpowVVhJNR-ZGhvdo,9520
+sparknlp/partition/partition_transformer.py,sha256=lRR1h-IMlHR8M0VeB50SbU39GHHF5PgMaJ42qOriS6A,6855
 sparknlp/pretrained/__init__.py,sha256=GV-x9UBK8F2_IR6zYatrzFcVJtkSUIMbxqWsxRUePmQ,793
 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/enums.py,sha256=MNGug9oJ1BBLM1Pbske13kAabalDzHa2kucF5xzFpHs,770
-sparknlp/reader/pdf_to_text.py,sha256=o2-ZqioR3-apGDo5WCb0_I0sEQr6O-CGMfMb4W4YSss,3892
-sparknlp/reader/sparknlp_reader.py,sha256=BEKfT9JaOWlA2ddsMNiC-pVRrM9Ad_4J4-Ur3iCNKH0,38218
+sparknlp/reader/pdf_to_text.py,sha256=pI1BBQ44tXn8GIMv--_kZJ3bPP8R9Q1lYejkfhi5pMQ,5739
+sparknlp/reader/sparknlp_reader.py,sha256=ybnMlwJaBOVbjDw7ng39jcrshlQzexwq98_PTwVeM8g,16779
 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
 sparknlp/training/pos.py,sha256=YchvPWksMAYvM6XPLNzbS-Kr96CRpLMSr21qe76m1PY,4091
 sparknlp/training/pub_tator.py,sha256=2DWuNJqAl81_Izaa_qoQMHkpeqDP8sA7mhehc6vI7Gw,3331
-sparknlp/training/spacy_to_annotation.py,sha256=uBSu3jb1El3WDWNXEMP8EkX44FZOwb-SJbhZkuBQPHs,6798
+sparknlp/training/spacy_to_annotation.py,sha256=b8WCqwr0kBRWa695ajDAxNVFg_z0yD1U1_dS3ryMY0I,6826
 sparknlp/training/tfgraphs.py,sha256=Hl3vp9VhLX_IinqOvtIH0r9Bf2BgcGrFKG5wBu3qTmc,244
 sparknlp/training/_tf_graph_builders/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sparknlp/training/_tf_graph_builders/graph_builders.py,sha256=0WqVTRnZValftGpGm6tYJCOQmJUL_B2pjZSQu8dLqs0,10819
@@ -268,7 +275,7 @@ 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-6.0.1rc1.dist-info/METADATA,sha256=z-li7N02SZLSg5k3RXH9w_GbQKh1ro03sRnl030YIQ8,19580
-spark_nlp-6.0.1rc1.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-spark_nlp-6.0.1rc1.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
-spark_nlp-6.0.1rc1.dist-info/RECORD,,
+spark_nlp-6.0.3.dist-info/METADATA,sha256=qMqGlXdyZgzm8D3KkC03Jl73y7S_cAh24necRw1G_Qc,19722
+spark_nlp-6.0.3.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
+spark_nlp-6.0.3.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
+spark_nlp-6.0.3.dist-info/RECORD,,

{spark_nlp-6.0.1rc1.dist-info → spark_nlp-6.0.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py2-none-any
 Tag: py3-none-any

sparknlp/__init__.py

@@ -66,6 +66,8 @@ sys.modules['com.johnsnowlabs.ml.ai'] = annotator
 annotators = annotator
 embeddings = annotator
 
+__version__ = "6.0.3"
+
 
 def start(gpu=False,
           apple_silicon=False,
@@ -132,7 +134,7 @@ def start(gpu=False,
         The initiated Spark session.
 
     """
-    current_version = "6.0.1-rc1"
+    current_version = __version__
 
     if params is None:
         params = {}
@@ -316,4 +318,4 @@ def version():
     str
         The current Spark NLP version.
     """
-    return '6.0.1-rc1'
+    return __version__

sparknlp/annotator/cv/__init__.py

@@ -25,3 +25,5 @@ from sparknlp.annotator.cv.phi3_vision_for_multimodal import *
 from sparknlp.annotator.cv.smolvlm_transformer import *
 from sparknlp.annotator.cv.paligemma_for_multimodal import *
 from sparknlp.annotator.cv.gemma3_for_multimodal import *
+from sparknlp.annotator.cv.internvl_for_multimodal import *
+from sparknlp.annotator.cv.florence2_transformer import *

sparknlp/annotator/cv/florence2_transformer.py

@@ -0,0 +1,180 @@
+#  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 Florence2Transformer(AnnotatorModel,
+                 HasBatchedAnnotateImage,
+                 HasImageFeatureProperties,
+                 HasEngine):
+    """Florence2Transformer can load Florence-2 models for a variety of vision and vision-language tasks using prompt-based inference.
+
+    The model supports image captioning, object detection, segmentation, OCR, and more, using prompt tokens as described in the Florence-2 documentation.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion object:
+
+    >>> florence2 = Florence2Transformer.pretrained() \
+    ...     .setInputCols(["image_assembler"]) \
+    ...     .setOutputCol("answer")
+
+    The default model is ``"florence2_base_ft_int4"``, if no name is provided.
+
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models?task=Vision+Tasks>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``IMAGE``              ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more memory, by default 2
+    maxOutputLength
+        Maximum length of output text, by default 200
+    minOutputLength
+        Minimum length of the sequence to be generated, by default 10
+    doSample
+        Whether or not to use sampling; use greedy decoding otherwise, by default False
+    temperature
+        The value used to module the next token probabilities, by default 1.0
+    topK
+        The number of highest probability vocabulary tokens to keep for top-k-filtering, by default 50
+    topP
+        If set to float < 1, only the most probable tokens with probabilities that add up to ``top_p`` or higher are kept for generation, by default 1.0
+    repetitionPenalty
+        The parameter for repetition penalty. 1.0 means no penalty, by default 1.0
+    noRepeatNgramSize
+        If set to int > 0, all ngrams of that size can only occur once, by default 3
+    ignoreTokenIds
+        A list of token ids which are ignored in the decoder's output, by default []
+    beamSize
+        The Number of beams for beam search, by default 1
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> image_df = spark.read.format("image").load(path=images_path)
+    >>> test_df = image_df.withColumn("text", lit("<OD>"))
+    >>> imageAssembler = ImageAssembler() \
+    ...     .setInputCol("image") \
+    ...     .setOutputCol("image_assembler")
+    >>> florence2 = Florence2Transformer.pretrained() \
+    ...     .setInputCols(["image_assembler"]) \
+    ...     .setOutputCol("answer")
+    >>> pipeline = Pipeline().setStages([
+    ...     imageAssembler,
+    ...     florence2
+    ... ])
+    >>> result = pipeline.fit(test_df).transform(test_df)
+    >>> result.select("image_assembler.origin", "answer.result").show(False)
+    """
+
+    name = "Florence2Transformer"
+
+    inputAnnotatorTypes = [AnnotatorType.IMAGE]
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    minOutputLength = Param(Params._dummy(), "minOutputLength", "Minimum length of the sequence to be generated", typeConverter=TypeConverters.toInt)
+    maxOutputLength = Param(Params._dummy(), "maxOutputLength", "Maximum length of output text", typeConverter=TypeConverters.toInt)
+    doSample = Param(Params._dummy(), "doSample", "Whether or not to use sampling; use greedy decoding otherwise", typeConverter=TypeConverters.toBoolean)
+    temperature = Param(Params._dummy(), "temperature", "The value used to module the next token probabilities", typeConverter=TypeConverters.toFloat)
+    topK = Param(Params._dummy(), "topK", "The number of highest probability vocabulary tokens to keep for top-k-filtering", typeConverter=TypeConverters.toInt)
+    topP = Param(Params._dummy(), "topP", "If set to float < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation", typeConverter=TypeConverters.toFloat)
+    repetitionPenalty = Param(Params._dummy(), "repetitionPenalty", "The parameter for repetition penalty. 1.0 means no penalty.", typeConverter=TypeConverters.toFloat)
+    noRepeatNgramSize = Param(Params._dummy(), "noRepeatNgramSize", "If set to int > 0, all ngrams of that size can only occur once", typeConverter=TypeConverters.toInt)
+    ignoreTokenIds = Param(Params._dummy(), "ignoreTokenIds", "A list of token ids which are ignored in the decoder's output", typeConverter=TypeConverters.toListInt)
+    beamSize = Param(Params._dummy(), "beamSize", "The Number of beams for beam search.", typeConverter=TypeConverters.toInt)
+    batchSize = Param(Params._dummy(), "batchSize", "Batch size. Large values allows faster processing but requires more memory", typeConverter=TypeConverters.toInt)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.cv.Florence2Transformer", java_model=None):
+        super(Florence2Transformer, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=2,
+            minOutputLength=10,
+            maxOutputLength=200,
+            doSample=False,
+            temperature=1.0,
+            topK=50,
+            topP=1.0,
+            repetitionPenalty=1.0,
+            noRepeatNgramSize=3,
+            ignoreTokenIds=[],
+            beamSize=1,
+        )
+
+    def setMinOutputLength(self, value):
+        """Sets minimum length of the sequence to be generated."""
+        return self._set(minOutputLength=value)
+
+    def setMaxOutputLength(self, value):
+        """Sets maximum length of output text."""
+        return self._set(maxOutputLength=value)
+
+    def setDoSample(self, value):
+        """Sets whether or not to use sampling; use greedy decoding otherwise."""
+        return self._set(doSample=value)
+
+    def setTemperature(self, value):
+        """Sets the value used to module the next token probabilities."""
+        return self._set(temperature=value)
+
+    def setTopK(self, value):
+        """Sets the number of highest probability vocabulary tokens to keep for top-k-filtering."""
+        return self._set(topK=value)
+
+    def setTopP(self, value):
+        """Sets the top cumulative probability for vocabulary tokens."""
+        return self._set(topP=value)
+
+    def setRepetitionPenalty(self, value):
+        """Sets the parameter for repetition penalty. 1.0 means no penalty."""
+        return self._set(repetitionPenalty=value)
+
+    def setNoRepeatNgramSize(self, value):
+        """Sets size of n-grams that can only occur once."""
+        return self._set(noRepeatNgramSize=value)
+
+    def setIgnoreTokenIds(self, value):
+        """A list of token ids which are ignored in the decoder's output."""
+        return self._set(ignoreTokenIds=value)
+
+    def setBeamSize(self, value):
+        """Sets the number of beams for beam search."""
+        return self._set(beamSize=value)
+
+    def setBatchSize(self, value):
+        """Sets the batch size."""
+        return self._set(batchSize=value)
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session, use_openvino=False):
+        """Loads a locally saved model."""
+        from sparknlp.internal import _Florence2TransformerLoader
+        jModel = _Florence2TransformerLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
+        return Florence2Transformer(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="florence2_base_ft_int4", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model."""
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(Florence2Transformer, name, lang, remote_loc) 

sparknlp/annotator/cv/gemma3_for_multimodal.py

@@ -83,23 +83,18 @@ class Gemma3ForMultiModal(AnnotatorModel,
     >>> from sparknlp.annotator import *
     >>> from pyspark.ml import Pipeline
     >>> from pyspark.sql.functions import lit
-    >>> 
     >>> imageDF = spark.read.format("image").load(images_path)
-    >>> testDF = imageDF.withColumn("text", lit("<bos><start_of_turn>user\nYou are a helpful assistant.\n\n<start_of_image>Describe this image in detail.<end_of_turn>\n<start_of_turn>model\n"))
-    >>> 
-    >>> imageAssembler = ImageAssembler() \
-    ...     .setInputCol("image") \
+    >>> testDF = imageDF.withColumn("text", lit("<bos><start_of_turn>user\\nYou are a helpful assistant.\\n\\n<start_of_image>Describe this image in detail.<end_of_turn>\\n<start_of_turn>model\\n"))
+    >>> imageAssembler = ImageAssembler() \\
+    ...     .setInputCol("image") \\
     ...     .setOutputCol("image_assembler")
-    >>> 
-    >>> visualQA = Gemma3ForMultiModal.pretrained() \
-    ...     .setInputCols("image_assembler") \
+    >>> visualQA = Gemma3ForMultiModal.pretrained() \\
+    ...     .setInputCols("image_assembler") \\
     ...     .setOutputCol("answer")
-    >>> 
     >>> pipeline = Pipeline().setStages([
     ...     imageAssembler,
     ...     visualQA
     ... ])
-    >>> 
     >>> result = pipeline.fit(testDF).transform(testDF)
     >>> result.select("image_assembler.origin", "answer.result").show(truncate=False)
     """