Packages

class VectorDBConnector extends AnnotatorModel[VectorDBConnector] with HasBatchedAnnotate[VectorDBConnector]

Connector for storing and retrieving embeddings from vector databases.

This annotator takes embeddings from previous annotators (like BertEmbeddings, SentenceEmbeddings, E5VEmbeddings, etc.) and stores them in a vector database for similarity search and retrieval. Currently supports Pinecone with more providers planned.

Supports two modality modes:

  • 'text' (default): expects DOCUMENT + SENTENCE_EMBEDDINGS input columns. Metadata is augmented with modality=text.
  • 'image': expects IMAGE + SENTENCE_EMBEDDINGS input columns (e.g. from ImageAssembler + E5VEmbeddings). Metadata is augmented with modality=image, image_origin, image_width, image_height, and image_nChannels. Vector IDs are generated as deterministic UUID-v3 values derived from the image file path (origin), ensuring stable re-indexing.

Supported Providers

  • pinecone: Pinecone vector database (default)

Text Example

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.embeddings.BertSentenceEmbeddings
import com.johnsnowlabs.ml.ai.VectorDBConnector
import org.apache.spark.ml.Pipeline

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

val embeddings = BertSentenceEmbeddings.pretrained()
  .setInputCols("document")
  .setOutputCol("sentence_embeddings")

val vectorDB = new VectorDBConnector()
  .setInputCols("document", "sentence_embeddings")
  .setOutputCol("vectordb_result")
  .setProvider("pinecone")
  .setIndexName("my-index")
  .setNamespace("production")
  .setIdColumn("id")
  .setMetadataColumns(Array("text", "category"))
  .setBatchSize(100)

val pipeline = new Pipeline().setStages(Array(
  documentAssembler,
  embeddings,
  vectorDB
))

val data = Seq(
  ("1", "Spark NLP is great", "tech"),
  ("2", "Vector databases enable semantic search", "tech")
).toDF("id", "text", "category")

val result = pipeline.fit(data).transform(data)

Image Example

import com.johnsnowlabs.nlp.base.ImageAssembler
import com.johnsnowlabs.nlp.embeddings.E5VEmbeddings
import com.johnsnowlabs.ml.ai.VectorDBConnector
import org.apache.spark.ml.Pipeline

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

val e5vEmbeddings = E5VEmbeddings.pretrained()
  .setInputCols("image_assembler")
  .setOutputCol("image_embeddings")

val vectorDB = new VectorDBConnector()
  .setInputCols("image_assembler", "image_embeddings")
  .setOutputCol("vectordb_result")
  .setProvider("pinecone")
  .setIndexName("my-multimodal-index")
  .setModalityMode("image")
  .setBatchSize(50)

val pipeline = new Pipeline().setStages(Array(
  imageAssembler,
  e5vEmbeddings,
  vectorDB
))
Linear Supertypes
HasBatchedAnnotate[VectorDBConnector], AnnotatorModel[VectorDBConnector], CanBeLazy, RawAnnotator[VectorDBConnector], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[VectorDBConnector], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. VectorDBConnector
  2. HasBatchedAnnotate
  3. AnnotatorModel
  4. CanBeLazy
  5. RawAnnotator
  6. HasOutputAnnotationCol
  7. HasInputAnnotationCols
  8. HasOutputAnnotatorType
  9. ParamsAndFeaturesWritable
  10. HasFeatures
  11. DefaultParamsWritable
  12. MLWritable
  13. Model
  14. Transformer
  15. PipelineStage
  16. Logging
  17. Params
  18. Serializable
  19. Serializable
  20. Identifiable
  21. AnyRef
  22. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new VectorDBConnector()
  2. new VectorDBConnector(uid: String)

    uid

    required uid for storing annotator to disk

Type Members

  1. type AnnotationContent = Seq[Row]

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  12. def batchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[Seq[Annotation]]

    Required by HasBatchedAnnotate trait - but we override batchProcess instead since we need Row-level access for idColumn and metadataColumns.

    Required by HasBatchedAnnotate trait - but we override batchProcess instead since we need Row-level access for idColumn and metadataColumns.

    batchedAnnotations

    Annotations in batches that correspond to inputAnnotationCols generated by previous annotators if any

    returns

    any number of annotations processed for every batch of input annotations. Not necessary one to one relationship IMPORTANT: !MUST! return sequences of equal lengths !! IMPORTANT: !MUST! return sentences that belong to the same original row !! (challenging)

    Definition Classes
    VectorDBConnector → HasBatchedAnnotate
  13. def batchProcess(rows: Iterator[_]): Iterator[Row]

    Override batchProcess to get direct access to Row data.

    Override batchProcess to get direct access to Row data.

    This is necessary because we need access to additional columns (idColumn, metadataColumns) beyond just the annotations. The standard batchAnnotate only receives annotations.

    Branches on modalityMode: in "text" mode the first input column is expected to carry DOCUMENT annotations; in "image" mode it carries IMAGE annotations (AnnotationImage).

    rows

    Iterator of rows to process

    returns

    Iterator of processed rows with output annotation

    Definition Classes
    VectorDBConnector → HasBatchedAnnotate
  14. val batchSize: IntParam

    Batch size for upsert operations

    Batch size for upsert operations

    Definition Classes
    VectorDBConnector → HasBatchedAnnotate
  15. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]

    Initialize configuration before annotation

    Initialize configuration before annotation

    Loads provider-specific configuration and initializes connection

    dataset

    Input dataset

    returns

    Dataset unchanged

    Definition Classes
    VectorDBConnector → AnnotatorModel
  16. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  17. final def clear(param: Param[_]): VectorDBConnector.this.type
    Definition Classes
    Params
  18. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  19. def copy(extra: ParamMap): VectorDBConnector

    requirement for annotators copies

    requirement for annotators copies

    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  20. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  21. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  22. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  23. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  24. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  25. def explainParams(): String
    Definition Classes
    Params
  26. final val extraInputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  27. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  28. def extraValidateMsg: String

    Override for additional custom schema checks

    Override for additional custom schema checks

    Attributes
    protected
    Definition Classes
    RawAnnotator
  29. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  30. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  31. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  32. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  33. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  34. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  38. def getApiKey: String

    Get the broadcasted API key

    Get the broadcasted API key

    returns

    API key string

  39. def getBatchSize: Int

    Definition Classes
    VectorDBConnector → HasBatchedAnnotate
  40. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  41. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  42. def getIdColumn: String

  43. def getIndexName: String

  44. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  45. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  46. def getMetadataColumns: Array[String]

  47. def getModalityMode: String

  48. def getNamespace: String

  49. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  50. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  51. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  52. def getProvider: String

  53. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  54. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  55. def hasParent: Boolean
    Definition Classes
    Model
  56. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  57. val idColumn: Param[String]

    Column name to use as vector ID

  58. val indexName: Param[String]

    Index/collection name in the vector database

  59. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  60. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  61. val inputAnnotatorTypes: Array[String]

    Input annotator types.

    Input annotator types.

    In 'text' mode (default): DOCUMENT, SENTENCE_EMBEDDINGS

    In 'image' mode: IMAGE, SENTENCE_EMBEDDINGS

    Definition Classes
    VectorDBConnector → HasInputAnnotationCols
  62. final val inputCols: StringArrayParam

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  63. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  64. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  65. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  66. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  67. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  68. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  69. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  76. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. val metadataColumns: StringArrayParam

    Metadata columns to include with vectors

  81. val modalityMode: Param[String]

    Modality mode for indexing: "text" (default) or "image".

    Modality mode for indexing: "text" (default) or "image".

    Set to "image" when the first input column contains IMAGE annotations (e.g. from ImageAssembler + E5VEmbeddings). In image mode vector IDs are stable UUID-v3 values derived from the image origin path and upserted records carry image-specific metadata fields.

  82. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  83. val namespace: Param[String]

    Namespace/partition within the index (optional, provider-specific)

  84. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  85. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  86. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  87. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  88. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  89. val outputAnnotatorType: String
    Definition Classes
    VectorDBConnector → HasOutputAnnotatorType
  90. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  91. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  92. var parent: Estimator[VectorDBConnector]
    Definition Classes
    Model
  93. val provider: Param[String]

    Vector database provider (e.g., 'pinecone')

  94. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  95. def set[T](feature: StructFeature[T], value: T): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  96. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  97. def set[T](feature: SetFeature[T], value: Set[T]): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  98. def set[T](feature: ArrayFeature[T], value: Array[T]): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  99. final def set(paramPair: ParamPair[_]): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    Params
  100. final def set(param: String, value: Any): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    Params
  101. final def set[T](param: Param[T], value: T): VectorDBConnector.this.type
    Definition Classes
    Params
  102. def setApiKeyIfNotSet(spark: SparkSession, key: Option[String]): VectorDBConnector.this.type

    Set API key if not already set

    Set API key if not already set

    spark

    SparkSession

    key

    API key for the vector database provider

    returns

    this

  103. def setBatchSize(value: Int): VectorDBConnector.this.type

    Definition Classes
    VectorDBConnector → HasBatchedAnnotate
  104. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  105. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  106. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  107. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  108. final def setDefault(paramPairs: ParamPair[_]*): VectorDBConnector.this.type
    Attributes
    protected
    Definition Classes
    Params
  109. final def setDefault[T](param: Param[T], value: T): VectorDBConnector.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  110. def setExtraInputCols(value: Array[String]): VectorDBConnector.this.type
    Definition Classes
    HasInputAnnotationCols
  111. def setIdColumn(value: String): VectorDBConnector.this.type

  112. def setIndexName(value: String): VectorDBConnector.this.type

  113. final def setInputCols(value: String*): VectorDBConnector.this.type
    Definition Classes
    HasInputAnnotationCols
  114. def setInputCols(value: Array[String]): VectorDBConnector.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  115. def setLazyAnnotator(value: Boolean): VectorDBConnector.this.type
    Definition Classes
    CanBeLazy
  116. def setMetadataColumns(value: Array[String]): VectorDBConnector.this.type

  117. def setModalityMode(value: String): VectorDBConnector.this.type

  118. def setNamespace(value: String): VectorDBConnector.this.type

  119. final def setOutputCol(value: String): VectorDBConnector.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  120. def setParent(parent: Estimator[VectorDBConnector]): VectorDBConnector
    Definition Classes
    Model
  121. def setProvider(value: String): VectorDBConnector.this.type

  122. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  123. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  124. final def transform(dataset: Dataset[_]): DataFrame

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    dataset

    Dataset[Row]

    Definition Classes
    AnnotatorModel → Transformer
  125. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  126. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  127. final def transformSchema(schema: StructType): StructType

    requirement for pipeline transformation validation.

    requirement for pipeline transformation validation. It is called on fit()

    Definition Classes
    RawAnnotator → PipelineStage
  128. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  129. val uid: String
    Definition Classes
    VectorDBConnector → Identifiable
  130. def validate(schema: StructType): Boolean

    Override schema validation to accept IMAGE in the first input column when modalityMode is set to "image", while still requiring SENTENCE_EMBEDDINGS in the second input column.

    Override schema validation to accept IMAGE in the first input column when modalityMode is set to "image", while still requiring SENTENCE_EMBEDDINGS in the second input column.

    schema

    to be validated

    returns

    True if all the required types are present, else false

    Attributes
    protected
    Definition Classes
    VectorDBConnector → RawAnnotator
  131. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  132. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  133. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  134. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  135. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from HasBatchedAnnotate[VectorDBConnector]

Inherited from AnnotatorModel[VectorDBConnector]

Inherited from CanBeLazy

Inherited from RawAnnotator[VectorDBConnector]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[VectorDBConnector]

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

A list of (hyper-)parameter keys this annotator can take. Users can set and get the parameter values through setters and getters, respectively.

Annotator types

Required input and expected output annotator types

Members

Parameter setters

Parameter getters