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

sparknlp/annotator/embeddings/e5v_embeddings.py

@@ -0,0 +1,138 @@
+#  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 E5VEmbeddings(AnnotatorModel,
+                   HasBatchedAnnotateImage,
+                   HasImageFeatureProperties,
+                   HasEngine,
+                    HasRescaleFactor):
+    """Universal multimodal embeddings using the E5-V model (see https://huggingface.co/royokong/e5-v).
+
+    E5-V bridges the modality gap between different input types (text, image) and demonstrates strong performance in multimodal embeddings, even without fine-tuning. It also supports a single-modality training approach, where the model is trained exclusively on text pairs, often yielding better performance than multimodal training.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion object:
+
+    >>> e5vEmbeddings = E5VEmbeddings.pretrained() \
+    ...     .setInputCols(["image_assembler"]) \
+    ...     .setOutputCol("e5v")
+
+    The default model is ``"e5v_int4"``, if no name is provided.
+
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models?task=Question+Answering>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``IMAGE``              ``SENTENCE_EMBEDDINGS``
+    ====================== ======================
+
+    Examples
+    --------
+    Image + Text Embedding:
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> image_df = spark.read.format("image").option("dropInvalid", value = True).load(imageFolder)
+    >>> imagePrompt = "<|start_header_id|>user<|end_header_id|>\n\n<image>\\nSummary above image in one word: <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n \n"
+    >>> test_df = image_df.withColumn("text", lit(imagePrompt))
+    >>> imageAssembler = ImageAssembler() \
+    ...     .setInputCol("image") \
+    ...     .setOutputCol("image_assembler")
+    >>> e5vEmbeddings = E5VEmbeddings.pretrained() \
+    ...     .setInputCols(["image_assembler"]) \
+    ...     .setOutputCol("e5v")
+    >>> pipeline = Pipeline().setStages([
+    ...     imageAssembler,
+    ...     e5vEmbeddings
+    ... ])
+    >>> result = pipeline.fit(test_df).transform(test_df)
+    >>> result.select("e5v.embeddings").show(truncate = False)
+
+    Text-Only Embedding:
+    >>> from sparknlp.util import EmbeddingsDataFrameUtils
+    >>> textPrompt = "<|start_header_id|>user<|end_header_id|>\n\n<sent>\\nSummary above sentence in one word: <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n \n"
+    >>> textDesc = "A cat sitting in a box."
+    >>> nullImageDF = spark.createDataFrame(spark.sparkContext.parallelize([EmbeddingsDataFrameUtils.emptyImageRow]), EmbeddingsDataFrameUtils.imageSchema)
+    >>> textDF = nullImageDF.withColumn("text", lit(textPrompt.replace("<sent>", textDesc)))
+    >>> e5vEmbeddings = E5VEmbeddings.pretrained() \
+    ...     .setInputCols(["image"]) \
+    ...     .setOutputCol("e5v")
+    >>> result = e5vEmbeddings.transform(textDF)
+    >>> result.select("e5v.embeddings").show(truncate = False)
+    """
+
+    name = "E5VEmbeddings"
+
+    inputAnnotatorTypes = [AnnotatorType.IMAGE]
+    outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.embeddings.E5VEmbeddings", java_model=None):
+        """Initializes the E5VEmbeddings annotator.
+
+        Parameters
+        ----------
+        classname : str, optional
+            The Java class name of the annotator, by default "com.johnsnowlabs.nlp.annotators.embeddings.E5VEmbeddings"
+        java_model : Optional[java.lang.Object], optional
+            A pre-initialized Java model, by default None
+        """
+        super(E5VEmbeddings, self).__init__(classname=classname, java_model=java_model)
+        self._setDefault()
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session, use_openvino=False):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+        use_openvino : bool, optional
+            Whether to use OpenVINO engine, by default False
+
+        Returns
+        -------
+        E5VEmbeddings
+            The restored model
+        """
+        from sparknlp.internal import _E5VEmbeddingsLoader
+        jModel = _E5VEmbeddingsLoader(folder, spark_session._jsparkSession, use_openvino)._java_obj
+        return E5VEmbeddings(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="e5v_int4", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "e5v_int4"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        E5VEmbeddings
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(E5VEmbeddings, name, lang, remote_loc) 

sparknlp/annotator/embeddings/snowflake_embeddings.py

@@ -47,21 +47,7 @@ class SnowFlakeEmbeddings(AnnotatorModel,
 	``DOCUMENT``            ``SENTENCE_EMBEDDINGS``
 	====================== ======================
 
-	Parameters
-	----------
-	batchSize
-		Size of every batch , by default 8
-	dimension
-		Number of embedding dimensions, by default 768
-	caseSensitive
-		Whether to ignore case in tokens for embeddings matching, by default False
-	maxSentenceLength
-		Max sentence length to process, by default 512
-	configProtoBytes
-		ConfigProto from tensorflow, serialized into byte array.
-
-	References
-	----------
+	**References**
 
 	`Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models <https://arxiv.org/abs/2405.05374>`__
 	`Snowflake Arctic-Embed Models <https://github.com/Snowflake-Labs/arctic-embed>`__
@@ -78,6 +64,20 @@ class SnowFlakeEmbeddings(AnnotatorModel,
      data curation is crucial to retrieval accuracy. A detailed technical report will be available
      shortly. *
 
+	Parameters
+	----------
+	batchSize
+		Size of every batch , by default 8
+	dimension
+		Number of embedding dimensions, by default 768
+	caseSensitive
+		Whether to ignore case in tokens for embeddings matching, by default False
+	maxSentenceLength
+		Max sentence length to process, by default 512
+	configProtoBytes
+		ConfigProto from tensorflow, serialized into byte array.
+
+
 	Examples
 	--------
 	>>> import sparknlp

sparknlp/annotator/openai/openai_completion.py

@@ -63,7 +63,6 @@ class OpenAICompletion(AnnotatorModel):
    >>> from sparknlp.annotator import *
    >>> from sparknlp.common import *
    >>> from pyspark.ml import Pipeline
-
    >>> documentAssembler = DocumentAssembler() \\
    ...     .setInputCol("text") \\
    ...     .setOutputCol("document")
@@ -83,9 +82,9 @@ class OpenAICompletion(AnnotatorModel):
    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
    |completion                                                                                                                                                                                                                                                                                        |
    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-   |[{document, 0, 258, \n\nI had the pleasure of dining at La Fiorita recently, and it was a truly delightful experience! The menu boasted a wonderful selection of classic Italian dishes, all exquisitely prepared and presented. The service staff was friendly and attentive and really, {}, []}]|
-   |[{document, 0, 227, \n\nI recently visited Barbecue Joe's for dinner and it was amazing! The menu had so many items to choose from including pulled pork, smoked turkey, brisket, pork ribs, and sandwiches. I opted for the pulled pork sandwich and let, {}, []}]                               |
-   |[{document, 0, 172, \n\n{ \n   "review": { \n      "overallRating": 4, \n      "reviewBody": "I enjoyed my meal at this restaurant. The food was flavourful, well-prepared and beautifully presented., {}, []}]                                                                                   |
+   |[{document, 0, 258, \\n\\nI had the pleasure of dining at La Fiorita recently, and it was a truly delightful experience! The menu boasted a wonderful selection of classic Italian dishes, all exquisitely prepared and presented. The service staff was friendly and attentive and really, {}, []}]|
+   |[{document, 0, 227, \\n\\nI recently visited Barbecue Joe's for dinner and it was amazing! The menu had so many items to choose from including pulled pork, smoked turkey, brisket, pork ribs, and sandwiches. I opted for the pulled pork sandwich and let, {}, []}]                               |
+   |[{document, 0, 172, \\n\\n{ \\n   "review": { \\n      "overallRating": 4, \\n      "reviewBody": "I enjoyed my meal at this restaurant. The food was flavourful, well-prepared and beautifully presented., {}, []}]                                                                                   |
    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
    """
 

sparknlp/annotator/seq2seq/m2m100_transformer.py

@@ -77,7 +77,7 @@ class M2M100Transformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
         Target Language (Default: `fr`)
 
     Languages Covered
-    -----
+    -----------------
     Afrikaans (af), Amharic (am), Arabic (ar), Asturian (ast), Azerbaijani (az), Bashkir (ba),
     Belarusian (be), Bulgarian (bg), Bengali (bn), Breton (br), Bosnian (bs), Catalan; Valencian
     (ca), Cebuano (ceb), Czech (cs), Welsh (cy), Danish (da), German (de), Greeek (el), English

sparknlp/annotator/seq2seq/mistral_transformer.py

@@ -91,8 +91,7 @@ class MistralTransformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
 
     References
     ----------
-    - `Mistral 7B
-      <https://mistral.ai/news/announcing-mistral_7b/>`__
+    - `Mistral 7B <https://mistral.ai/news/announcing-mistral_7b/>`__
     - https://github.com/mistralai/mistral-src
 
     **Paper Abstract:**
@@ -126,7 +125,7 @@ class MistralTransformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
     +----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
     |result                                                                                                                                                                                              |
     +----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |[Leonardo Da Vinci invented the microscope?\n Question: Leonardo Da Vinci invented the microscope?\n Answer: No, Leonardo Da Vinci did not invent the microscope. The first microscope was invented |
+    |[Leonardo Da Vinci invented the microscope?\\n Question: Leonardo Da Vinci invented the microscope?\\n Answer: No, Leonardo Da Vinci did not invent the microscope. The first microscope was invented |
     | in the late 16th century, long after Leonardo']                                                                                                                                                    |
     -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
     """

sparknlp/annotator/seq2seq/nllb_transformer.py

@@ -77,7 +77,7 @@ class NLLBTransformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
         Target Language (Default: `fr`)
 
     Languages Covered
-    -----
+    -----------------
     Acehnese (Arabic script) (ace_Arab), Acehnese (Latin script) (ace_Latn), Mesopotamian Arabic
     (acm_Arab), Ta’izzi-Adeni Arabic (acq_Arab), Tunisian Arabic (aeb_Arab), Afrikaans (afr_Latn),
     South Levantine Arabic (ajp_Arab), Akan (aka_Latn), Amharic (amh_Ethi), North Levantine Arabic

sparknlp/annotator/seq2seq/qwen_transformer.py

@@ -52,6 +52,32 @@ class QwenTransformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
     ``DOCUMENT``           ``DOCUMENT``
     ====================== ======================
 
+    **References**
+    
+    - `Qwen Technical Report
+      <https://arxiv.org/pdf/2309.16609.pdf>`__
+    - https://qwenlm.github.io/blog/qwen1.5/
+    - https://github.com/QwenLM/Qwen1.5
+
+    **Paper Abstract:**
+
+    *Large language models (LLMs) have revolutionized the field of artificial intelligence,
+    enabling natural language processing tasks that were previously thought to be exclusive to
+    humans. In this work, we introduce Qwen, the first installment of our large language model
+    series. Qwen is a comprehensive language model series that encompasses distinct models with
+    varying parameter counts. It includes Qwen, the base pretrained language models, and
+    Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models
+    consistently demonstrate superior performance across a multitude of downstream tasks, and the
+    chat models, particularly those trained using Reinforcement Learning from Human Feedback
+    (RLHF), are highly competitive. The chat models possess advanced tool-use and planning
+    capabilities for creating agent applications, showcasing impressive performance even when
+    compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we
+    have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as
+    mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These
+    models demonstrate significantly improved performance in comparison with open-source models,
+    and slightly fall behind the proprietary models.*
+
+
     Parameters
     ----------
     configProtoBytes
@@ -87,31 +113,6 @@ class QwenTransformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
     This is a very computationally expensive module especially on larger
     sequence. The use of an accelerator such as GPU is recommended.
 
-    References
-    ----------
-    - `Qwen Technical Report
-      <https://arxiv.org/pdf/2309.16609.pdf>`__
-    - https://qwenlm.github.io/blog/qwen1.5/
-    - https://github.com/QwenLM/Qwen1.5
-
-    **Paper Abstract:**
-
-    *Large language models (LLMs) have revolutionized the field of artificial intelligence,
-    enabling natural language processing tasks that were previously thought to be exclusive to
-    humans. In this work, we introduce Qwen, the first installment of our large language model
-    series. Qwen is a comprehensive language model series that encompasses distinct models with
-    varying parameter counts. It includes Qwen, the base pretrained language models, and
-    Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models
-    consistently demonstrate superior performance across a multitude of downstream tasks, and the
-    chat models, particularly those trained using Reinforcement Learning from Human Feedback
-    (RLHF), are highly competitive. The chat models possess advanced tool-use and planning
-    capabilities for creating agent applications, showcasing impressive performance even when
-    compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we
-    have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as
-    mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These
-    models demonstrate significantly improved performance in comparison with open-source models,
-    and slightly fall behind the proprietary models.*
-
     Examples
     --------
     >>> import sparknlp

sparknlp/annotator/spell_check/context_spell_checker.py

@@ -565,7 +565,7 @@ class ContextSpellCheckerModel(AnnotatorModel, HasEngine):
 
 
     References
-    -------------
+    ----------
     For an in-depth explanation of the module see the article `Applying Context
     Aware Spell Checking in Spark NLP
     <https://medium.com/spark-nlp/applying-context-aware-spell-checking-in-spark-nlp-3c29c46963bc>`__.

sparknlp/base/prompt_assembler.py

@@ -122,7 +122,7 @@ class PromptAssembler(AnnotatorTransformer):
     +----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
     |result                                                                                                                                                                                                                                                                                                                      |
     +----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |[<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nHello there, how can I help you?<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nI need help with organizing my room.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n]|
+    |[<|start_header_id|>system<|end_header_id|>\\n\\nYou are a helpful assistant.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\nHello there, how can I help you?<|eot_id|><|start_header_id|>user<|end_header_id|>\\n\\nI need help with organizing my room.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n]|
     +----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
     """
 

sparknlp/common/properties.py

@@ -38,7 +38,7 @@ class HasBatchedAnnotate:
         int
             Current batch size
         """
-        return self.getOrDefault("batchSize")
+        return self.getOrDefault(self.batchSize)
 
 
 class HasCaseSensitiveProperties:
@@ -245,7 +245,7 @@ class HasBatchedAnnotateImage:
         int
             Current batch size
         """
-        return self.getOrDefault("batchSize")
+        return self.getOrDefault(self.batchSize)
 
 
 class HasImageFeatureProperties:
@@ -402,7 +402,7 @@ class HasBatchedAnnotateAudio:
         int
             Current batch size
         """
-        return self.getOrDefault("batchSize")
+        return self.getOrDefault(self.batchSize)
 
 
 class HasAudioFeatureProperties:
@@ -1099,7 +1099,7 @@ class HasLlamaCppProperties:
         return self._set(flashAttention=flashAttention)
 
     def setInputPrefixBos(self, inputPrefixBos: bool):
-        """Whether to add prefix BOS to user inputs, preceding the `--in-prefix` bool"""
+        """Whether to add prefix BOS to user inputs, preceding the `--in-prefix` string"""
         return self._set(inputPrefixBos=inputPrefixBos)
 
     def setUseMmap(self, useMmap: bool):
@@ -1114,7 +1114,7 @@ class HasLlamaCppProperties:
         """Whether to disable KV offload"""
         return self._set(noKvOffload=noKvOffload)
 
-    def setSystemPrompt(self, systemPrompt: bool):
+    def setSystemPrompt(self, systemPrompt: str):
         """Set a system prompt to use"""
         return self._set(systemPrompt=systemPrompt)
 
@@ -1219,7 +1219,7 @@ class HasLlamaCppProperties:
         """Set the amount of tokens the samplers should return at least (0 = disabled)"""
         return self._set(minKeep=minKeep)
 
-    def setGrammar(self, grammar: bool):
+    def setGrammar(self, grammar: str):
         """Set BNF-like grammar to constrain generations"""
         return self._set(grammar=grammar)
 
@@ -1261,7 +1261,7 @@ class HasLlamaCppProperties:
         return self._call_java("setTokenBias", tokenBias)
 
     def setLoraAdapters(self, loraAdapters: Dict[str, float]):
-        """Set token id bias"""
+        """Set LoRA adapters with their scaling factors"""
         return self._call_java("setLoraAdapters", loraAdapters)
 
     def getMetadata(self):

sparknlp/internal/__init__.py

@@ -281,6 +281,16 @@ class _Gemma3ForMultiModalLoader(ExtendedJavaWrapper):
             use_openvino
         )
 
+class _InternVLForMultiModalLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_InternVLForMultiModalLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.InternVLForMultiModal.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )
+
+
 class _JanusForMultiModalLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark, use_openvino=False):
         super(_JanusForMultiModalLoader, self).__init__(
@@ -1146,3 +1156,20 @@ class _SmolVLMTransformerLoader(ExtendedJavaWrapper):
             jspark,
             use_openvino
         )
+
+class _Florence2TransformerLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_Florence2TransformerLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.Florence2Transformer.loadSavedModel",
+            path,
+            jspark,
+            use_openvino,
+        )
+class _E5VEmbeddingsLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_E5VEmbeddingsLoader, self).__init__(
+            "com.johnsnowlabs.nlp.embeddings.E5VEmbeddings.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )

sparknlp/partition/__init__.py

@@ -0,0 +1,16 @@
+#  Copyright 2017-2025 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.
+"""Module to read various types of documents into chunks"""
+from sparknlp.partition.partition import *
+from sparknlp.partition.partition_transformer import *