Packages

package nlp

Ordering
  1. Alphabetic
Visibility
  1. Public
  2. All

Type Members

  1. case class Annotation(annotatorType: String, begin: Int, end: Int, result: String, metadata: Map[String, String], embeddings: Array[Float] = Array.emptyFloatArray) extends IAnnotation with Product with Serializable

    represents annotator's output parts and their details

    represents annotator's output parts and their details

    annotatorType

    the type of annotation

    begin

    the index of the first character under this annotation

    end

    the index after the last character under this annotation

    metadata

    associated metadata for this annotation

  2. case class AnnotationAudio(annotatorType: String, result: Array[Float], metadata: Map[String, String]) extends IAnnotation with Product with Serializable

    Represents AudioAssembler's output parts and their details.

  3. case class AnnotationImage(annotatorType: String, origin: String, height: Int, width: Int, nChannels: Int, mode: Int, result: Array[Byte], metadata: Map[String, String], text: String = "") extends IAnnotation with Product with Serializable

    Represents ImageAssembler's output parts and their details

    Represents ImageAssembler's output parts and their details

    annotatorType

    Image annotator type

    origin

    The origin of the image

    height

    Height of the image in pixels

    width

    Width of the image in pixels

    nChannels

    Number of image channels

    mode

    OpenCV-compatible type

    result

    Result of the annotation

    metadata

    Metadata of the annotation

  4. abstract class AnnotatorApproach[M <: Model[M]] extends Estimator[M] with HasInputAnnotationCols with HasOutputAnnotationCol with HasOutputAnnotatorType with DefaultParamsWritable with CanBeLazy

    This class should grow once we start training on datasets and share params For now it stands as a dummy placeholder for future reference

  5. abstract class AnnotatorModel[M <: Model[M]] extends Model[M] with RawAnnotator[M] with CanBeLazy

    This trait implements logic that applies nlp using Spark ML Pipeline transformers Should strongly change once UsedDefinedTypes are allowed https://issues.apache.org/jira/browse/SPARK-7768

  6. class AudioAssembler extends Transformer with DefaultParamsWritable with HasOutputAnnotatorType with HasOutputAnnotationCol

    Prepares audio read by Spark into a format that is processable by Spark NLP.

    Prepares audio read by Spark into a format that is processable by Spark NLP. This component is needed to process audio.

    Input col is a single record that contains the raw content and metadata of the file.

    Example

    import com.johnsnowlabs.nlp.AudioAssembler
import org.apache.spark.ml.Pipeline

val audioAssembler = new AudioAssembler()
  .setInputCol("audio")
  .setOutputCol("audio_assembler")

val pipeline = new Pipeline().setStages(Array(audioAssembler))
val pipelineDF = pipeline.fit(imageDF).transform(wavDf)
pipelineDF.printSchema()
root
  7. trait CanBeLazy extends AnyRef
  8. class Doc2Chunk extends Model[Doc2Chunk] with RawAnnotator[Doc2Chunk]

    Converts DOCUMENT type annotations into CHUNK type with the contents of a chunkCol.

    Converts DOCUMENT type annotations into CHUNK type with the contents of a chunkCol. Chunk text must be contained within input DOCUMENT. May be either StringType or ArrayType[StringType] (using setIsArray). Useful for annotators that require a CHUNK type input.

    Example

    import spark.implicits._
import com.johnsnowlabs.nlp.{Doc2Chunk, DocumentAssembler}
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler().setInputCol("text").setOutputCol("document")
val chunkAssembler = new Doc2Chunk()
  .setInputCols("document")
  .setChunkCol("target")
  .setOutputCol("chunk")
  .setIsArray(true)

val data = Seq(
  ("Spark NLP is an open-source text processing library for advanced natural language processing.",
    Seq("Spark NLP", "text processing library", "natural language processing"))
).toDF("text", "target")

val pipeline = new Pipeline().setStages(Array(documentAssembler, chunkAssembler)).fit(data)
val result = pipeline.transform(data)

result.selectExpr("chunk.result", "chunk.annotatorType").show(false)
+-----------------------------------------------------------------+---------------------+
|result                                                           |annotatorType        |
+-----------------------------------------------------------------+---------------------+
|[Spark NLP, text processing library, natural language processing]|[chunk, chunk, chunk]|
+-----------------------------------------------------------------+---------------------+
    See also

    Chunk2Doc for converting CHUNK annotations to DOCUMENT

  9. class DocumentAssembler extends Transformer with DefaultParamsWritable with HasOutputAnnotatorType with HasOutputAnnotationCol

    Prepares data into a format that is processable by Spark NLP.

    Prepares data into a format that is processable by Spark NLP. This is the entry point for every Spark NLP pipeline. The DocumentAssembler reads String columns. Additionally, setCleanupMode can be used to pre-process the text (Default: disabled). For possible options please refer to the parameters section.

    For more extended examples on document pre-processing see the Examples.

    Example

    import spark.implicits._
import com.johnsnowlabs.nlp.DocumentAssembler

val data = Seq("Spark NLP is an open-source text processing library.").toDF("text")
val documentAssembler = new DocumentAssembler().setInputCol("text").setOutputCol("document")

val result = documentAssembler.transform(data)

result.select("document").show(false)
+----------------------------------------------------------------------------------------------+
|document                                                                                      |
+----------------------------------------------------------------------------------------------+
|[[document, 0, 51, Spark NLP is an open-source text processing library., [sentence -> 0], []]]|
+----------------------------------------------------------------------------------------------+

result.select("document").printSchema
root
 |-- document: array (nullable = true)
 |    |-- element: struct (containsNull = true)
 |    |    |-- annotatorType: string (nullable = true)
 |    |    |-- begin: integer (nullable = false)
 |    |    |-- end: integer (nullable = false)
 |    |    |-- result: string (nullable = true)
 |    |    |-- metadata: map (nullable = true)
 |    |    |    |-- key: string
 |    |    |    |-- value: string (valueContainsNull = true)
 |    |    |-- embeddings: array (nullable = true)
 |    |    |    |-- element: float (containsNull = false)
  10. class EmbeddingsFinisher extends Transformer with DefaultParamsWritable

    Extracts embeddings from Annotations into a more easily usable form.

    Extracts embeddings from Annotations into a more easily usable form.

    This is useful for example: WordEmbeddings, BertEmbeddings, SentenceEmbeddings and ChunkEmbeddings.

    By using EmbeddingsFinisher you can easily transform your embeddings into array of floats or vectors which are compatible with Spark ML functions such as LDA, K-mean, Random Forest classifier or any other functions that require featureCol.

    For more extended examples see the Examples.

    Example

    import spark.implicits._
import org.apache.spark.ml.Pipeline
import com.johnsnowlabs.nlp.{DocumentAssembler, EmbeddingsFinisher}
import com.johnsnowlabs.nlp.annotator.{Normalizer, StopWordsCleaner, Tokenizer, WordEmbeddingsModel}

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val tokenizer = new Tokenizer()
  .setInputCols("document")
  .setOutputCol("token")

val normalizer = new Normalizer()
  .setInputCols("token")
  .setOutputCol("normalized")

val stopwordsCleaner = new StopWordsCleaner()
  .setInputCols("normalized")
  .setOutputCol("cleanTokens")
  .setCaseSensitive(false)

val gloveEmbeddings = WordEmbeddingsModel.pretrained()
  .setInputCols("document", "cleanTokens")
  .setOutputCol("embeddings")
  .setCaseSensitive(false)

val embeddingsFinisher = new EmbeddingsFinisher()
  .setInputCols("embeddings")
  .setOutputCols("finished_sentence_embeddings")
  .setOutputAsVector(true)
  .setCleanAnnotations(false)

val data = Seq("Spark NLP is an open-source text processing library.")
  .toDF("text")
val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  tokenizer,
  normalizer,
  stopwordsCleaner,
  gloveEmbeddings,
  embeddingsFinisher
)).fit(data)

val result = pipeline.transform(data)
val resultWithSize = result.selectExpr("explode(finished_sentence_embeddings)")
  .map { row =>
    val vector = row.getAs[org.apache.spark.ml.linalg.DenseVector](0)
    (vector.size, vector)
  }.toDF("size", "vector")

resultWithSize.show(5, 80)
+----+--------------------------------------------------------------------------------+
|size|                                                                          vector|
+----+--------------------------------------------------------------------------------+
| 100|[0.1619900017976761,0.045552998781204224,-0.03229299932718277,-0.685609996318...|
| 100|[-0.42416998744010925,1.1378999948501587,-0.5717899799346924,-0.5078899860382...|
| 100|[0.08621499687433243,-0.15772999823093414,-0.06067200005054474,0.395359992980...|
| 100|[-0.4970499873161316,0.7164199948310852,0.40119001269340515,-0.05761000141501...|
| 100|[-0.08170200139284134,0.7159299850463867,-0.20677000284194946,0.0295659992843...|
+----+--------------------------------------------------------------------------------+
    See also

    Finisher for finishing Strings

  11. class FeaturesFallbackReader[T <: HasFeatures] extends MLReader[T]

    MLReader that loads a model with params and features, and has a fallback mechanism.

    MLReader that loads a model with params and features, and has a fallback mechanism.

    The fallback load will be called in case there is an exception during Spark loading (i.e. missing parameters or features).

    Usually, you might want to call loadSavedModel in the fallbackLoad method to load a model with default params.

    T

    The type of the model that extends HasFeatures

  12. class FeaturesReader[T <: HasFeatures] extends MLReader[T]
  13. class FeaturesWriter[T] extends MLWriter with HasFeatures
  14. class Finisher extends Transformer with DefaultParamsWritable

    Converts annotation results into a format that easier to use.

    Converts annotation results into a format that easier to use. It is useful to extract the results from Spark NLP Pipelines. The Finisher outputs annotation(s) values into String.

    For more extended examples on document pre-processing see the Examples.

    Example

    import spark.implicits._
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
import com.johnsnowlabs.nlp.Finisher

val data = Seq((1, "New York and New Jersey aren't that far apart actually.")).toDF("id", "text")

// Extracts Named Entities amongst other things
val pipeline = PretrainedPipeline("explain_document_dl")

val finisher = new Finisher().setInputCols("entities").setOutputCols("output")
val explainResult = pipeline.transform(data)

explainResult.selectExpr("explode(entities)").show(false)
+------------------------------------------------------------------------------------------------------------------------------------------------------+
|entities                                                                                                                                              |
+------------------------------------------------------------------------------------------------------------------------------------------------------+
|[[chunk, 0, 7, New York, [entity -> LOC, sentence -> 0, chunk -> 0], []], [chunk, 13, 22, New Jersey, [entity -> LOC, sentence -> 0, chunk -> 1], []]]|
+------------------------------------------------------------------------------------------------------------------------------------------------------+

val result = finisher.transform(explainResult)
result.select("output").show(false)
+----------------------+
|output                |
+----------------------+
|[New York, New Jersey]|
+----------------------+
    See also

    EmbeddingsFinisher for finishing embeddings

  15. class GraphFinisher extends Transformer

    Helper class to convert the knowledge graph from GraphExtraction into a generic format, such as RDF.

    Helper class to convert the knowledge graph from GraphExtraction into a generic format, such as RDF.

    Example

    This is a continuation of the example of GraphExtraction. To see how the graph is extracted, see the documentation of that class.

    import com.johnsnowlabs.nlp.GraphFinisher

val graphFinisher = new GraphFinisher()
  .setInputCol("graph")
  .setOutputCol("graph_finished")
  .setOutputAsArray(false)

val finishedResult = graphFinisher.transform(result)
finishedResult.select("text", "graph_finished").show(false)
+-----------------------------------------------------+-----------------------------------------------------------------------+
|text                                                 |graph_finished                                                         |
+-----------------------------------------------------+-----------------------------------------------------------------------+
|You and John prefer the morning flight through Denver|[[(prefer,nsubj,morning), (morning,flat,flight), (flight,flat,Denver)]]|
+-----------------------------------------------------+-----------------------------------------------------------------------+
    See also

    GraphExtraction to extract the graph.

  16. trait HasAudioFeatureProperties extends ParamsAndFeaturesWritable

    example of required parameters

    example of required parameters

    {
"do_normalize": true,
"feature_size": 1,
"padding_side": "right",
"padding_value": 0.0,
"return_attention_mask": false,
"sampling_rate": 16000
}
  17. trait HasBatchedAnnotate[M <: Model[M]] extends AnyRef
  18. trait HasBatchedAnnotateAudio[M <: Model[M]] extends AnyRef
  19. trait HasBatchedAnnotateImage[M <: Model[M]] extends AnyRef
  20. trait HasBatchedAnnotateTextImage[M <: Model[M]] extends AnyRef
  21. trait HasCandidateLabelsProperties extends ParamsAndFeaturesWritable
  22. trait HasCaseSensitiveProperties extends ParamsAndFeaturesWritable
  23. trait HasClassifierActivationProperties extends ParamsAndFeaturesWritable
  24. trait HasClsTokenProperties extends ParamsAndFeaturesWritable
  25. trait HasEnableCachingProperties extends ParamsAndFeaturesWritable
  26. trait HasEngine extends ParamsAndFeaturesWritable
  27. trait HasFeatures extends AnyRef
  28. trait HasGeneratorProperties extends AnyRef

    Parameters to configure beam search text generation.

  29. trait HasImageFeatureProperties extends ParamsAndFeaturesWritable

    example of required parameters

    example of required parameters

    {
"do_normalize": true,
"do_resize": true,
"feature_extractor_type": "ViTFeatureExtractor",
"image_mean": [
0.5,
0.5,
0.5
],
"image_std": [
0.5,
0.5,
0.5
],
"resample": 2,
"size": 224
}
  30. trait HasInputAnnotationCols extends Params
  31. trait HasLlamaCppInferenceProperties extends AnyRef

    Contains settable inference parameters for the AutoGGUFModel.

  32. trait HasLlamaCppModelProperties extends AnyRef

    Contains settable model parameters for the AutoGGUFModel.

  33. trait HasMultipleInputAnnotationCols extends HasInputAnnotationCols

    Trait used to create annotators with input columns of variable length.

  34. trait HasOutputAnnotationCol extends Params
  35. trait HasOutputAnnotatorType extends AnyRef
  36. trait HasPretrained[M <: PipelineStage] extends AnyRef
  37. trait HasProtectedParams extends AnyRef

    Enables a class to protect a parameter, which means that it can only be set once.

    Enables a class to protect a parameter, which means that it can only be set once.

    This trait will enable a implicit conversion from Param to ProtectedParam. In addition, the new set for ProtectedParam will then check, whether or not the value was already set. If so, then a warning will be output and the value will not be set again.

  38. trait HasRecursiveFit[M <: Model[M]] extends AnyRef

    AnnotatorApproach'es may extend this trait in order to allow RecursivePipelines to include intermediate steps trained PipelineModel's

  39. trait HasRecursiveTransform[M <: Model[M]] extends AnyRef
  40. trait HasSimpleAnnotate[M <: Model[M]] extends AnyRef
  41. trait IAnnotation extends AnyRef

    IAnnotation trait is used to abstract the annotator's output for each NLP tasks available in Spark NLP.

    IAnnotation trait is used to abstract the annotator's output for each NLP tasks available in Spark NLP.

    Currently Spark NLP supports three types of outputs:

    LightPipeline models in Java/Scala returns an IAnnotation collection. All of these outputs are structs with the required data types to represent Text, Image and Audio.

    If one wants to access the data as Annotation, AnnotationImage or AnnotationAudio, one just needs casting to the desired output.

    Example

    import com.johnsnowlabs.nlp.annotators.cv.ViTForImageClassification
import org.apache.spark.ml.Pipeline
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.sbd.pragmatic.SentenceDetector
import com.johnsnowlabs.nlp.ImageAssembler
import com.johnsnowlabs.nlp.LightPipeline
import com.johnsnowlabs.util.PipelineModels

val imageDf = spark.read
 .format("image")
 .option("dropInvalid", value = true)
 .load("./images")

val imageAssembler = new ImageAssembler()
  .setInputCol("image")
  .setOutputCol("image_assembler")

val imageClassifier = ViTForImageClassification
.pretrained()
.setInputCols("image_assembler")
.setOutputCol("class")

val pipeline: Pipeline = new Pipeline().setStages(Array(imageAssembler, imageClassifier))

val vitModel = pipeline.fit(imageDf)
val lightPipeline = new LightPipeline(vitModel)
val predictions = lightPipeline.fullAnnotate("./images/hen.JPEG")

val result = predictions.flatMap(prediction => prediction._2.map {
    case annotationText: Annotation =>
      annotationText
    case annotationImage: AnnotationImage =>
      annotationImage
})
  42. class ImageAssembler extends Transformer with DefaultParamsWritable with HasOutputAnnotatorType with HasOutputAnnotationCol

    Prepares images read by Spark into a format that is processable by Spark NLP.

    Prepares images read by Spark into a format that is processable by Spark NLP. This component is needed to process images.

    Example

    import com.johnsnowlabs.nlp.ImageAssembler
import org.apache.spark.ml.Pipeline

val imageDF: DataFrame = spark.read
  .format("image")
  .option("dropInvalid", value = true)
  .load("src/test/resources/image/")

val imageAssembler = new ImageAssembler()
  .setInputCol("image")
  .setOutputCol("image_assembler")

val pipeline = new Pipeline().setStages(Array(imageAssembler))
val pipelineDF = pipeline.fit(imageDF).transform(imageDF)
pipelineDF.printSchema()
root
 |-- image_assembler: array (nullable = true)
 |    |-- element: struct (containsNull = true)
 |    |    |-- annotatorType: string (nullable = true)
 |    |    |-- origin: string (nullable = true)
 |    |    |-- height: integer (nullable = false)
 |    |    |-- width: integer (nullable = false)
 |    |    |-- nChannels: integer (nullable = false)
 |    |    |-- mode: integer (nullable = false)
 |    |    |-- result: binary (nullable = true)
 |    |    |-- metadata: map (nullable = true)
 |    |    |    |-- key: string
 |    |    |    |-- value: string (valueContainsNull = true)
  43. case class JavaAnnotation(annotatorType: String, begin: Int, end: Int, result: String, metadata: Map[String, String], embeddings: Array[Float] = Array.emptyFloatArray) extends IAnnotation with Product with Serializable
  44. class LightPipeline extends AnyRef
  45. class MultiDocumentAssembler extends Transformer with DefaultParamsWritable with HasOutputAnnotatorType

    Prepares data into a format that is processable by Spark NLP.

    Prepares data into a format that is processable by Spark NLP. This is the entry point for every Spark NLP pipeline. The MultiDocumentAssembler can read either a String column or an Array[String]. Additionally, setCleanupMode can be used to pre-process the text (Default: disabled). For possible options please refer the parameters section.

    For more extended examples on document pre-processing see the Examples.

    Example

    import spark.implicits._
import com.johnsnowlabs.nlp.MultiDocumentAssembler

val data = Seq("Spark NLP is an open-source text processing library.").toDF("text")
val multiDocumentAssembler = new MultiDocumentAssembler().setInputCols("text").setOutputCols("document")

val result = multiDocumentAssembler.transform(data)

result.select("document").show(false)
+----------------------------------------------------------------------------------------------+
|document                                                                                      |
+----------------------------------------------------------------------------------------------+
|[[document, 0, 51, Spark NLP is an open-source text processing library., [sentence -> 0], []]]|
+----------------------------------------------------------------------------------------------+

result.select("document").printSchema
root
 |-- document: array (nullable = true)
 |    |-- element: struct (containsNull = true)
 |    |    |-- annotatorType: string (nullable = true)
 |    |    |-- begin: integer (nullable = false)
 |    |    |-- end: integer (nullable = false)
 |    |    |-- result: string (nullable = true)
 |    |    |-- metadata: map (nullable = true)
 |    |    |    |-- key: string
 |    |    |    |-- value: string (valueContainsNull = true)
 |    |    |-- embeddings: array (nullable = true)
 |    |    |    |-- element: float (containsNull = false)
  46. trait ParamsAndFeaturesFallbackReadable[T <: HasFeatures] extends ParamsAndFeaturesReadable[T]

    Enables loading models with params and features with a fallback mechanism.

    Enables loading models with params and features with a fallback mechanism. The fallbackLoad function will be called in case there is an exception during Spark loading (i.e. missing parameters or features).

    Usually, you might want to call loadSavedModel in the fallbackLoad method to load a model with default params.

    T

    The type of the model that extends HasFeatures

  47. trait ParamsAndFeaturesReadable[T <: HasFeatures] extends DefaultParamsReadable[T]
  48. trait ParamsAndFeaturesWritable extends DefaultParamsWritable with Params with HasFeatures
  49. class PromptAssembler extends Transformer with DefaultParamsWritable with HasOutputAnnotatorType with HasOutputAnnotationCol

    Assembles a sequence of messages into a single string using a template.

    Assembles a sequence of messages into a single string using a template. These strings can then be used as prompts for large language models.

    This annotator expects an array of two-tuples as the type of the input column (one array of tuples per row). The first element of the tuples should be the role and the second element is the text of the message. Possible roles are "system", "user" and "assistant".

    An assistant header can be added to the end of the generated string by using setAddAssistant(true).

    At the moment, this annotator uses llama.cpp as a backend to parse and apply the templates. llama.cpp uses basic pattern matching to determine the type of the template, then applies a basic version of the template to the messages. This means that more advanced templates are not supported.

    For an extended example see the example notebook.

    Example

    // Batches (whole conversations) of arrays of messages
val data: Seq[Seq[(String, String)]] = Seq(
  Seq(
    ("system", "You are a helpful assistant."),
    ("assistant", "Hello there, how can I help you?"),
    ("user", "I need help with organizing my room.")))

val dataDF = data.toDF("messages")

// llama3.1
val template =
  "{{- bos_token }} {%- if custom_tools is defined %} {%- set tools = custom_tools %} {%- " +
    "endif %} {%- if not tools_in_user_message is defined %} {%- set tools_in_user_message = true %} {%- " +
    "endif %} {%- if not date_string is defined %} {%- set date_string = \"26 Jul 2024\" %} {%- endif %} " +
    "{%- if not tools is defined %} {%- set tools = none %} {%- endif %} {#- This block extracts the " +
    "system message, so we can slot it into the right place. #} {%- if messages[0]['role'] == 'system' %}" +
    " {%- set system_message = messages[0]['content']|trim %} {%- set messages = messages[1:] %} {%- else" +
    " %} {%- set system_message = \"\" %} {%- endif %} {#- System message + builtin tools #} {{- " +
    "\"<|start_header_id|>system<|end_header_id|>\\n\\n\" }} {%- if builtin_tools is defined or tools is " +
    "not none %} {{- \"Environment: ipython\\n\" }} {%- endif %} {%- if builtin_tools is defined %} {{- " +
    "\"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}} " +
    "{%- endif %} {{- \"Cutting Knowledge Date: December 2023\\n\" }} {{- \"Today Date: \" + date_string " +
    "+ \"\\n\\n\" }} {%- if tools is not none and not tools_in_user_message %} {{- \"You have access to " +
    "the following functions. To call a function, please respond with JSON for a function call.\" }} {{- " +
    "'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its" +
    " value}.' }} {{- \"Do not use variables.\\n\\n\" }} {%- for t in tools %} {{- t | tojson(indent=4) " +
    "}} {{- \"\\n\\n\" }} {%- endfor %} {%- endif %} {{- system_message }} {{- \"<|eot_id|>\" }} {#- " +
    "Custom tools are passed in a user message with some extra guidance #} {%- if tools_in_user_message " +
    "and not tools is none %} {#- Extract the first user message so we can plug it in here #} {%- if " +
    "messages | length != 0 %} {%- set first_user_message = messages[0]['content']|trim %} {%- set " +
    "messages = messages[1:] %} {%- else %} {{- raise_exception(\"Cannot put tools in the first user " +
    "message when there's no first user message!\") }} {%- endif %} {{- " +
    "'<|start_header_id|>user<|end_header_id|>\\n\\n' -}} {{- \"Given the following functions, please " +
    "respond with a JSON for a function call \" }} {{- \"with its proper arguments that best answers the " +
    "given prompt.\\n\\n\" }} {{- 'Respond in the format {\"name\": function name, \"parameters\": " +
    "dictionary of argument name and its value}.' }} {{- \"Do not use variables.\\n\\n\" }} {%- for t in " +
    "tools %} {{- t | tojson(indent=4) }} {{- \"\\n\\n\" }} {%- endfor %} {{- first_user_message + " +
    "\"<|eot_id|>\"}} {%- endif %} {%- for message in messages %} {%- if not (message.role == 'ipython' " +
    "or message.role == 'tool' or 'tool_calls' in message) %} {{- '<|start_header_id|>' + message['role']" +
    " + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }} {%- elif 'tool_calls' in " +
    "message %} {%- if not message.tool_calls|length == 1 %} {{- raise_exception(\"This model only " +
    "supports single tool-calls at once!\") }} {%- endif %} {%- set tool_call = message.tool_calls[0]" +
    ".function %} {%- if builtin_tools is defined and tool_call.name in builtin_tools %} {{- " +
    "'<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}} {{- \"<|python_tag|>\" + tool_call.name + " +
    "\".call(\" }} {%- for arg_name, arg_val in tool_call.arguments | items %} {{- arg_name + '=\"' + " +
    "arg_val + '\"' }} {%- if not loop.last %} {{- \", \" }} {%- endif %} {%- endfor %} {{- \")\" }} {%- " +
    "else %} {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}} {{- '{\"name\": \"' + " +
    "tool_call.name + '\", ' }} {{- '\"parameters\": ' }} {{- tool_call.arguments | tojson }} {{- \"}\" " +
    "}} {%- endif %} {%- if builtin_tools is defined %} {#- This means we're in ipython mode #} {{- " +
    "\"<|eom_id|>\" }} {%- else %} {{- \"<|eot_id|>\" }} {%- endif %} {%- elif message.role == \"tool\" " +
    "or message.role == \"ipython\" %} {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }} {%- " +
    "if message.content is mapping or message.content is iterable %} {{- message.content | tojson }} {%- " +
    "else %} {{- message.content }} {%- endif %} {{- \"<|eot_id|>\" }} {%- endif %} {%- endfor %} {%- if " +
    "add_generation_prompt %} {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }} {%- endif %} "

val promptAssembler = new PromptAssembler()
  .setInputCol("messages")
  .setOutputCol("prompt")
  .setChatTemplate(template)

promptAssembler.transform(dataDF).select("prompt.result").show(truncate = false)
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|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]|
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
  50. trait RawAnnotator[M <: Model[M]] extends Model[M] with ParamsAndFeaturesWritable with HasOutputAnnotatorType with HasInputAnnotationCols with HasOutputAnnotationCol
  51. class RecursivePipeline extends Pipeline
  52. class RecursivePipelineModel extends Model[RecursivePipelineModel] with MLWritable with Logging
  53. class TableAssembler extends AnnotatorModel[TokenAssembler] with HasSimpleAnnotate[TokenAssembler]

    This transformer parses text into tabular representation.

    This transformer parses text into tabular representation. The input consists of DOCUMENT annotations and the output are TABLE annotations. The source format can be either JSON or CSV. The format of the JSON files should be:

    {
  "header": [col1, col2, ..., colN],
  "rows": [
    [val11, val12, ..., val1N],
    [val22, va22, ..., val2N],
    ...
   ]
}

    The CSV format support alternative delimiters (e.g. tab), as well as escaping delimiters by surrounding cell values with double quotes. For example:

    column1, column2, "column with, comma"
value1, value2, value3
"escaped value", "value with, comma", "value with double ("") quote"

    The transformer stores tabular data internally as JSON. The default input format is also JSON.

    Example

    import spark.implicits._
import com.johnsnowlabs.nlp.DocumentAssembler
import org.apache.spark.ml.Pipeline

val csvData =
  """
    |"name", "money", "age"
    |"Donald Trump", "$100,000,000", "75"
    |"Elon Musk", "$20,000,000,000,000", "55"
    |""".stripMargin.trim

val data =Seq(csvData).toDF("csv")

val documentAssembler = new DocumentAssembler()
  .setInputCol("csv")
  .setOutputCol("document")

val tableAssembler = new TableAssembler()
  .setInputCols(Array("document"))
  .setOutputCol("table")
  .setInputFormat("csv")

val pipeline = new Pipeline()
  .setStages(
    Array(documentAssembler, tableAssembler)
    ).fit(data)

val result = pipeline.transform(data)
result
  .selectExpr("explode(table) AS table")
  .select("table.result", "table.metadata.input_format")
  .show(false)

+--------------------------------------------+-------------+
|result                                      |input_format |
+--------------------------------------------+-------------+
|{                                           |csv          |
| "header": ["name","money","age"],          |             |
|  "rows":[                                  |             |
|   ["Donald Trump","$100,000,000","75"],    |             |
|   ["Elon Musk","$20,000,000,000,000","55"] |             |
|  ]                                         |             |
|}                                           |             |
+--------------------------------------------+-------------+
  54. class TokenAssembler extends AnnotatorModel[TokenAssembler] with HasSimpleAnnotate[TokenAssembler]

    This transformer reconstructs a DOCUMENT type annotation from tokens, usually after these have been normalized, lemmatized, normalized, spell checked, etc, in order to use this document annotation in further annotators.

    This transformer reconstructs a DOCUMENT type annotation from tokens, usually after these have been normalized, lemmatized, normalized, spell checked, etc, in order to use this document annotation in further annotators. Requires DOCUMENT and TOKEN type annotations as input.

    For more extended examples on document pre-processing see the Examples.

    Example

    import spark.implicits._
import com.johnsnowlabs.nlp.DocumentAssembler
import com.johnsnowlabs.nlp.annotator.SentenceDetector
import com.johnsnowlabs.nlp.annotator.Tokenizer
import com.johnsnowlabs.nlp.annotator.{Normalizer, StopWordsCleaner}
import com.johnsnowlabs.nlp.TokenAssembler
import org.apache.spark.ml.Pipeline

// First, the text is tokenized and cleaned
val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentenceDetector = new SentenceDetector()
  .setInputCols("document")
  .setOutputCol("sentences")

val tokenizer = new Tokenizer()
  .setInputCols("sentences")
  .setOutputCol("token")

val normalizer = new Normalizer()
  .setInputCols("token")
  .setOutputCol("normalized")
  .setLowercase(false)

val stopwordsCleaner = new StopWordsCleaner()
  .setInputCols("normalized")
  .setOutputCol("cleanTokens")
  .setCaseSensitive(false)

// Then the TokenAssembler turns the cleaned tokens into a `DOCUMENT` type structure.
val tokenAssembler = new TokenAssembler()
  .setInputCols("sentences", "cleanTokens")
  .setOutputCol("cleanText")

val data = Seq("Spark NLP is an open-source text processing library for advanced natural language processing.")
  .toDF("text")

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  sentenceDetector,
  tokenizer,
  normalizer,
  stopwordsCleaner,
  tokenAssembler
)).fit(data)

val result = pipeline.transform(data)
result.select("cleanText").show(false)
+---------------------------------------------------------------------------------------------------------------------------+
|cleanText                                                                                                                  |
+---------------------------------------------------------------------------------------------------------------------------+
|[[document, 0, 80, Spark NLP opensource text processing library advanced natural language processing, [sentence -> 0], []]]|
+---------------------------------------------------------------------------------------------------------------------------+
    See also

    DocumentAssembler on the data structure

Value Members

  1. object ActivationFunction
  2. object Annotation extends Serializable
  3. object AnnotationAudio extends Serializable
  4. object AnnotationImage extends Serializable
  5. object AnnotatorType
  6. object AudioAssembler extends DefaultParamsReadable[AudioAssembler] with Serializable

    This is the companion object of AudioAssembler.

    This is the companion object of AudioAssembler. Please refer to that class for the documentation.

  7. object Doc2Chunk extends DefaultParamsReadable[Doc2Chunk] with Serializable

    This is the companion object of Doc2Chunk.

    This is the companion object of Doc2Chunk. Please refer to that class for the documentation.

  8. object DocumentAssembler extends DefaultParamsReadable[DocumentAssembler] with Serializable

    This is the companion object of DocumentAssembler.

    This is the companion object of DocumentAssembler. Please refer to that class for the documentation.

  9. object EmbeddingsFinisher extends DefaultParamsReadable[EmbeddingsFinisher] with Serializable

    This is the companion object of EmbeddingsFinisher.

    This is the companion object of EmbeddingsFinisher. Please refer to that class for the documentation.

  10. object Finisher extends DefaultParamsReadable[Finisher] with Serializable

    This is the companion object of Finisher.

    This is the companion object of Finisher. Please refer to that class for the documentation.

  11. object ImageAssembler extends DefaultParamsReadable[ImageAssembler] with Serializable

    This is the companion object of ImageAssembler.

    This is the companion object of ImageAssembler. Please refer to that class for the documentation.

  12. object MultiDocumentAssembler extends DefaultParamsReadable[MultiDocumentAssembler] with Serializable

    This is the companion object of MultiDocumentAssembler.

    This is the companion object of MultiDocumentAssembler. Please refer to that class for the documentation.

  13. object PromptAssembler extends DefaultParamsReadable[PromptAssembler] with Serializable

    This is the companion object of PromptAssembler.

    This is the companion object of PromptAssembler. Please refer to that class for the documentation.

  14. object SparkNLP
  15. object TableAssembler extends DefaultParamsReadable[DocumentAssembler] with Serializable

    This is the companion object of TableAssembler.

    This is the companion object of TableAssembler. Please refer to that class for the documentation.

  16. object TokenAssembler extends DefaultParamsReadable[TokenAssembler] with Serializable

    This is the companion object of TokenAssembler.

    This is the companion object of TokenAssembler. Please refer to that class for the documentation.

  17. object functions

Ungrouped