rajatkrishna
diff --git a/‎CHANGELOG‎
Lines changed: 30 additions & 0 deletions b/‎CHANGELOG‎
Lines changed: 30 additions & 0 deletions
diff --git a/‎README.md‎
Lines changed: 53 additions & 50 deletions b/‎README.md‎
Lines changed: 53 additions & 50 deletions
diff --git a/‎build.sbt‎
Lines changed: 1 addition & 1 deletion b/‎build.sbt‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎conda/meta.yaml‎
Lines changed: 2 additions & 2 deletions b/‎conda/meta.yaml‎
Lines changed: 2 additions & 2 deletions
diff --git a/‎docs/_includes/head.html‎
Lines changed: 1 addition & 1 deletion b/‎docs/_includes/head.html‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎docs/_layouts/landing.html‎
Lines changed: 5 additions & 3 deletions b/‎docs/_layouts/landing.html‎
Lines changed: 5 additions & 3 deletions
diff --git a/‎docs/_posts/DevinTDHa/2023-12-02-zero_shot_classifier_clip_vit_base_patch32_en.md‎
Lines changed: 149 additions & 0 deletions b/‎docs/_posts/DevinTDHa/2023-12-02-zero_shot_classifier_clip_vit_base_patch32_en.md‎
Lines changed: 149 additions & 0 deletions
diff --git a/‎docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_cosine_en.md‎ renamed to ‎docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_2_11_2_2022_en.md‎
Lines changed: 10 additions & 10 deletions b/‎docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_cosine_en.md‎ renamed to ‎docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_2_11_2_2022_en.md‎
Lines changed: 10 additions & 10 deletions
@@ -1,3 +1,33 @@
+========
+5.2.0
+========
+----------------
+New Features & Enhancements
+----------------
+* **NEW:** Introduceding the `CLIPForZeroShotClassification` for Zero-Shot Image Classification using OpenAI's CLIP models
+* **NEW:** Introduceding the `DocumentTokenSplitter` which allows users to split large documents into smaller chunks to be used in RAG with LLM models
+* **NEW:** Introducing support for ONNX Runtime in T5Transformer annotator
+* **NEW:** Introducing support for ONNX Runtime in MarianTransformer annotator
+* **NEW:** Introducing support for ONNX Runtime in BertSentenceEmbeddings annotator
+* **NEW:** Introducing support for ONNX Runtime in XlmRoBertaSentenceEmbeddings annotator
+* **NEW:** Introducing support for ONNX Runtime in CamemBertForQuestionAnswering, CamemBertForTokenClassification, and CamemBertForSequenceClassification annotators
+* Adding a caching support for newly imported T5 models in TF format to improve the performance to be competitive to ONNX version
+* Improve ZIP util and add tests for both ZipArchiveUtil and OnnxWrapper
+* Refactor ONNX and add OnnxSession to broadcast
+* Update ONNX Runtime to 1.16.3
+* Add a new notebook fro structure streaming
+
+----------------
+Bug Fixes
+----------------
+* Fix random dimension mismatch in E5Embeddings and MPNetEmbeddings due to a missing average_pool after last_hidden_state in the output
+* Fix batching exception in E5 and MPNet embeddings annotators failing when sentence is used instead of document
+* Fix chunk construction when an entity is found
+* Fix a bug in library's version in Scala
+* Fix Whisper models not downloading due to wrong library's version
+* Fix and refactor saving best model based on given metrics during NerDL training
+
+
 ========
 5.1.4
 ========
 
@@ -6,7 +6,7 @@ name := getPackageName(is_silicon, is_gpu, is_aarch64)
 
 organization := "com.johnsnowlabs.nlp"
 
-version := "5.1.4"
+version := "5.2.0"
 
 (ThisBuild / scalaVersion) := scalaVer
 
 
@@ -1,13 +1,13 @@
 {% set name = "spark-nlp" %}
-{% set version = "5.1.4" %}
+{% set version = "5.2.0" %}
 
 package:
   name: {{ name|lower }}
   version: {{ version }}
 
 source:
   url: https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/spark-nlp-{{ version }}.tar.gz
-  sha256: f18c2b7e8e82a126b2dab812511de668ea525dfd4a647d20b92a2db1e373476b
+  sha256: d5735efc1b3e2d2df5d4311838583baec2af0b5fffb3773168d1cdd1feb91ae9
 
 build:
   noarch: python
 
@@ -16,7 +16,7 @@
 {%- assign _article_pagetitle = __return -%}
 
 {%- if page.layout == "landing" -%}
-<title>Spark NLP - State of the Art NLP</title>
+<title>Spark NLP - State of the Art NLP Library for Large Language Models (LLMs)</title>
 {%- elsif page.layout == "model" -%}
 <title>{%- include snippets/get-article-modeltitle.html article=page -%}</title>
 {%- elsif _pagetitle -%}
 
@@ -201,7 +201,7 @@ <h3 class="grey h3_title">{{ _section.title }}</h3>
                   <div class="highlight-box">
     {% highlight bash %}
     # Using PyPI
-    $ pip install spark-nlp==5.1.4
+    $ pip install spark-nlp==5.2.0
 
     # Using Anaconda/Conda
     $ conda install -c johnsnowlabs spark-nlp
@@ -336,12 +336,14 @@ <h4 class="blue h4_title">NLP Features</h4>
                     <li>Vision Transformer (Google ViT) <strong>Image Classification</strong></li>
                     <li>Microsoft Swin Transformer <strong>Image Classification</strong></li>
                     <li>Facebook ConvNext <strong>Image Classification</strong></li>
+                    <li>Image to Text <strong>Image Captioning</strong></li>
+                    <li>Zero-Shot <strong>Image Classification (OpenAI CLIP)</strong></li>
                     <li>Automatic Speech Recognition <strong>(OpenAI Whisper, Wav2Vec2 & HuBERT)</strong></li>
                     <li>Easy <strong>ONNX</strong> and <strong>TensorFlow</strong> integrations</li>
                     <li><strong>GPU</strong> Support</li>
                     <li>Full integration with <strong>Spark ML</strong> functions</li>
-                    <li><strong>16800+</strong> pre-trained <strong>models </strong> in <strong>200+ languages! </strong>
-                    <li><strong>5900+</strong> pre-trained <strong>pipelines </strong> in <strong>200+ languages! </strong>
+                    <li><strong>24000+</strong> pre-trained <strong>models </strong> in <strong>200+ languages! </strong>
+                    <li><strong>6000+</strong> pre-trained <strong>pipelines </strong> in <strong>200+ languages! </strong>
                   </ul>
                 </div>
 {% highlight python %}
 
@@ -0,0 +1,149 @@
+---
+layout: model
+title: Image Zero Shot Classification with CLIP
+author: John Snow Labs
+name: zero_shot_classifier_clip_vit_base_patch32
+date: 2023-12-02
+tags: [classification, image, en, zero_shot, open_source, onnx]
+task: Zero-Shot Classification
+language: en
+edition: Spark NLP 5.2.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: CLIPForZeroShotClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+CLIP (Contrastive Language-Image Pre-Training) is a neural network that was trained on image
+and text pairs. It has the ability to predict images without training on any hard-coded
+labels. This makes it very flexible, as labels can be provided during inference. This is
+similar to the zero-shot capabilities of the GPT-2 and 3 models.
+
+This model was imported from huggingface transformers:
+https://huggingface.co/openai/clip-vit-base-patch32
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/zero_shot_classifier_clip_vit_base_patch32_en_5.2.0_3.0_1701541274927.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/zero_shot_classifier_clip_vit_base_patch32_en_5.2.0_3.0_1701541274927.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+import sparknlp
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+imageDF = spark.read \
+    .format("image") \
+    .option("dropInvalid", value = True) \
+    .load("src/test/resources/image/")
+
+imageAssembler: ImageAssembler = ImageAssembler() \
+    .setInputCol("image") \
+    .setOutputCol("image_assembler")
+
+candidateLabels = [
+    "a photo of a bird",
+    "a photo of a cat",
+    "a photo of a dog",
+    "a photo of a hen",
+    "a photo of a hippo",
+    "a photo of a room",
+    "a photo of a tractor",
+    "a photo of an ostrich",
+    "a photo of an ox"]
+
+imageClassifier = CLIPForZeroShotClassification \
+    .pretrained() \
+    .setInputCols(["image_assembler"]) \
+    .setOutputCol("label") \
+    .setCandidateLabels(candidateLabels)
+
+pipeline = Pipeline().setStages([imageAssembler, imageClassifier])
+pipelineDF = pipeline.fit(imageDF).transform(imageDF)
+pipelineDF \
+  .selectExpr("reverse(split(image.origin, '/'))[0] as image_name", "label.result") \
+  .show(truncate=False)
+```
+```scala
+import com.johnsnowlabs.nlp.ImageAssembler
+import com.johnsnowlabs.nlp.annotator._
+import org.apache.spark.ml.Pipeline
+val imageDF = ResourceHelper.spark.read
+  .format("image")
+  .option("dropInvalid", value = true)
+  .load("src/test/resources/image/")
+val imageAssembler: ImageAssembler = new ImageAssembler()
+  .setInputCol("image")
+  .setOutputCol("image_assembler")
+val candidateLabels = Array(
+  "a photo of a bird",
+  "a photo of a cat",
+  "a photo of a dog",
+  "a photo of a hen",
+  "a photo of a hippo",
+  "a photo of a room",
+  "a photo of a tractor",
+  "a photo of an ostrich",
+  "a photo of an ox")
+val imageClassifier = CLIPForZeroShotClassification
+  .pretrained()
+  .setInputCols("image_assembler")
+  .setOutputCol("label")
+  .setCandidateLabels(candidateLabels)
+val pipeline =
+  new Pipeline().setStages(Array(imageAssembler, imageClassifier)).fit(imageDF).transform(imageDF)
+pipeline
+  .selectExpr("reverse(split(image.origin, '/'))[0] as image_name", "label.result")
+  .show(truncate = false)
+```
+</div>
+
+## Results
+
+```bash
++-----------------+-----------------------+
+|image_name       |result                 |
++-----------------+-----------------------+
+|palace.JPEG      |[a photo of a room]    |
+|egyptian_cat.jpeg|[a photo of a cat]     |
+|hippopotamus.JPEG|[a photo of a hippo]   |
+|hen.JPEG         |[a photo of a hen]     |
+|ostrich.JPEG     |[a photo of an ostrich]|
+|junco.JPEG       |[a photo of a bird]    |
+|bluetick.jpg     |[a photo of a dog]     |
+|chihuahua.jpg    |[a photo of a dog]     |
+|tractor.JPEG     |[a photo of a tractor] |
+|ox.JPEG          |[a photo of an ox]     |
++-----------------+-----------------------+
+```
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|zero_shot_classifier_clip_vit_base_patch32|
+|Compatibility:|Spark NLP 5.2.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[image_assembler]|
+|Output Labels:|[classification]|
+|Language:|en|
+|Size:|392.8 MB|
@@ -1,8 +1,8 @@
 ---
 layout: model
-title: English hf_distilbert_imdb_mlm_cosine DistilBertEmbeddings from nos1de
+title: English google_job_data_tuned_trial_2_11_2_2022 DistilBertEmbeddings from EslamAhmed
 author: John Snow Labs
-name: hf_distilbert_imdb_mlm_cosine
+name: google_job_data_tuned_trial_2_11_2_2022
 date: 2023-09-15
 tags: [distilbert, en, open_source, fill_mask, onnx]
 task: Embeddings
@@ -19,13 +19,13 @@ use_language_switcher: "Python-Scala-Java"
 
 ## Description
 
-Pretrained DistilBertEmbeddings  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`hf_distilbert_imdb_mlm_cosine` is a English model originally trained by nos1de.
+Pretrained DistilBertEmbeddings  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`google_job_data_tuned_trial_2_11_2_2022` is a English model originally trained by EslamAhmed.
 
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
-[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_cosine_en_5.1.2_3.0_1694769976827.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
-[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_cosine_en_5.1.2_3.0_1694769976827.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/google_job_data_tuned_trial_2_11_2_2022_en_5.1.2_3.0_1694772782812.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/google_job_data_tuned_trial_2_11_2_2022_en_5.1.2_3.0_1694772782812.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
 
 ## How to use
 
@@ -41,7 +41,7 @@ document_assembler = DocumentAssembler() \
     .setOutputCol("documents")
 
 
-embeddings =DistilBertEmbeddings.pretrained("hf_distilbert_imdb_mlm_cosine","en") \
+embeddings =DistilBertEmbeddings.pretrained("google_job_data_tuned_trial_2_11_2_2022","en") \
             .setInputCols(["documents","token"]) \
             .setOutputCol("embeddings")
 
@@ -60,7 +60,7 @@ val document_assembler = new DocumentAssembler()
     .setOutputCol("embeddings")
 
 val embeddings = DistilBertEmbeddings 
-    .pretrained("hf_distilbert_imdb_mlm_cosine", "en")
+    .pretrained("google_job_data_tuned_trial_2_11_2_2022", "en")
     .setInputCols(Array("documents","token")) 
     .setOutputCol("embeddings") 
 
@@ -79,15 +79,15 @@ val pipelineDF = pipelineModel.transform(data)
 
 {:.table-model}
 |---|---|
-|Model Name:|hf_distilbert_imdb_mlm_cosine|
+|Model Name:|google_job_data_tuned_trial_2_11_2_2022|
 |Compatibility:|Spark NLP 5.1.2+|
 |License:|Open Source|
 |Edition:|Official|
 |Input Labels:|[documents, token]|
 |Output Labels:|[embeddings]|
 |Language:|en|
-|Size:|247.2 MB|
+|Size:|402.3 MB|
 
 ## References
 
-https://huggingface.co/nos1de/hf-distilbert-imdb-mlm-cosine
+https://huggingface.co/EslamAhmed/google_Job_data_tuned_trial_2_11-2-2022