JohnSnowLabs · DevinTDHa · Jun 30, 2025 · Jun 23, 2025 · Jun 23, 2025 · Jun 24, 2025
diff --git a/CHANGELOG b/CHANGELOG
@@ -1,3 +1,14 @@
+=======
+6.0.4
+=======
+----------------
+New Features & Enhancements
+----------------
+* Introducing MiniLMEmbeddings (SPARKNLP-282)
+* Introducing DataFrameOptimizer (SPARKNLP-1086)
+* Added PDF Reader features (SPARKNLP-1161)
+
+
 =======
 6.0.3
 =======

diff --git a/README.md b/README.md
@@ -63,7 +63,7 @@ $ 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==6.0.3 pyspark==3.3.1
+$ pip install spark-nlp==6.0.4 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -129,7 +129,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-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 *6.0.4* 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 |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -159,7 +159,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.0.3 has been tested and is compatible with the following runtimes:
+Spark NLP 6.0.4 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -176,7 +176,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.0.3 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.0.4 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

diff --git a/build.sbt b/build.sbt
@@ -1,12 +1,12 @@
-import sbtassembly.MergeStrategy
+import Dependencies.*
 import M2Resolvers.m2Resolvers
-import Dependencies._
+import sbtassembly.MergeStrategy
 
 name := getPackageName(is_silicon, is_gpu, is_aarch64)
 
 organization := "com.johnsnowlabs.nlp"
 
-version := "6.0.3"
+version := "6.0.4"
 
 (ThisBuild / scalaVersion) := scalaVer
 
@@ -34,100 +34,8 @@ Compile / doc / target := baseDirectory.value / "docs/api"
 coverageExcludedPackages := ".*nlp.embeddings.*;.*ml.tensorflow.*;.*nlp.annotators.classifier.dl.*;" +
   ".*nlp.annotators.seq2seq.*;.*ml.*"
 
-licenses += "Apache-2.0" -> url("https://opensource.org/licenses/Apache-2.0")
-
 (ThisBuild / resolvers) := m2Resolvers
 
-credentials += Credentials(Path.userHome / ".ivy2" / ".sbtcredentials")
-
-sonatypeProfileName := "com.johnsnowlabs.nlp"
-
-publishTo := sonatypePublishToBundle.value
-
-sonatypeRepository := "https://s01.oss.sonatype.org/service/local"
-
-sonatypeCredentialHost := "s01.oss.sonatype.org"
-
-publishTo := {
-  val nexus = "https://s01.oss.sonatype.org/"
-  if (isSnapshot.value) Some("snapshots" at nexus + "content/repositories/snapshots")
-  else Some("releases" at nexus + "service/local/staging/deploy/maven2")
-}
-
-homepage := Some(url("https://sparknlp.org"))
-
-scmInfo := Some(
-  ScmInfo(
-    url("https://github.com/JohnSnowLabs/spark-nlp"),
-    "scm:[email protected]:JohnSnowLabs/spark-nlp.git"))
-
-(ThisBuild / developers) := List(
-  Developer(
-    id = "saifjsl",
-    name = "Saif Addin",
-    email = "[email protected]",
-    url = url("https://github.com/saifjsl")),
-  Developer(
-    id = "maziyarpanahi",
-    name = "Maziyar Panahi",
-    email = "[email protected]",
-    url = url("https://github.com/maziyarpanahi")),
-  Developer(
-    id = "albertoandreottiATgmail",
-    name = "Alberto Andreotti",
-    email = "[email protected]",
-    url = url("https://github.com/albertoandreottiATgmail")),
-  Developer(
-    id = "danilojsl",
-    name = "Danilo Burbano",
-    email = "[email protected]",
-    url = url("https://github.com/danilojsl")),
-  Developer(
-    id = "rohit13k",
-    name = "Rohit Kumar",
-    email = "[email protected]",
-    url = url("https://github.com/rohit13k")),
-  Developer(
-    id = "aleksei-ai",
-    name = "Aleksei Alekseev",
-    email = "[email protected]",
-    url = url("https://github.com/aleksei-ai")),
-  Developer(
-    id = "showy",
-    name = "Eduardo Muñoz",
-    email = "[email protected]",
-    url = url("https://github.com/showy")),
-  Developer(
-    id = "C-K-Loan",
-    name = "Christian Kasim Loan",
-    email = "[email protected]",
-    url = url("https://github.com/C-K-Loan")),
-  Developer(
-    id = "wolliq",
-    name = "Stefano Lori",
-    email = "[email protected]",
-    url = url("https://github.com/wolliq")),
-  Developer(
-    id = "vankov",
-    name = "Ivan Vankov",
-    email = "[email protected]",
-    url = url("https://github.com/vankov")),
-  Developer(
-    id = "alinapetukhova",
-    name = "Alina Petukhova",
-    email = "[email protected]",
-    url = url("https://github.com/alinapetukhova")),
-  Developer(
-    id = "hatrungduc",
-    name = "Devin Ha",
-    email = "[email protected]",
-    url = url("https://github.com/hatrungduc")),
-  Developer(
-    id = "ahmedlone127",
-    name = "Khawja Ahmed Lone",
-    email = "[email protected]",
-    url = url("https://github.com/ahmedlone127")))
-
 lazy val analyticsDependencies = Seq(
   "org.apache.spark" %% "spark-core" % sparkVer % Provided,
   "org.apache.spark" %% "spark-mllib" % sparkVer % Provided)
@@ -164,8 +72,7 @@ lazy val utilDependencies = Seq(
     exclude ("org.apache.logging.log4j", "log4j-api"),
   scratchpad
     exclude ("org.apache.logging.log4j", "log4j-api"),
-  pdfBox
-)
+  pdfBox)
 
 lazy val typedDependencyParserDependencies = Seq(junit)
 
@@ -238,7 +145,8 @@ lazy val root = (project in file("."))
 
 (assembly / assemblyMergeStrategy) := {
   case PathList("META-INF", "versions", "9", "module-info.class") => MergeStrategy.discard
-  case PathList("module-info.class") => MergeStrategy.discard // Discard any module-info.class globally
+  case PathList("module-info.class") =>
+    MergeStrategy.discard // Discard any module-info.class globally
   case PathList("apache.commons.lang3", _ @_*) => MergeStrategy.discard
   case PathList("org.apache.hadoop", _ @_*) => MergeStrategy.first
   case PathList("com.amazonaws", _ @_*) => MergeStrategy.last

diff --git a/conda/meta.yaml b/conda/meta.yaml
@@ -1,13 +1,13 @@
 {% set name = "spark-nlp" %}
-{% set version = "6.0.3" %}
+{% set version = "6.0.4" %}
 
 package:
   name: {{ name|lower }}
   version: {{ version }}
 
 source:
   url: https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/spark_nlp-{{ version }}.tar.gz
-  sha256: ff09f27c512401cff1ec3af572069b2e2af35b87a0f6737c5340538bac10faf7
+  sha256: 29daf034686ae428eaf83dd371ad095b42164dff40148039002cd3afa66389ee
 
 build:
   noarch: python

diff --git a/docs/api/com/index.html b/docs/api/com/index.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">

diff --git a/docs/api/com/johnsnowlabs/client/CloudClient.html b/docs/api/com/johnsnowlabs/client/CloudClient.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com.johnsnowlabs.client.CloudClient</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com.johnsnowlabs.client.CloudClient" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com.johnsnowlabs.client.CloudClient" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com.johnsnowlabs.client.CloudClient</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com.johnsnowlabs.client.CloudClient" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com.johnsnowlabs.client.CloudClient" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">

diff --git a/docs/api/com/johnsnowlabs/client/CloudManager.html b/docs/api/com/johnsnowlabs/client/CloudManager.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com.johnsnowlabs.client.CloudManager</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com.johnsnowlabs.client.CloudManager" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com.johnsnowlabs.client.CloudManager" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com.johnsnowlabs.client.CloudManager</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com.johnsnowlabs.client.CloudManager" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com.johnsnowlabs.client.CloudManager" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">

diff --git a/docs/api/com/johnsnowlabs/client/CloudResources$.html b/docs/api/com/johnsnowlabs/client/CloudResources$.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com.johnsnowlabs.client.CloudResources</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com.johnsnowlabs.client.CloudResources" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com.johnsnowlabs.client.CloudResources" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com.johnsnowlabs.client.CloudResources</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com.johnsnowlabs.client.CloudResources" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com.johnsnowlabs.client.CloudResources" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">

diff --git a/docs/api/com/johnsnowlabs/client/CloudStorage.html b/docs/api/com/johnsnowlabs/client/CloudStorage.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com.johnsnowlabs.client.CloudStorage</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com.johnsnowlabs.client.CloudStorage" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com.johnsnowlabs.client.CloudStorage" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com.johnsnowlabs.client.CloudStorage</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com.johnsnowlabs.client.CloudStorage" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com.johnsnowlabs.client.CloudStorage" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">

diff --git a/docs/api/com/johnsnowlabs/client/aws/AWSAnonymousCredentials.html b/docs/api/com/johnsnowlabs/client/aws/AWSAnonymousCredentials.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com.johnsnowlabs.client.aws.AWSAnonymousCredentials</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com.johnsnowlabs.client.aws.AWSAnonymousCredentials" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com.johnsnowlabs.client.aws.AWSAnonymousCredentials" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com.johnsnowlabs.client.aws.AWSAnonymousCredentials</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com.johnsnowlabs.client.aws.AWSAnonymousCredentials" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com.johnsnowlabs.client.aws.AWSAnonymousCredentials" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">

diff --git a/docs/api/com/johnsnowlabs/client/aws/AWSBasicCredentials.html b/docs/api/com/johnsnowlabs/client/aws/AWSBasicCredentials.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com.johnsnowlabs.client.aws.AWSBasicCredentials</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com.johnsnowlabs.client.aws.AWSBasicCredentials" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com.johnsnowlabs.client.aws.AWSBasicCredentials" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com.johnsnowlabs.client.aws.AWSBasicCredentials</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com.johnsnowlabs.client.aws.AWSBasicCredentials" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com.johnsnowlabs.client.aws.AWSBasicCredentials" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">

diff --git a/docs/api/com/johnsnowlabs/client/aws/AWSClient.html b/docs/api/com/johnsnowlabs/client/aws/AWSClient.html
@@ -3,9 +3,9 @@
         <head>
           <meta http-equiv="X-UA-Compatible" content="IE=edge" />
           <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
-          <title>Spark NLP 6.0.3 ScalaDoc  - com.johnsnowlabs.client.aws.AWSClient</title>
-          <meta name="description" content="Spark NLP 6.0.3 ScalaDoc - com.johnsnowlabs.client.aws.AWSClient" />
-          <meta name="keywords" content="Spark NLP 6.0.3 ScalaDoc com.johnsnowlabs.client.aws.AWSClient" />
+          <title>Spark NLP 6.0.4 ScalaDoc  - com.johnsnowlabs.client.aws.AWSClient</title>
+          <meta name="description" content="Spark NLP 6.0.4 ScalaDoc - com.johnsnowlabs.client.aws.AWSClient" />
+          <meta name="keywords" content="Spark NLP 6.0.4 ScalaDoc com.johnsnowlabs.client.aws.AWSClient" />
           <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
 
 
@@ -28,7 +28,7 @@
         </head>
         <body>
       <div id="search">
-        <span id="doc-title">Spark NLP 6.0.3 ScalaDoc<span id="doc-version"></span></span>
+        <span id="doc-title">Spark NLP 6.0.4 ScalaDoc<span id="doc-version"></span></span>
         <span class="close-results"><span class="left">&lt;</span> Back</span>
         <div id="textfilter">
           <span class="input">