diff --git a/docs/source/guide/ml_tutorials.html b/docs/source/guide/ml_tutorials.html
index ab8b112b2181..0c065faf759e 100644
--- a/docs/source/guide/ml_tutorials.html
+++ b/docs/source/guide/ml_tutorials.html
@@ -1,35 +1,5 @@
 ---
 cards:
-- categories:
-  - Computer Vision
-  - Image Annotation
-  - Object Detection
-  - Grounding DINO
-  hide_frontmatter_title: true
-  hide_menu: true
-  image: /tutorials/grounding-dino.png
-  meta_description: Label Studio tutorial for using Grounding DINO for zero-shot object
-    detection in images
-  meta_title: Image segmentation in Label Studio using a Grounding DINO backend
-  order: 15
-  tier: all
-  title: Zero-shot object detection and image segmentation with Grounding DINO
-  type: guide
-  url: /tutorials/grounding_dino.html
-- categories:
-  - Computer Vision
-  - Video Annotation
-  - Object Detection
-  - Segment Anything Model
-  hide_frontmatter_title: true
-  hide_menu: true
-  image: /tutorials/sam2-video.png
-  meta_title: Using SAM2 with Label Studio for Video Annotation
-  order: 15
-  tier: all
-  title: SAM2 with Videos
-  type: guide
-  url: /tutorials/segment_anything_2_video.html
 - categories:
   - Natural Language Processing
   - Text Classification
@@ -49,94 +19,104 @@
 - categories:
   - Computer Vision
   - Optical Character Recognition
-  - Tesseract
+  - EasyOCR
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/tesseract.png
-  meta_description: Tutorial for how to use Label Studio and Tesseract to assist with
-    your OCR projects
-  meta_title: Interactive bounding boxes OCR in Label Studio with a Tesseract backend
-  order: 55
+  image: /tutorials/easyocr.png
+  meta_description: The EasyOCR model connection integrates the capabilities of EasyOCR
+    with Label Studio to assist in machine learning labeling tasks involving Optical
+    Character Recognition (OCR).
+  meta_title: EasyOCR model connection for transcribing text in images
+  order: 40
   tier: all
-  title: Interactive bounding boxes OCR with Tesseract
+  title: Transcribe text from images with EasyOCR
   type: guide
-  url: /tutorials/tesseract.html
+  url: /tutorials/easyocr.html
 - categories:
-  - Generative AI
-  - Retrieval Augmented Generation
-  - Google
-  - OpenAI
-  - Langchain
+  - Natural Language Processing
+  - Named Entity Recognition
+  - Flair
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/langchain.png
-  meta_description: Use Langchain, OpenAI, and Google to generate responses based
-    on Google search results.
-  meta_title: RAG with a Langchain search agent
-  order: 45
+  image: /tutorials/flair.png
+  meta_description: Tutorial on how to use Label Studio and Flair for faster NER labeling
+  meta_title: Use Flair with Label Studio
+  order: 75
   tier: all
-  title: RAG with a Langchain search agent
+  title: NER labeling with Flair
   type: guide
-  url: /tutorials/langchain_search_agent.html
+  url: /tutorials/flair.html
 - categories:
-  - Audio/Speech Processing
-  - Automatic Speech Recognition
-  - NeMo
-  - NVidia
+  - Natural Language Processing
+  - Named Entity Recognition
+  - GLiNER
+  - BERT
+  - Hugging Face
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/nvidia.png
-  meta_description: Tutorial on how to use set up Nvidia NeMo to use for ASR tasks
-    in Label Studio
-  meta_title: Automatic Speech Recognition with NeMo
-  order: 60
+  image: /tutorials/gliner.png
+  meta_description: Tutorial on how to use GLiNER with your Label Studio project to
+    complete NER tasks
+  meta_title: Use GLiNER for NER annotation
+  order: 37
   tier: all
-  title: Automatic Speech Recognition with NVidia NeMo
+  title: Use GLiNER for NER annotation
   type: guide
-  url: /tutorials/nemo_asr.html
+  url: /tutorials/gliner.html
 - categories:
-  - Natural Language Processing
-  - Named Entity Recognition
-  - Interactive matching
+  - Computer Vision
+  - Image Annotation
+  - Object Detection
+  - Grounding DINO
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/interactive-substring-matching.png
-  meta_description: Use the interactive substring matching model for labeling NER
-    tasks in Label Studio
-  meta_title: Interactive substring matching for NER tasks
-  order: 30
+  image: /tutorials/grounding-dino.png
+  meta_description: Label Studio tutorial for using Grounding DINO for zero-shot object
+    detection in images
+  meta_title: Image segmentation in Label Studio using a Grounding DINO backend
+  order: 15
   tier: all
-  title: Interactive substring matching for NER tasks
+  title: Zero-shot object detection and image segmentation with Grounding DINO
   type: guide
-  url: /tutorials/interactive_substring_matching.html
+  url: /tutorials/grounding_dino.html
 - categories:
   - Computer Vision
-  - Large Language Model
-  - WatsonX
+  - Image Annotation
+  - Object Detection
+  - Zero-shot Image Segmentation
+  - Grounding DINO
+  - Segment Anything Model
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/watsonx.png
-  meta_title: Integrate WatsonX with Label Studio
+  image: /tutorials/grounding-sam.png
+  meta_description: Label Studio tutorial for using Grounding DINO and SAM for zero-shot
+    object detection in images
+  meta_title: Image segmentation in Label Studio using a Grounding DINO backend and
+    SAM
   order: 15
   tier: all
-  title: Integrate WatsonX with Label Studio
+  title: Zero-shot object detection and image segmentation with Grounding DINO and
+    SAM
   type: guide
-  url: /tutorials/watsonx_llm.html
+  url: /tutorials/grounding_sam.html
 - categories:
-  - Natural Language Processing
-  - Named Entity Recognition
-  - SpaCy
+  - Generative AI
+  - Large Language Model
+  - Text Generation
+  - Hugging Face
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/spacy.png
-  meta_description: Tutorial on how to use Label Studio and spaCy for faster NER and
-    POS labeling
-  meta_title: Use spaCy models with Label Studio
-  order: 70
+  image: /tutorials/hf-llm.png
+  meta_description: This tutorial explains how to run Hugging Face Large Language
+    model backend in Label Studio. Hugging Face Large Language Model Backend is a
+    machine learning backend designed to work with Label Studio, providing a custom
+    model for text generation.
+  meta_title: Label Studio tutorial to run Hugging Face Large Language Model backend
+  order: 20
   tier: all
-  title: spaCy models for NER
+  title: Hugging Face Large Language Model (LLM)
   type: guide
-  url: /tutorials/spacy.html
+  url: /tutorials/huggingface_llm.html
 - categories:
   - Natural Language Processing
   - Named Entity Recognition
@@ -154,71 +134,87 @@
   url: /tutorials/huggingface_ner.html
 - categories:
   - Natural Language Processing
-  - Text Classification
-  - Scikit-learn
+  - Named Entity Recognition
+  - Interactive matching
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/scikit-learn.png
-  meta_description: Tutorial on how to use an example ML backend for Label Studio
-    with Scikit-learn logistic regression
-  meta_title: Sklearn Text Classifier model for Label Studio
-  order: 50
+  image: /tutorials/interactive-substring-matching.png
+  meta_description: Use the interactive substring matching model for labeling NER
+    tasks in Label Studio
+  meta_title: Interactive substring matching for NER tasks
+  order: 30
   tier: all
-  title: Sklearn Text Classifier model
+  title: Interactive substring matching for NER tasks
   type: guide
-  url: /tutorials/sklearn_text_classifier.html
+  url: /tutorials/interactive_substring_matching.html
 - categories:
-  - Computer Vision
-  - Optical Character Recognition
-  - EasyOCR
+  - Generative AI
+  - Retrieval Augmented Generation
+  - Google
+  - OpenAI
+  - Langchain
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/easyocr.png
-  meta_description: The EasyOCR model connection integrates the capabilities of EasyOCR
-    with Label Studio to assist in machine learning labeling tasks involving Optical
-    Character Recognition (OCR).
-  meta_title: EasyOCR model connection for transcribing text in images
-  order: 40
+  image: /tutorials/langchain.png
+  meta_description: Use Langchain, OpenAI, and Google to generate responses based
+    on Google search results.
+  meta_title: RAG with a Langchain search agent
+  order: 45
   tier: all
-  title: Transcribe text from images with EasyOCR
+  title: RAG with a Langchain search agent
   type: guide
-  url: /tutorials/easyocr.html
+  url: /tutorials/langchain_search_agent.html
 - categories:
   - Generative AI
   - Large Language Model
-  - Text Generation
-  - Hugging Face
+  - OpenAI
+  - Azure
+  - Ollama
+  - ChatGPT
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/hf-llm.png
-  meta_description: This tutorial explains how to run Hugging Face Large Language
-    model backend in Label Studio. Hugging Face Large Language Model Backend is a
-    machine learning backend designed to work with Label Studio, providing a custom
-    model for text generation.
-  meta_title: Label Studio tutorial to run Hugging Face Large Language Model backend
-  order: 20
+  image: /tutorials/llm-interactive.png
+  meta_description: Label Studio tutorial for interactive LLM labeling with OpenAI,
+    Azure, or Ollama
+  meta_title: Interactive LLM labeling with OpenAI, Azure, or Ollama
+  order: 5
   tier: all
-  title: Hugging Face Large Language Model (LLM)
+  title: Interactive LLM labeling with GPT
   type: guide
-  url: /tutorials/huggingface_llm.html
+  url: /tutorials/llm_interactive.html
 - categories:
   - Computer Vision
   - Object Detection
   - Image Annotation
-  - Segment Anything Model
-  - Facebook
-  - ONNX
+  - OpenMMLab
+  - MMDetection
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/segment-anything.png
-  meta_description: Label Studio tutorial for labeling images with MobileSAM or ONNX
-    SAM.
-  meta_title: Interactive annotation in Label Studio with Segment Anything Model (SAM)
-  order: 10
+  image: /tutorials/openmmlab.png
+  meta_description: This is a tutorial on how to use the example MMDetection model
+    backend with Label Studio for image segmentation tasks.
+  meta_title: Object detection in images with Label Studio and MMDetection
+  order: 65
   tier: all
-  title: Interactive annotation with Segment Anything Model
+  title: Object detection with bounding boxes using MMDetection
   type: guide
-  url: /tutorials/segment_anything_model.html
+  url: /tutorials/mmdetection-3.html
+- categories:
+  - Audio/Speech Processing
+  - Automatic Speech Recognition
+  - NeMo
+  - NVidia
+  hide_frontmatter_title: true
+  hide_menu: true
+  image: /tutorials/nvidia.png
+  meta_description: Tutorial on how to use set up Nvidia NeMo to use for ASR tasks
+    in Label Studio
+  meta_title: Automatic Speech Recognition with NeMo
+  order: 60
+  tier: all
+  title: Automatic Speech Recognition with NVidia NeMo
+  type: guide
+  url: /tutorials/nemo_asr.html
 - categories:
   - Computer Vision
   - Image Annotation
@@ -233,92 +229,112 @@
   title: SAM2 with Images
   type: guide
   url: /tutorials/segment_anything_2_image.html
+- categories:
+  - Computer Vision
+  - Video Annotation
+  - Object Detection
+  - Segment Anything Model
+  hide_frontmatter_title: true
+  hide_menu: true
+  image: /tutorials/sam2-video.png
+  meta_title: Using SAM2 with Label Studio for Video Annotation
+  order: 15
+  tier: all
+  title: SAM2 with Videos
+  type: guide
+  url: /tutorials/segment_anything_2_video.html
+- categories:
+  - Computer Vision
+  - Object Detection
+  - Image Annotation
+  - Segment Anything Model
+  - Facebook
+  - ONNX
+  hide_frontmatter_title: true
+  hide_menu: true
+  image: /tutorials/segment-anything.png
+  meta_description: Label Studio tutorial for labeling images with MobileSAM or ONNX
+    SAM.
+  meta_title: Interactive annotation in Label Studio with Segment Anything Model (SAM)
+  order: 10
+  tier: all
+  title: Interactive annotation with Segment Anything Model
+  type: guide
+  url: /tutorials/segment_anything_model.html
 - categories:
   - Natural Language Processing
-  - Named Entity Recognition
-  - GLiNER
-  - BERT
-  - Hugging Face
+  - Text Classification
+  - Scikit-learn
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/gliner.png
-  meta_description: Tutorial on how to use GLiNER with your Label Studio project to
-    complete NER tasks
-  meta_title: Use GLiNER for NER annotation
-  order: 37
+  image: /tutorials/scikit-learn.png
+  meta_description: Tutorial on how to use an example ML backend for Label Studio
+    with Scikit-learn logistic regression
+  meta_title: Sklearn Text Classifier model for Label Studio
+  order: 50
   tier: all
-  title: Use GLiNER for NER annotation
+  title: Sklearn Text Classifier model
   type: guide
-  url: /tutorials/gliner.html
+  url: /tutorials/sklearn_text_classifier.html
 - categories:
   - Natural Language Processing
   - Named Entity Recognition
-  - Flair
+  - SpaCy
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/flair.png
-  meta_description: Tutorial on how to use Label Studio and Flair for faster NER labeling
-  meta_title: Use Flair with Label Studio
-  order: 75
+  image: /tutorials/spacy.png
+  meta_description: Tutorial on how to use Label Studio and spaCy for faster NER and
+    POS labeling
+  meta_title: Use spaCy models with Label Studio
+  order: 70
   tier: all
-  title: NER labeling with Flair
+  title: spaCy models for NER
   type: guide
-  url: /tutorials/flair.html
+  url: /tutorials/spacy.html
 - categories:
-  - Generative AI
-  - Large Language Model
-  - OpenAI
-  - Azure
-  - Ollama
-  - ChatGPT
+  - Computer Vision
+  - Optical Character Recognition
+  - Tesseract
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/llm-interactive.png
-  meta_description: Label Studio tutorial for interactive LLM labeling with OpenAI,
-    Azure, or Ollama
-  meta_title: Interactive LLM labeling with OpenAI, Azure, or Ollama
-  order: 5
+  image: /tutorials/tesseract.png
+  meta_description: Tutorial for how to use Label Studio and Tesseract to assist with
+    your OCR projects
+  meta_title: Interactive bounding boxes OCR in Label Studio with a Tesseract backend
+  order: 55
   tier: all
-  title: Interactive LLM labeling with GPT
+  title: Interactive bounding boxes OCR with Tesseract
   type: guide
-  url: /tutorials/llm_interactive.html
+  url: /tutorials/tesseract.html
 - categories:
-  - Computer Vision
-  - Object Detection
-  - Image Annotation
-  - OpenMMLab
-  - MMDetection
+  - Generative AI
+  - Large Language Model
+  - WatsonX
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/openmmlab.png
-  meta_description: This is a tutorial on how to use the example MMDetection model
-    backend with Label Studio for image segmentation tasks.
-  meta_title: Object detection in images with Label Studio and MMDetection
-  order: 65
+  image: /tutorials/watsonx.png
+  meta_title: Integrate WatsonX with Label Studio
+  order: 15
   tier: all
-  title: Object detection with bounding boxes using MMDetection
+  title: Integrate WatsonX with Label Studio
   type: guide
-  url: /tutorials/mmdetection-3.html
+  url: /tutorials/watsonx_llm.html
 - categories:
   - Computer Vision
-  - Image Annotation
   - Object Detection
-  - Zero-shot Image Segmentation
-  - Grounding DINO
-  - Segment Anything Model
+  - Image Segmentation
+  - YOLO
   hide_frontmatter_title: true
   hide_menu: true
-  image: /tutorials/grounding-sam.png
-  meta_description: Label Studio tutorial for using Grounding DINO and SAM for zero-shot
-    object detection in images
-  meta_title: Image segmentation in Label Studio using a Grounding DINO backend and
-    SAM
-  order: 15
+  image: /tutorials/yolo.png
+  meta_description: Tutorial on how to use an example ML backend for Label Studio
+    with YOLO
+  meta_title: YOLO ML Backend for Label Studio
+  order: 50
   tier: all
-  title: Zero-shot object detection and image segmentation with Grounding DINO and
-    SAM
+  title: YOLO ML Backend for Label Studio
   type: guide
-  url: /tutorials/grounding_sam.html
+  url: /tutorials/yolo.html
 layout: templates
 meta_description: Tutorial documentation for setting up a machine learning model with
   predictions using PyTorch, GPT2, Sci-kit learn, and other popular frameworks.
diff --git a/docs/source/tutorials/bert_classifier.md b/docs/source/tutorials/bert_classifier.md
index 06872e582a74..97594b68a1a1 100644
--- a/docs/source/tutorials/bert_classifier.md
+++ b/docs/source/tutorials/bert_classifier.md
@@ -15,10 +15,6 @@ categories:
 image: "/tutorials/bert.png"
 ---
 
-<!--
-
--->
-
 # BERT-based text classification
 
 The NewModel is a BERT-based text classification model that is designed to work with Label Studio. This model uses the Hugging Face Transformers library to fine-tune a BERT model for text classification. The model is trained on the labeled data from Label Studio and then used to make predictions on new data.  With this model connected to Label Studio, you can: 
diff --git a/docs/source/tutorials/easyocr.md b/docs/source/tutorials/easyocr.md
index a32058cbbbda..82ac3b4fccbf 100644
--- a/docs/source/tutorials/easyocr.md
+++ b/docs/source/tutorials/easyocr.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/easyocr.png"
 ---
 
-<!--
-
--->
-
 # EasyOCR model connection
 
 The [EasyOCR](https://github.com/JaidedAI/EasyOCR) model connection is a powerful tool that integrates the capabilities of EasyOCR with Label Studio. It is designed to assist in machine learning labeling tasks, specifically those involving Optical Character Recognition (OCR). 
diff --git a/docs/source/tutorials/flair.md b/docs/source/tutorials/flair.md
index 899cb8f82423..6008612eb4df 100644
--- a/docs/source/tutorials/flair.md
+++ b/docs/source/tutorials/flair.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/flair.png"
 ---
 
-<!--
-
--->
-
 # Flair NER example
 
 This example demonstrates how to use Flair NER model with Label Studio.
diff --git a/docs/source/tutorials/gliner.md b/docs/source/tutorials/gliner.md
index 31048adba9d6..e2c8e28dbc16 100644
--- a/docs/source/tutorials/gliner.md
+++ b/docs/source/tutorials/gliner.md
@@ -16,10 +16,6 @@ categories:
 image: "/tutorials/gliner.png"
 ---
 
-<!--
-
--->
-
 # Use GLiNER for NER annotation
 
 The GLiNER model is a BERT family model for generalist NER. We download the model from HuggingFace, but the original
diff --git a/docs/source/tutorials/grounding_dino.md b/docs/source/tutorials/grounding_dino.md
index 5b91a0a4ccee..e27776f26f90 100644
--- a/docs/source/tutorials/grounding_dino.md
+++ b/docs/source/tutorials/grounding_dino.md
@@ -15,10 +15,6 @@ categories:
 image: "/tutorials/grounding-dino.png"
 ---
 
-<!--
-
--->
-
 https://github.com/HumanSignal/label-studio-ml-backend/assets/106922533/d1d2f233-d7c0-40ac-ba6f-368c3c01fd36
 
 
diff --git a/docs/source/tutorials/grounding_sam.md b/docs/source/tutorials/grounding_sam.md
index 002ddfd5b102..37bb01383a52 100644
--- a/docs/source/tutorials/grounding_sam.md
+++ b/docs/source/tutorials/grounding_sam.md
@@ -125,4 +125,4 @@ https://github.com/HumanSignal/label-studio-ml-backend/assets/106922533/79b788e3
 
 Adjust `BOX_THRESHOLD` and `TEXT_THRESHOLD` values in the Dockerfile to a number between 0 to 1 if experimenting. Defaults are set in `dino.py`. For more information about these values, [click here](https://github.com/IDEA-Research/GroundingDINO#star-explanationstips-for-grounding-dino-inputs-and-outputs).
 
-If you want to use SAM models saved from either directories, you can use the `MOBILESAM_CHECKPOINT` and `SAM_CHECKPOINT` as shown in the Dockerfile.
+If you want to use SAM models saved from either directories, you can use the `MOBILESAM_CHECKPOINT` and `SAM_CHECKPOINT` as shown in the Dockerfile.
\ No newline at end of file
diff --git a/docs/source/tutorials/huggingface_llm.md b/docs/source/tutorials/huggingface_llm.md
index 8f0f177471c2..6daa9ae78982 100644
--- a/docs/source/tutorials/huggingface_llm.md
+++ b/docs/source/tutorials/huggingface_llm.md
@@ -15,10 +15,6 @@ categories:
 image: "/tutorials/hf-llm.png"
 ---
 
-<!--
-
--->
-
 # Hugging Face Large Language Model backend
 
 This machine learning backend is designed to work with Label Studio, providing a custom model for text generation. The model is based on the Hugging Face's transformers library and uses a pre-trained model.
diff --git a/docs/source/tutorials/huggingface_ner.md b/docs/source/tutorials/huggingface_ner.md
index 00cc99eb968a..ff68d2a13114 100644
--- a/docs/source/tutorials/huggingface_ner.md
+++ b/docs/source/tutorials/huggingface_ner.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/hf-ner.png"
 ---
 
-<!--
-
--->
-
 # Hugging Face NER model with Label Studio
 
 This project uses a custom machine learning backend model for Named Entity Recognition (NER) with Hugging Face's transformers and Label Studio.
diff --git a/docs/source/tutorials/interactive_substring_matching.md b/docs/source/tutorials/interactive_substring_matching.md
index 6ec043868766..c271b10730ba 100644
--- a/docs/source/tutorials/interactive_substring_matching.md
+++ b/docs/source/tutorials/interactive_substring_matching.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/interactive-substring-matching.png"
 ---
 
-<!--
-
--->
-
 # Interactive substring matching
 
 The Machine Learning (ML) backend is designed to enhance the efficiency of auto-labeling in Named Entity Recognition (NER) tasks. It achieves this by selecting a keyword and automatically matching the same keyword in the provided text. 
diff --git a/docs/source/tutorials/langchain_search_agent.md b/docs/source/tutorials/langchain_search_agent.md
index d67cfd453546..bfb22480188f 100644
--- a/docs/source/tutorials/langchain_search_agent.md
+++ b/docs/source/tutorials/langchain_search_agent.md
@@ -16,12 +16,6 @@ categories:
 image: "/tutorials/langchain.png"
 ---
 
-<!--
-
--->
-
-
-
 # Langchain search agent
 
 This example demonstrates how to use Label Studio with a custom Machine Learning backend.
diff --git a/docs/source/tutorials/llm_interactive.md b/docs/source/tutorials/llm_interactive.md
index f2f0a16dbd42..d7234a59d7ea 100644
--- a/docs/source/tutorials/llm_interactive.md
+++ b/docs/source/tutorials/llm_interactive.md
@@ -17,10 +17,6 @@ categories:
 image: "/tutorials/llm-interactive.png"
 ---
 
-<!--
-
--->
-
 # Interactive LLM labeling
 
 This example server connects Label Studio to [OpenAI](https://platform.openai.com/), [Ollama](https://ollama.com/),
diff --git a/docs/source/tutorials/mmdetection-3.md b/docs/source/tutorials/mmdetection-3.md
index 6f680e84c085..a8a95043be65 100644
--- a/docs/source/tutorials/mmdetection-3.md
+++ b/docs/source/tutorials/mmdetection-3.md
@@ -16,10 +16,6 @@ categories:
 image: "/tutorials/openmmlab.png"
 ---
 
-<!--
-
--->
-
 # Object detection with bounding boxes using MMDetection
 
 https://mmdetection.readthedocs.io/en/latest/
@@ -27,7 +23,7 @@ https://mmdetection.readthedocs.io/en/latest/
 This example demonstrates how to use the MMDetection model with Label Studio to annotate images with bounding boxes. 
 The model is based on the YOLOv3 architecture with a MobileNetV2 backbone and trained on the COCO dataset. 
 
-![screenshot.png](/tutorials/screenshot.png)
+![screenshot.png](screenshot.png)
 
 ## Quick usage
 
@@ -164,4 +160,4 @@ gunicorn --preload --bind :9090 --workers 1 --threads 1 --timeout 0 _wsgi:app
 ```
 
 * Use this guide to find out your access token: https://labelstud.io/guide/api.html
-* You can use and increased value of `SCORE_THRESHOLD` parameter when you see a lot of unwanted detections or lower its value if you don't see any detections.
+* You can use and increased value of `SCORE_THRESHOLD` parameter when you see a lot of unwanted detections or lower its value if you don't see any detections.
\ No newline at end of file
diff --git a/docs/source/tutorials/models.md b/docs/source/tutorials/models.md
new file mode 100644
index 000000000000..98de338a9d10
--- /dev/null
+++ b/docs/source/tutorials/models.md
@@ -0,0 +1 @@
+t your YOLO models here.
\ No newline at end of file
diff --git a/docs/source/tutorials/nemo_asr.md b/docs/source/tutorials/nemo_asr.md
index 413375d1e390..b88a410a7cdc 100644
--- a/docs/source/tutorials/nemo_asr.md
+++ b/docs/source/tutorials/nemo_asr.md
@@ -15,10 +15,6 @@ categories:
 image: "/tutorials/nvidia.png"
 ---
 
-<!--
-
--->
-
 # ASR with NeMo
 
 This example demonstrates how to use the [NeMo](https://github.com/NVIDIA/NeMo/blob/main/nemo/collections/asr/README.md) to perform ASR (Automatic Speech Recognition) in Label Studio.
diff --git a/docs/source/tutorials/segment_anything_2_image.md b/docs/source/tutorials/segment_anything_2_image.md
index 75d2368de652..71e82cf6ba19 100644
--- a/docs/source/tutorials/segment_anything_2_image.md
+++ b/docs/source/tutorials/segment_anything_2_image.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/sam2-images.png"
 ---
 
-<!--
-
--->
-
 # Using SAM2 with Label Studio for Image Annotation
 
 Segment Anything 2, or SAM 2, is a model released by Meta in July 2024. An update to the original Segment Anything Model, 
diff --git a/docs/source/tutorials/segment_anything_2_video.md b/docs/source/tutorials/segment_anything_2_video.md
index 7561c8f7b6c2..1d081f3c1148 100644
--- a/docs/source/tutorials/segment_anything_2_video.md
+++ b/docs/source/tutorials/segment_anything_2_video.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/sam2-video.png"
 ---
 
-<!--
-
--->
-
 # Using SAM2 with Label Studio for Video Annotation
 
 This guide describes the simplest way to start using **SegmentAnything 2** with Label Studio.
@@ -25,7 +21,7 @@ This guide describes the simplest way to start using **SegmentAnything 2** with
 This repository is specifically for working with object tracking in videos. For working with images, 
 see the [segment_anything_2_image repository](https://github.com/HumanSignal/label-studio-ml-backend/tree/master/label_studio_ml/examples/segment_anything_2_image)
 
-![sam2](/tutorials/Sam2Video.gif)
+![sam2](./Sam2Video.gif)
 
 ## Running from source
 
@@ -81,4 +77,4 @@ If you want to contribute to this repository to help with some of these limitati
 
 ## Customization
 
-The ML backend can be customized by adding your own models and logic inside the `./segment_anything_2_video` directory.
+The ML backend can be customized by adding your own models and logic inside the `./segment_anything_2_video` directory.
\ No newline at end of file
diff --git a/docs/source/tutorials/segment_anything_model.md b/docs/source/tutorials/segment_anything_model.md
index a6460cfff782..b7a7a1a6eb55 100644
--- a/docs/source/tutorials/segment_anything_model.md
+++ b/docs/source/tutorials/segment_anything_model.md
@@ -17,10 +17,6 @@ categories:
 image: "/tutorials/segment-anything.png"
 ---
 
-<!--
-
--->
-
 # Interactive annotation in Label Studio with Segment Anything Model
 
 https://github.com/shondle/label-studio-ml-backend/assets/106922533/42a8a535-167c-404a-96bd-c2e2382df99a
diff --git a/docs/source/tutorials/sklearn_text_classifier.md b/docs/source/tutorials/sklearn_text_classifier.md
index 454d1ca59983..ee4102ed65f3 100644
--- a/docs/source/tutorials/sklearn_text_classifier.md
+++ b/docs/source/tutorials/sklearn_text_classifier.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/scikit-learn.png"
 ---
 
-<!--
-
--->
-
 # Sklearn Text Classifier model for Label Studio
 
 The Sklearn Text Classifier model is a custom machine learning backend for Label Studio. It uses a [Logistic Regression model from the Scikit-learn](https://scikit-learn.org/) library to classify text data. This model is particularly useful for text classification tasks in Label Studio, providing an efficient way to generate pre-annotations based on the model's predictions.
diff --git a/docs/source/tutorials/spacy.md b/docs/source/tutorials/spacy.md
index e220c32fae40..3a2567f6069e 100644
--- a/docs/source/tutorials/spacy.md
+++ b/docs/source/tutorials/spacy.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/spacy.png"
 ---
 
-<!--
-
--->
-
 This ML backend provides a simple way to use [spaCy](https://spacy.io/) models for Named Entity Recognition (NER) and Part-of-Speech (POS) tagging.
 
 Current implementation includes the following models:
diff --git a/docs/source/tutorials/tesseract.md b/docs/source/tutorials/tesseract.md
index a4221a74ad2b..d05996faa91b 100644
--- a/docs/source/tutorials/tesseract.md
+++ b/docs/source/tutorials/tesseract.md
@@ -14,10 +14,6 @@ categories:
 image: "/tutorials/tesseract.png"
 ---
 
-<!--
-
--->
-
 # Interactive bounding boxes OCR using Tesseract
 
 Use an OCR engine for interactive ML-assisted labeling, facilitating faster 
@@ -175,4 +171,4 @@ Example below:
 
 Reference links: 
 - https://labelstud.io/blog/Improve-OCR-quality-with-Tesseract-and-Label-Studio.html
-- https://labelstud.io/blog/release-130.html
+- https://labelstud.io/blog/release-130.html
\ No newline at end of file
diff --git a/docs/source/tutorials/watsonx_llm.md b/docs/source/tutorials/watsonx_llm.md
index abfd477bd703..814f60a79b92 100644
--- a/docs/source/tutorials/watsonx_llm.md
+++ b/docs/source/tutorials/watsonx_llm.md
@@ -13,10 +13,6 @@ categories:
 image: "/tutorials/watsonx.png"
 ---
 
-<!--
-
--->
-
 # Integrate WatsonX to Label Studio
 
 WatsonX offers a suite of machine learning tools, including access to many LLMs, prompt
@@ -167,4 +163,4 @@ To get the host and port information below, you can follow the steps under [Pre-
 - `WATSONX_ENG_PORT` - the port information for your WatsonX.data Engine
 - `WATSONX_CATALOG` - the name of the catalog for the table you'll insert your data into. Must be created in the WatsonX.data platform.
 - `WATSONX_SCHEMA` - the name of the schema for the table you'll insert your data into. Must be created in the WatsonX.data platform.
-- `WATSONX_TABLE` - the name of the table you'll insert your data into. Does not need to be already created.
+- `WATSONX_TABLE` - the name of the table you'll insert your data into. Does not need to be already created.
\ No newline at end of file
diff --git a/docs/source/tutorials/yolo.md b/docs/source/tutorials/yolo.md
new file mode 100644
index 000000000000..c287917662ee
--- /dev/null
+++ b/docs/source/tutorials/yolo.md
@@ -0,0 +1,808 @@
+---
+title: YOLO ML Backend for Label Studio
+type: guide
+tier: all
+order: 50
+hide_menu: true
+hide_frontmatter_title: true
+meta_title: YOLO ML Backend for Label Studio
+meta_description: Tutorial on how to use an example ML backend for Label Studio with YOLO
+categories:
+    - Computer Vision
+    - Object Detection
+    - Image Segmentation
+    - YOLO
+image: "/tutorials/yolo.png"
+---
+
+# YOLO ML backend for Label Studio
+
+The YOLO ML backend for Label Studio is designed to integrate advanced object detection, 
+segmentation, classification, and video object tracking capabilities directly into Label Studio. 
+
+This integration allows you to leverage powerful YOLOv8 models for various machine learning tasks, 
+making it easier to annotate large datasets and ensure high-quality predictions. 
+
+<div align="left">
+  <a href="http://www.youtube.com/watch?v=UyaecID1iG8" title="Integrating YOLO V8 with Label Studio">
+    <img src="http://img.youtube.com/vi/UyaecID1iG8/0.jpg" alt="YOLO Integration Video" style="width:50%;"/>
+      <br>
+    Check the video tutorial
+  </a>
+</div>
+<br/>
+
+**Supported Features**
+
+| YOLO Task Name                        | LS Control Tag                       | Prediction Supported | LS Import Supported | LS Export Supported |
+|---------------------------------------|--------------------------------------|----------------------|---------------------|---------------------|
+| Object Detection                      | `<RectangleLabels>`                  | ✅                    | YOLO, COCO          | YOLO, COCO          |
+| Oriented Bounding Boxes (OBB)         | `<RectangleLabels model_obb="true">` | ✅                    | YOLO                | YOLO                |
+| Image Instance Segmentation: Polygons | `<PolygonLabels>`                    | ✅                    | COCO                | YOLO, COCO          |
+| Image Semantic Segmentation: Masks    | `<BrushLabels>`                      | ❌                    | Native              | Native              |
+| Image Classification                  | `<Choices>`                          | ✅                    | Native              | Native              |
+| Pose Detection                        | `<KeyPoints>`                        | ✅                    | Native              | Native              |
+| Video Object Tracking                 | `<VideoRectangle>`                   | ✅                    | Native              | Native              |
+| Video Temporal Classification         | `<TimelineLabels>`                   | Coming soon          | Native              | Native              |
+
+* **LS Control Tag**: Label Studio [control tag](https://labelstud.io/tags/) from the labeling configuration. 
+* **LS Import Supported**: Indicates whether Label Studio supports Import from YOLO format to Label Studio (using the LS converter).
+* **LS Export Supported**: Indicates whether Label Studio supports Export from Label Studio to YOLO format (the **Export** button on the Data Manager and using the LS converter).
+* **Native**: Native means that only native Label Studio JSON format is supported.
+
+
+## Before you begin 
+
+Before you begin, you need to install the [Label Studio ML backend](https://github.com/HumanSignal/label-studio-ml-backend?tab=readme-ov-file#quickstart). 
+
+This tutorial uses the [YOLO example](https://github.com/HumanSignal/label-studio-ml-backend/tree/master/label_studio_ml/examples/yolo).
+
+## Quick start
+
+1. Add `LABEL_STUDIO_URL` and `LABEL_STUDIO_API_KEY` to the `docker-compose.yml` file. These variables should point to your Label Studio instance and its API key, respectively. For more information about finding your Label Studio API key, [see our documentation](https://labelstud.io/guide/user_account#Access-token).
+
+2. Run docker compose
+
+    ```bash
+    docker-compose up --build
+    ```
+
+3. Open Label Studio and create a new project with the following labeling config:
+
+    ```xml
+    <View>
+      <Image name="image" value="$image"/>
+      <RectangleLabels name="label" toName="image" model_score_threshold="0.25">
+        <Label value="Car" background="blue" predicted_values="jeep,cab,limousine,truck"/>
+      </RectangleLabels>
+    </View>
+    ```
+
+4. Then from the **Model** page in the project settings, [connect the model](https://labelstud.io/guide/ml#Connect-the-model-to-Label-Studio). The default URL is `http://localhost:9090`. 
+
+5. Add images to Label Studio.
+
+6. Open any task in the Data Manager and see the predictions from the YOLO model.
+
+## Labeling configurations
+
+### Supported object & control tags
+
+**Object tags**
+
+- `<Image>` - [Image to annotate](https://labelstud.io/tags/image)
+- `<Video>` - [Video to annotate](https://labelstud.io/tags/video)
+
+**Control tags**
+
+- `<RectangleLabels>` - [Bounding boxes](https://labelstud.io/tags/rectanglelabels); object detection task
+- `<PolygonLabels>` - [Polygons](https://labelstud.io/tags/polygonlables); segmentation task
+- `<VideoRectangle>` - [Video bounding boxes](https://labelstud.io/tags/videorectangle); object tracking task
+- `<Choices>` - [Classification](https://labelstud.io/tags/choices)
+
+**How to skip the control tag?**
+
+If you don't want to use the ML backend for some control tags, 
+you can force skipping by adding the `model_skip="true"` attribute to the control tag:
+    
+```xml
+<Choices name="choice" toName="image" model_skip="true">
+```
+
+### Mixed object and control tags
+
+You can mix different object and control tags in one project. 
+The YOLO model will detect all known control tags and make predictions for them.
+For example: 
+
+```xml
+<View>
+  <Image name="image1" value="$image"/>
+  <RectangleLabels name="label" toName="image1" model_score_threshold="0.1">
+    <Label value="person" background="red"/>
+    <Label value="car" background="blue"/>
+  </RectangleLabels>
+  
+  <Image name="image2" value="$image"/>
+  <Choices name="choice" toName="image2" model_score_threshold="0.1">
+    <Choice value="airship"/>
+    <Choice value="passenger_car"/>
+  </Choices>
+</View>
+```
+
+In this example, both `RectangleLabels` and `Choices` will be detected and predicted by the YOLO model.
+
+You can also use different YOLO models for the same task to compare them visually:
+
+```xml
+<View>
+  <Image name="image1" value="$image"/>
+  <RectangleLabels name="label1" toName="image1" model_path="yolov8n.pt" model_score_threshold="0.1">
+    <Label value="car" background="blue"/>
+  </RectangleLabels>
+  <RectangleLabels name="label2" toName="image1" model_path="yolov8m.pt" model_score_threshold="0.1">
+    <Label value="car" background="red"/>
+  </RectangleLabels>
+</View>
+```
+
+
+### Label and choice mapping
+
+```mermaid
+graph TD
+    A[Label Studio :: Labeling Config :: Labels or Choices] <--> B[ML Model :: Names]
+```
+
+If you use a common YOLO model, you have to add mapping between your labels and the ML model labels. 
+By default, the YOLO ML backend will use the same (or lowercased) names as you specified in the `value` attribute. 
+
+In this example the label "Jeep" will be mapped to "jeep" in the ML model:
+
+```xml
+<Choice value="Jeep"/> 
+```
+
+For more precise control you can use the `predicted_values` attribute 
+to specify multiple and different labels from the ML model:
+
+```xml
+<Choice value="Car" predicted_values="jeep,cab,limousine"/>
+```
+
+<details>
+<summary>Tip: How to find all YOLO model names?</summary>
+<br/>
+Labels are printed in the ML model logs when you start using the ML backend with the INFO logging level. 
+
+Or you can find some labels in [YOLO_CLASSES.md](YOLO_CLASSES.md)
+</details>
+
+<details>
+<summary>Tip: How to map my labels to YOLO names using an LLM?</summary>
+<br/>
+You can use an LLM model (e.g. ChatGPT) to automatically build mapping between Label Studio labels and ML model labels. 
+Here is an example of a prompt for this. It includes 1000 labels from YOLOv8 classification model (`yolov8n-cls`).
+
+```
+**Task:**
+
+1. **ML Model Labels:**
+   - I have the following labels in my ML model:
+['tench', 'goldfish', 'great_white_shark', 'tiger_shark', 'hammerhead', 'electric_ray', 'stingray', 'cock', 'hen', 'ostrich', 'brambling', 'goldfinch', 'house_finch', 'junco', 'indigo_bunting', 'robin', 'bulbul', 'jay', 'magpie', 'chickadee', 'water_ouzel', 'kite', 'bald_eagle', 'vulture', 'great_grey_owl', 'European_fire_salamander', 'common_newt', 'eft', 'spotted_salamander', 'axolotl', 'bullfrog', 'tree_frog', 'tailed_frog', 'loggerhead', 'leatherback_turtle', 'mud_turtle', 'terrapin', 'box_turtle', 'banded_gecko', 'common_iguana', 'American_chameleon', 'whiptail', 'agama', 'frilled_lizard', 'alligator_lizard', 'Gila_monster', 'green_lizard', 'African_chameleon', 'Komodo_dragon', 'African_crocodile', 'American_alligator', 'triceratops', 'thunder_snake', 'ringneck_snake', 'hognose_snake', 'green_snake', 'king_snake', 'garter_snake', 'water_snake', 'vine_snake', 'night_snake', 'boa_constrictor', 'rock_python', 'Indian_cobra', 'green_mamba', 'sea_snake', 'horned_viper', 'diamondback', 'sidewinder', 'trilobite', 'harvestman', 'scorpion', 'black_and_gold_garden_spider', 'barn_spider', 'garden_spider', 'black_widow', 'tarantula', 'wolf_spider', 'tick', 'centipede', 'black_grouse', 'ptarmigan', 'ruffed_grouse', 'prairie_chicken', 'peacock', 'quail', 'partridge', 'African_grey', 'macaw', 'sulphur-crested_cockatoo', 'lorikeet', 'coucal', 'bee_eater', 'hornbill', 'hummingbird', 'jacamar', 'toucan', 'drake', 'red-breasted_merganser', 'goose', 'black_swan', 'tusker', 'echidna', 'platypus', 'wallaby', 'koala', 'wombat', 'jellyfish', 'sea_anemone', 'brain_coral', 'flatworm', 'nematode', 'conch', 'snail', 'slug', 'sea_slug', 'chiton', 'chambered_nautilus', 'Dungeness_crab', 'rock_crab', 'fiddler_crab', 'king_crab', 'American_lobster', 'spiny_lobster', 'crayfish', 'hermit_crab', 'isopod', 'white_stork', 'black_stork', 'spoonbill', 'flamingo', 'little_blue_heron', 'American_egret', 'bittern', 'crane_(bird)', 'limpkin', 'European_gallinule', 'American_coot', 'bustard', 'ruddy_turnstone', 'red-backed_sandpiper', 'redshank', 'dowitcher', 'oystercatcher', 'pelican', 'king_penguin', 'albatross', 'grey_whale', 'killer_whale', 'dugong', 'sea_lion', 'Chihuahua', 'Japanese_spaniel', 'Maltese_dog', 'Pekinese', 'Shih-Tzu', 'Blenheim_spaniel', 'papillon', 'toy_terrier', 'Rhodesian_ridgeback', 'Afghan_hound', 'basset', 'beagle', 'bloodhound', 'bluetick', 'black-and-tan_coonhound', 'Walker_hound', 'English_foxhound', 'redbone', 'borzoi', 'Irish_wolfhound', 'Italian_greyhound', 'whippet', 'Ibizan_hound', 'Norwegian_elkhound', 'otterhound', 'Saluki', 'Scottish_deerhound', 'Weimaraner', 'Staffordshire_bullterrier', 'American_Staffordshire_terrier', 'Bedlington_terrier', 'Border_terrier', 'Kerry_blue_terrier', 'Irish_terrier', 'Norfolk_terrier', 'Norwich_terrier', 'Yorkshire_terrier', 'wire-haired_fox_terrier', 'Lakeland_terrier', 'Sealyham_terrier', 'Airedale', 'cairn', 'Australian_terrier', 'Dandie_Dinmont', 'Boston_bull', 'miniature_schnauzer', 'giant_schnauzer', 'standard_schnauzer', 'Scotch_terrier', 'Tibetan_terrier', 'silky_terrier', 'soft-coated_wheaten_terrier', 'West_Highland_white_terrier', 'Lhasa', 'flat-coated_retriever', 'curly-coated_retriever', 'golden_retriever', 'Labrador_retriever', 'Chesapeake_Bay_retriever', 'German_short-haired_pointer', 'vizsla', 'English_setter', 'Irish_setter', 'Gordon_setter', 'Brittany_spaniel', 'clumber', 'English_springer', 'Welsh_springer_spaniel', 'cocker_spaniel', 'Sussex_spaniel', 'Irish_water_spaniel', 'kuvasz', 'schipperke', 'groenendael', 'malinois', 'briard', 'kelpie', 'komondor', 'Old_English_sheepdog', 'Shetland_sheepdog', 'collie', 'Border_collie', 'Bouvier_des_Flandres', 'Rottweiler', 'German_shepherd', 'Doberman', 'miniature_pinscher', 'Greater_Swiss_Mountain_dog', 'Bernese_mountain_dog', 'Appenzeller', 'EntleBucher', 'boxer', 'bull_mastiff', 'Tibetan_mastiff', 'French_bulldog', 'Great_Dane', 'Saint_Bernard', 'Eskimo_dog', 'malamute', 'Siberian_husky', 'dalmatian', 'affenpinscher', 'basenji', 'pug', 'Leonberg', 'Newfoundland', 'Great_Pyrenees', 'Samoyed', 'Pomeranian', 'chow', 'keeshond', 'Brabancon_griffon', 'Pembroke', 'Cardigan', 'toy_poodle', 'miniature_poodle', 'standard_poodle', 'Mexican_hairless', 'timber_wolf', 'white_wolf', 'red_wolf', 'coyote', 'dingo', 'dhole', 'African_hunting_dog', 'hyena', 'red_fox', 'kit_fox', 'Arctic_fox', 'grey_fox', 'tabby', 'tiger_cat', 'Persian_cat', 'Siamese_cat', 'Egyptian_cat', 'cougar', 'lynx', 'leopard', 'snow_leopard', 'jaguar', 'lion', 'tiger', 'cheetah', 'brown_bear', 'American_black_bear', 'ice_bear', 'sloth_bear', 'mongoose', 'meerkat', 'tiger_beetle', 'ladybug', 'ground_beetle', 'long-horned_beetle', 'leaf_beetle', 'dung_beetle', 'rhinoceros_beetle', 'weevil', 'fly', 'bee', 'ant', 'grasshopper', 'cricket', 'walking_stick', 'cockroach', 'mantis', 'cicada', 'leafhopper', 'lacewing', 'dragonfly', 'damselfly', 'admiral', 'ringlet', 'monarch', 'cabbage_butterfly', 'sulphur_butterfly', 'lycaenid', 'starfish', 'sea_urchin', 'sea_cucumber', 'wood_rabbit', 'hare', 'Angora', 'hamster', 'porcupine', 'fox_squirrel', 'marmot', 'beaver', 'guinea_pig', 'sorrel', 'zebra', 'hog', 'wild_boar', 'warthog', 'hippopotamus', 'ox', 'water_buffalo', 'bison', 'ram', 'bighorn', 'ibex', 'hartebeest', 'impala', 'gazelle', 'Arabian_camel', 'llama', 'weasel', 'mink', 'polecat', 'black-footed_ferret', 'otter', 'skunk', 'badger', 'armadillo', 'three-toed_sloth', 'orangutan', 'gorilla', 'chimpanzee', 'gibbon', 'siamang', 'guenon', 'patas', 'baboon', 'macaque', 'langur', 'colobus', 'proboscis_monkey', 'marmoset', 'capuchin', 'howler_monkey', 'titi', 'spider_monkey', 'squirrel_monkey', 'Madagascar_cat', 'indri', 'Indian_elephant', 'African_elephant', 'lesser_panda', 'giant_panda', 'barracouta', 'eel', 'coho', 'rock_beauty', 'anemone_fish', 'sturgeon', 'gar', 'lionfish', 'puffer', 'abacus', 'abaya', 'academic_gown', 'accordion', 'acoustic_guitar', 'aircraft_carrier', 'airliner', 'airship', 'altar', 'ambulance', 'amphibian', 'analog_clock', 'apiary', 'apron', 'ashcan', 'assault_rifle', 'backpack', 'bakery', 'balance_beam', 'balloon', 'ballpoint', 'Band_Aid', 'banjo', 'bannister', 'barbell', 'barber_chair', 'barbershop', 'barn', 'barometer', 'barrel', 'barrow', 'baseball', 'basketball', 'bassinet', 'bassoon', 'bathing_cap', 'bath_towel', 'bathtub', 'beach_wagon', 'beacon', 'beaker', 'bearskin', 'beer_bottle', 'beer_glass', 'bell_cote', 'bib', 'bicycle-built-for-two', 'bikini', 'binder', 'binoculars', 'birdhouse', 'boathouse', 'bobsled', 'bolo_tie', 'bonnet', 'bookcase', 'bookshop', 'bottlecap', 'bow', 'bow_tie', 'brass', 'brassiere', 'breakwater', 'breastplate', 'broom', 'bucket', 'buckle', 'bulletproof_vest', 'bullet_train', 'butcher_shop', 'cab', 'caldron', 'candle', 'cannon', 'canoe', 'can_opener', 'cardigan', 'car_mirror', 'carousel', "carpenter's_kit", 'carton', 'car_wheel', 'cash_machine', 'cassette', 'cassette_player', 'castle', 'catamaran', 'CD_player', 'cello', 'cellular_telephone', 'chain', 'chainlink_fence', 'chain_mail', 'chain_saw', 'chest', 'chiffonier', 'chime', 'china_cabinet', 'Christmas_stocking', 'church', 'cinema', 'cleaver', 'cliff_dwelling', 'cloak', 'clog', 'cocktail_shaker', 'coffee_mug', 'coffeepot', 'coil', 'combination_lock', 'computer_keyboard', 'confectionery', 'container_ship', 'convertible', 'corkscrew', 'cornet', 'cowboy_boot', 'cowboy_hat', 'cradle', 'crane_(machine)', 'crash_helmet', 'crate', 'crib', 'Crock_Pot', 'croquet_ball', 'crutch', 'cuirass', 'dam', 'desk', 'desktop_computer', 'dial_telephone', 'diaper', 'digital_clock', 'digital_watch', 'dining_table', 'dishrag', 'dishwasher', 'disk_brake', 'dock', 'dogsled', 'dome', 'doormat', 'drilling_platform', 'drum', 'drumstick', 'dumbbell', 'Dutch_oven', 'electric_fan', 'electric_guitar', 'electric_locomotive', 'entertainment_center', 'envelope', 'espresso_maker', 'face_powder', 'feather_boa', 'file', 'fireboat', 'fire_engine', 'fire_screen', 'flagpole', 'flute', 'folding_chair', 'football_helmet', 'forklift', 'fountain', 'fountain_pen', 'four-poster', 'freight_car', 'French_horn', 'frying_pan', 'fur_coat', 'garbage_truck', 'gasmask', 'gas_pump', 'goblet', 'go-kart', 'golf_ball', 'golfcart', 'gondola', 'gong', 'gown', 'grand_piano', 'greenhouse', 'grille', 'grocery_store', 'guillotine', 'hair_slide', 'hair_spray', 'half_track', 'hammer', 'hamper', 'hand_blower', 'hand-held_computer', 'handkerchief', 'hard_disc', 'harmonica', 'harp', 'harvester', 'hatchet', 'holster', 'home_theater', 'honeycomb', 'hook', 'hoopskirt', 'horizontal_bar', 'horse_cart', 'hourglass', 'iPod', 'iron', "jack-o'-lantern", 'jean', 'jeep', 'jersey', 'jigsaw_puzzle', 'jinrikisha', 'joystick', 'kimono', 'knee_pad', 'knot', 'lab_coat', 'ladle', 'lampshade', 'laptop', 'lawn_mower', 'lens_cap', 'letter_opener', 'library', 'lifeboat', 'lighter', 'limousine', 'liner', 'lipstick', 'Loafer', 'lotion', 'loudspeaker', 'loupe', 'lumbermill', 'magnetic_compass', 'mailbag', 'mailbox', 'maillot_(tights)', 'maillot_(tank_suit)', 'manhole_cover', 'maraca', 'marimba', 'mask', 'matchstick', 'maypole', 'maze', 'measuring_cup', 'medicine_chest', 'megalith', 'microphone', 'microwave', 'military_uniform', 'milk_can', 'minibus', 'miniskirt', 'minivan', 'missile', 'mitten', 'mixing_bowl', 'mobile_home', 'Model_T', 'modem', 'monastery', 'monitor', 'moped', 'mortar', 'mortarboard', 'mosque', 'mosquito_net', 'motor_scooter', 'mountain_bike', 'mountain_tent', 'mouse', 'mousetrap', 'moving_van', 'muzzle', 'nail', 'neck_brace', 'necklace', 'nipple', 'notebook', 'obelisk', 'oboe', 'ocarina', 'odometer', 'oil_filter', 'organ', 'oscilloscope', 'overskirt', 'oxcart', 'oxygen_mask', 'packet', 'paddle', 'paddlewheel', 'padlock', 'paintbrush', 'pajama', 'palace', 'panpipe', 'paper_towel', 'parachute', 'parallel_bars', 'park_bench', 'parking_meter', 'passenger_car', 'patio', 'pay-phone', 'pedestal', 'pencil_box', 'pencil_sharpener', 'perfume', 'Petri_dish', 'photocopier', 'pick', 'pickelhaube', 'picket_fence', 'pickup', 'pier', 'piggy_bank', 'pill_bottle', 'pillow', 'ping-pong_ball', 'pinwheel', 'pirate', 'pitcher', 'plane', 'planetarium', 'plastic_bag', 'plate_rack', 'plow', 'plunger', 'Polaroid_camera', 'pole', 'police_van', 'poncho', 'pool_table', 'pop_bottle', 'pot', "potter's_wheel", 'power_drill', 'prayer_rug', 'printer', 'prison', 'projectile', 'projector', 'puck', 'punching_bag', 'purse', 'quill', 'quilt', 'racer', 'racket', 'radiator', 'radio', 'radio_telescope', 'rain_barrel', 'recreational_vehicle', 'reel', 'reflex_camera', 'refrigerator', 'remote_control', 'restaurant', 'revolver', 'rifle', 'rocking_chair', 'rotisserie', 'rubber_eraser', 'rugby_ball', 'rule', 'running_shoe', 'safe', 'safety_pin', 'saltshaker', 'sandal', 'sarong', 'sax', 'scabbard', 'scale', 'school_bus', 'schooner', 'scoreboard', 'screen', 'screw', 'screwdriver', 'seat_belt', 'sewing_machine', 'shield', 'shoe_shop', 'shoji', 'shopping_basket', 'shopping_cart', 'shovel', 'shower_cap', 'shower_curtain', 'ski', 'ski_mask', 'sleeping_bag', 'slide_rule', 'sliding_door', 'slot', 'snorkel', 'snowmobile', 'snowplow', 'soap_dispenser', 'soccer_ball', 'sock', 'solar_dish', 'sombrero', 'soup_bowl', 'space_bar', 'space_heater', 'space_shuttle', 'spatula', 'speedboat', 'spider_web', 'spindle', 'sports_car', 'spotlight', 'stage', 'steam_locomotive', 'steel_arch_bridge', 'steel_drum', 'stethoscope', 'stole', 'stone_wall', 'stopwatch', 'stove', 'strainer', 'streetcar', 'stretcher', 'studio_couch', 'stupa', 'submarine', 'suit', 'sundial', 'sunglass', 'sunglasses', 'sunscreen', 'suspension_bridge', 'swab', 'sweatshirt', 'swimming_trunks', 'swing', 'switch', 'syringe', 'table_lamp', 'tank', 'tape_player', 'teapot', 'teddy', 'television', 'tennis_ball', 'thatch', 'theater_curtain', 'thimble', 'thresher', 'throne', 'tile_roof', 'toaster', 'tobacco_shop', 'toilet_seat', 'torch', 'totem_pole', 'tow_truck', 'toyshop', 'tractor', 'trailer_truck', 'tray', 'trench_coat', 'tricycle', 'trimaran', 'tripod', 'triumphal_arch', 'trolleybus', 'trombone', 'tub', 'turnstile', 'typewriter_keyboard', 'umbrella', 'unicycle', 'upright', 'vacuum', 'vase', 'vault', 'velvet', 'vending_machine', 'vestment', 'viaduct', 'violin', 'volleyball', 'waffle_iron', 'wall_clock', 'wallet', 'wardrobe', 'warplane', 'washbasin', 'washer', 'water_bottle', 'water_jug', 'water_tower', 'whiskey_jug', 'whistle', 'wig', 'window_screen', 'window_shade', 'Windsor_tie', 'wine_bottle', 'wing', 'wok', 'wooden_spoon', 'wool', 'worm_fence', 'wreck', 'yawl', 'yurt', 'web_site', 'comic_book', 'crossword_puzzle', 'street_sign', 'traffic_light', 'book_jacket', 'menu', 'plate', 'guacamole', 'consomme', 'hot_pot', 'trifle', 'ice_cream', 'ice_lolly', 'French_loaf', 'bagel', 'pretzel', 'cheeseburger', 'hotdog', 'mashed_potato', 'head_cabbage', 'broccoli', 'cauliflower', 'zucchini', 'spaghetti_squash', 'acorn_squash', 'butternut_squash', 'cucumber', 'artichoke', 'bell_pepper', 'cardoon', 'mushroom', 'Granny_Smith', 'strawberry', 'orange', 'lemon', 'fig', 'pineapple', 'banana', 'jackfruit', 'custard_apple', 'pomegranate', 'hay', 'carbonara', 'chocolate_sauce', 'dough', 'meat_loaf', 'pizza', 'potpie', 'burrito', 'red_wine', 'espresso', 'cup', 'eggnog', 'alp', 'bubble', 'cliff', 'coral_reef', 'geyser', 'lakeside', 'promontory', 'sandbar', 'seashore', 'valley', 'volcano', 'ballplayer', 'groom', 'scuba_diver', 'rapeseed', 'daisy', "yellow_lady's_slipper", 'corn', 'acorn', 'hip', 'buckeye', 'coral_fungus', 'agaric', 'gyromitra', 'stinkhorn', 'earthstar', 'hen-of-the-woods', 'bolete', 'ear', 'toilet_tissue']
+
+
+2. **Labeling Config:**
+   - I have this labeling config from Label Studio:
+   <View>
+     <Image name="image" value="$image"/>
+     <Choices name="choice" toName="image">
+       <Choice value="Airplane"/>
+       <Choice value="Car"/>
+     </Choices>
+   </View>
+
+3. **Mapping Instructions:**
+   - Map the labels from the Label Studio config to the closest matching ML model labels as follows:
+     1. Use the `value` attribute from each `<Choice>` tag to identify the label.
+     2. Find all similar and relevant labels from the ML model corresponding to each `<Choice>` label.
+     3. Add a `predicted_values="<relevant_label1_from_ml_model>,<relevant_label2_from_ml_model>"` attribute inside each `<Choice>` tag using only labels from the ML model.
+
+4. **Output:**
+   - Provide the final labeling config with the `predicted_values` attribute added, using all relevant labels from the ML model, without any explanations.
+```
+
+</details>
+
+## YOLOv5 and other YOLO models
+
+YOLOv8 models have been successfully tested with this ML backend.
+
+Attempts to run YOLOv5 were unsuccessful without modifications. 
+It may be possible to run it by applying some changes, such as installing additional dependencies. 
+The same applies to other YOLO models.
+
+## Custom YOLO models
+
+You can load your own YOLO labels using the following steps:
+
+1. Mount your model as `/app/models/<your-model>.pt` inside of your docker.
+2. Set `ALLOW_CUSTOM_MODEL_PATH=true` (it is true by default) in your Docker environment parameters ([`docker-compose.yml`](docker-compose.yml)).
+3. Add `model_path="<your-model>.pt"` to the control tag in the labeling configuration, e.g.:
+
+```xml
+<RectangleLabels model_path="my_model.pt">
+```
+
+## Training
+
+The current Label Studio ML backend doesn't support training YOLO models. You have to do it manually on your side.
+Or you can contribute to this repository and add training support for this ML backend.
+
+<br>
+
+-------------------
+
+<br>
+
+
+## Classification using `<Choices>`
+
+YOLO provides a classification model and Label Studio supports this with the `Choices` control tag.
+
+More info: https://docs.ultralytics.com/tasks/classify/
+
+https://github.com/user-attachments/assets/30c5ce43-2c89-4ddf-a77d-9d1d75ac3419
+
+
+### Labeling config
+
+```xml
+<View>
+  <Image name="image" value="$image"/>
+  <Choices name="choice" toName="image" model_score_threshold="0.25">
+    <Choice value="Airplane" predicted_values="aircraft_carrier,airliner,airship,warplane"/>
+    <Choice value="Car" predicted_values="limousine,minivan,jeep,sports_car,passenger_car,police_van"/>
+  </Choices>
+</View>
+```
+
+### Parameters
+
+| Parameter               | Type   | Default | Description                                                                                                                                                                                                                                                                                                                                                          |
+|-------------------------|--------|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `model_score_threshold` | float  | 0.5     | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives.                                                                                                                                                                               |
+| `model_path`            | string | None    | Path to the custom YOLO model. See more in the section "Custom YOLO Models."                                                                                                                                                                                                                                                                                         |
+| `choice`                | string | single  | Possible values: `single`, `single-radio`, `multiple`. If you use `choice="single"` (default) you can select only one label. The ML backend will return the label with the highest confidence using argmax strategy. If you use `choice="multiple"` you can select multiple labels. The ML backend will return all labels with confidence above the `model_score_threshold`. |
+
+
+For example:
+```xml
+<Choices name="choice" toName="image" model_score_threshold="0.25" model_path="my_model.pt">
+```
+
+### Default model
+
+`yolov8n-cls.pt` is the default classification model.
+
+<br>
+
+-------------------
+
+<br>
+
+## Object detection using `RectangleLabels`
+
+YOLO models provide bounding box detection, also known as "object detection." 
+Label Studio supports this with the `RectangleLabels` control tag.
+
+YOLO OBB models are also supported.
+
+More info: https://docs.ultralytics.com/tasks/detect/
+
+https://github.com/user-attachments/assets/413b4650-422d-43dc-809d-51c08f0ad434
+
+
+### Labeling config
+
+```xml
+<View>
+  <Image name="image" value="$image"/>
+  <RectangleLabels name="label" toName="image" model_score_threshold="0.25" opacity="0.1">
+    <Label value="Person" background="red"/>
+    <Label value="Car" background="blue"/>
+  </RectangleLabels>
+</View>
+```
+
+### Parameters
+
+| Parameter               | Type   | Default | Description                                                                                                                                                                            |
+|-------------------------|--------|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `model_score_threshold` | float  | 0.5     | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. |
+| `model_path`            | string | None    | Path to the custom YOLO model. See more in the section "Custom YOLO Models."                                                                                                               |
+| `model_obb`             | bool   | False   | Enables Oriented Bounding Boxes (OBB) mode. Typically it uses `*-obb.pt` yolo models.                                                                                                  |
+
+For example:
+```xml
+<RectangleLabels name="label" toName="image" model_score_threshold="0.25" model_path="my_model.pt">
+```
+
+### Default model
+
+`yolov8m.pt` is the default object detection model.
+`yolov8n-obb.pt` is the default OBB object detection model.
+
+### Oriented Bounding Boxes (YOLO OBB)
+
+Oriented (rotated) bounding boxes will be generated automatically if you use an OBB model. 
+Specify `model_obb="true"` in the `RectangleLabels` tag to enable this mode:
+
+```xml
+<RectangleLabels name="label" toName="image" model_score_threshold="0.25" model_obb="true">
+```
+
+More info: https://docs.ultralytics.com/tasks/obb/
+
+<br>
+
+-------------------
+
+<br>
+
+## Segmentation using `PolygonLabels`
+
+YOLO models provide segmentation detection, also known as "instance segmentation." 
+Label Studio supports this with the `PolygonLabels` control tag.
+
+More info: https://docs.ultralytics.com/tasks/segment/
+
+![Yolo Polygons](./YoloPolygons.gif)
+
+https://github.com/user-attachments/assets/9b2447d3-392d-42be-bc7f-ef2b6c81d54c
+
+
+### Labeling config
+
+```xml
+<View>
+  <Image name="image" value="$image"/>
+  <PolygonLabels name="label" toName="image" model_score_threshold="0.25" opacity="0.1">
+    <Label value="Car" background="blue"/>
+    <Label value="Person" background="red"/>
+  </PolygonLabels>
+</View>
+```
+
+### Parameters
+
+| Parameter               | Type   | Default | Description                                                                                                                                                                            |
+|-------------------------|--------|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `model_score_threshold` | float  | 0.5     | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. |
+| `model_path`            | string | None    | Path to the custom YOLO model. See more in the section "Custom YOLO Models."                                                                                                               |
+
+For example:
+```xml
+<PolygonLabels name="label" toName="image" model_score_threshold="0.25" model_path="my_model.pt">
+```
+
+### Default model
+
+`yolov8n-seg.pt` is the default segmentation model.
+
+<br>
+
+-------------------
+
+<br>
+
+## Keypoint detection using `KeyPointLabels`
+
+YOLO models provide keypoint detection, also known as "pose estimation." 
+Label Studio supports this with the `KeyPointLabels` control tag.
+
+More info: [Ultralytics YOLO Keypoint Documentation](https://docs.ultralytics.com/tasks/pose/)
+
+![image](https://github.com/user-attachments/assets/72e32125-ba72-47b2-bc9d-a3269d199996)
+
+
+### Labeling config
+
+```xml
+<View>
+  <RectangleLabels name="keypoints_bbox" toName="image" model_skip="true">
+    <Label value="person"/>
+  </RectangleLabels>
+  
+  <KeyPointLabels name="keypoints" toName="image"
+    model_score_threshold="0.75" model_point_threshold="0.5" 
+    model_add_bboxes="true" model_point_size="1"
+    model_path="yolov8n-pose.pt"
+  >
+    <Label value="nose" predicted_values="person" model_index="1" background="red" />
+
+    <Label value="left_eye" predicted_values="person" model_index="2" background="yellow" />
+    <Label value="right_eye" predicted_values="person" model_index="3" background="yellow" />
+
+    <Label value="left_ear" predicted_values="person" model_index="4" background="purple" />
+    <Label value="right_ear" predicted_values="person" model_index="5" background="purple" />
+    
+    <View>
+      <Label value="left_shoulder" predicted_values="person" model_index="6" background="green" />
+      <Label value="left_elbow" predicted_values="person" model_index="8" background="green" />
+      <Label value="left_wrist" predicted_values="person" model_index="10" background="green" />
+
+      <Label value="right_shoulder" predicted_values="person" model_index="7" background="blue" />
+      <Label value="right_elbow" predicted_values="person" model_index="9" background="blue" />
+      <Label value="right_wrist" predicted_values="person" model_index="11" background="blue" />
+    </View>
+    
+    <View>
+      <Label value="left_hip" predicted_values="person" model_index="12" background="brown" />
+      <Label value="left_knee" predicted_values="person" model_index="14" background="brown" />
+      <Label value="left_ankle" predicted_values="person" model_index="16" background="brown" />
+
+      <Label value="right_hip" predicted_values="person" model_index="13" background="orange" />
+      <Label value="right_knee" predicted_values="person" model_index="15" background="orange" />
+      <Label value="right_ankle" predicted_values="person" model_index="17" background="orange" />
+    </View>
+  </KeyPointLabels>
+  
+  <Image name="image" value="$image" />
+</View>
+```
+
+### Parameters
+
+| Parameter               | Type   | Default | Description                                                                                                                                                                    |
+|-------------------------|--------|---------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `model_path`            | string | None    | Path to the custom YOLO model. See more in the section "Custom YOLO Models."                                                                                                       |
+| `model_score_threshold` | float  | 0.5     | Sets the minimum confidence threshold for bounding box detections. Keypoints that are related to the detected bbox with a confidence below this threshold will be disregarded. |
+| `model_point_threshold` | float  | 0.0     | Minimum confidence threshold for keypoints. Keypoints with confidence below this value will be ignored.                                                                        |
+| `model_add_bboxes`      | bool   | True    | Adds bounding boxes for detected keypoints. All keypoints will be grouped by parent bounding boxes on the region panel. See details in the tip below.                          |
+| `model_point_size`      | float  | 1       | Size of the keypoints in pixels. Just a visual parameter.                                                                                                                      |
+| `model_index`           | int    | None    | Index of the keypoint in the YOLO model output. It's used in `Label` tags only to build mapping between a Label and an output point.                                           |
+
+For example:
+
+```xml
+<KeyPointLabels name="keypoints" toName="image"
+                model_path="yolov8n-pose.pt"
+                model_score_threshold="0.25" model_point_threshold="0.5" 
+                model_add_bboxes="true" model_point_size="2">
+```
+
+### Default model
+
+`yolov8n-pose.pt` is the default keypoint detection model.
+
+### Grouping keypoints with bounding boxes
+
+When using keypoint detection, the ML backend groups keypoints by the bounding box (bbox) associated with each detected person or object. 
+You will see the grouping under the **Regions** panel on the right side of Label Studio. Note that you can drag and drop region items as necessary.
+
+The bounding boxes are added to the prediction results by default. You can enable or disable this behavior by setting `model_add_bboxes`:
+
+```xml
+<KeyPointLabels name="keypoints" toName="image" model_add_bboxes="false">
+```
+
+<details><summary>Tip: How to only keep keypoints and discard bounding boxes?</summary>
+
+To enable both keypoint detection and bounding box detection in the same task, you have to 
+1. set `model_add_bboxes="false"` in the `KeyPointLabels` tag,
+2. remove `RectangleLabels` tag.
+
+You can use this labeling configuration to get rid of bounding boxes and keep only keypoints:
+
+```xml
+<View>
+  <KeyPointLabels name="keypoints" toName="image"
+    model_score_threshold="0.75" model_point_threshold="0.5" 
+    model_path="yolov8n-pose.pt" model_point_size="1"
+    model_add_bboxes="false"              
+  >
+    <Label value="nose" predicted_values="person" model_index="1" background="red" />
+
+    <Label value="left_eye" predicted_values="person" model_index="2" background="yellow" />
+    <Label value="right_eye" predicted_values="person" model_index="3" background="yellow" />
+
+    <Label value="left_ear" predicted_values="person" model_index="4" background="purple" />
+    <Label value="right_ear" predicted_values="person" model_index="5" background="purple" />
+    
+    <View>
+      <Label value="left_shoulder" predicted_values="person" model_index="6" background="green" />
+      <Label value="left_elbow" predicted_values="person" model_index="8" background="green" />
+      <Label value="left_wrist" predicted_values="person" model_index="10" background="green" />
+
+      <Label value="right_shoulder" predicted_values="person" model_index="7" background="blue" />
+      <Label value="right_elbow" predicted_values="person" model_index="9" background="blue" />
+      <Label value="right_wrist" predicted_values="person" model_index="11" background="blue" />
+    </View>
+    
+    <View>
+      <Label value="left_hip" predicted_values="person" model_index="12" background="brown" />
+      <Label value="left_knee" predicted_values="person" model_index="14" background="brown" />
+      <Label value="left_ankle" predicted_values="person" model_index="16" background="brown" />
+
+      <Label value="right_hip" predicted_values="person" model_index="13" background="orange" />
+      <Label value="right_knee" predicted_values="person" model_index="15" background="orange" />
+      <Label value="right_ankle" predicted_values="person" model_index="17" background="orange" />
+    </View>
+  </KeyPointLabels>
+  <Image name="image" value="$image" />
+</View>
+```
+
+</details>
+
+### Point mapping
+
+For precise control, you can map keypoints to specific labels in your Label Studio configuration. 
+Each keypoint can be associated with a specific part of a person or object, 
+and you can define this mapping using the `model_index` and `predicted_values` attributes.
+
+```xml
+<Label value="left_eye" predicted_values="person" model_index="2" />
+<Label value="right_eye" predicted_values="person" model_index="3" />
+```
+
+This configuration ensures that the keypoints detected by the YOLO model are correctly labeled in the Label Studio interface.
+For pose detection models, the `model_index` attribute is used to map keypoints to specific parts of the body according to the YOLO model output:
+
+```
+0: Nose 1: Left Eye 2: Right Eye 3: Left Ear 4: Right Ear 
+5: Left Shoulder 6: Right Shoulder 7: Left Elbow 8: Right Elbow 9: Left Wrist 10: Right Wrist 
+11: Left Hip 12: Right Hip 13: Left Knee 14: Right Knee 15: Left Ankle 16: Right Ankle
+```
+
+### Recommendations
+
+- **Bounding Box Visualization**: Use the `model_add_bboxes` parameter to visualize the bounding box containing the keypoints. This is especially useful when dealing with multiple detected persons or objects.
+- **Threshold Adjustment**: Adjust the `model_score_threshold` and `model_point_threshold` parameters based on your dataset and the confidence level required for accurate keypoint detection.
+
+<br>
+
+-------------------
+
+<br>
+
+## Video object tracking using `VideoRectangle` 
+
+YOLO models provide object tracking, also known as "multi-object tracking."
+Label Studio supports this with the `VideoRectangle` + `Labels` control tags.
+
+More info: https://docs.ultralytics.com/modes/track/
+
+![Video Object Tracking](./YoloVideo.gif)
+
+
+https://github.com/user-attachments/assets/7b0d50e6-164a-4d66-87cf-df443b77f638
+
+
+
+### Labeling config
+
+```xml
+<View>
+    <Video name="video" value="$video"/>
+    <VideoRectangle name="box" toName="video" model_tracker="botsort" model_conf="0.25" model_iou="0.7" />
+    <Labels name="label" toName="video">
+      <Label value="Person" background="red"/>
+      <Label value="Car" background="blue"/>
+    </Labels>
+</View>
+```
+
+### Trackers
+
+https://docs.ultralytics.com/modes/track/?h=track#tracker-selection
+
+The best tracker to use with Ultralytics YOLO depends on your specific needs.
+
+
+The default tracker is [BoT-SORT](https://github.com/NirAharon/BoT-SORT), which is generally well-suited for most scenarios. 
+
+However, if you're looking for an alternative with different strengths, 
+[ByteTrack](https://github.com/ifzhang/ByteTrack) is another good choice that you can easily configure. 
+ByteTrack is known for its high performance in multi-object tracking, 
+especially in situations with varying object appearances and reappearances. 
+
+Both trackers can be customized using YAML configuration files to fit your specific use cases.
+
+You can specify the tracker in the control tag: 
+* `<VideoRectangle model_tracker="botsort">`
+* `<VideoRectangle model_tracker="bytetrack">`
+
+### Parameters for bounding boxes
+
+The tracker works with the object detection model (bounding boxes). 
+
+The first step is to detect bounding boxes, the second step is to track them (find the same boxes among frames). 
+These parameters are related to the first step - bounding box detection.
+
+Read more about these parameters: 
+https://docs.ultralytics.com/modes/track/?h=track#tracking-arguments
+
+| Parameter       | Type   | Default   | Description                                                                                                                                                                            |
+|-----------------|--------|-----------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `model_conf`    | float  | 0.25      | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. |
+| `model_iou`     | float  | 0.7       | Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Lower values result in fewer detections by eliminating overlapping boxes, useful for reducing duplicates.   |
+| `model_tracker` | string | `botsort` | Sets the tracker to use for multi-object tracking. Options include `botsort`, `bytetrack`, or a custom YAML file.                                                                      |
+| `model_path`    | string | None      | Path to the custom YOLO model. See more in the section "Custom YOLO Models."                                                                                                               |
+
+For example: 
+```xml
+<VideoRectangle name="label" toName="video" model_tracker="botsort" model_conf="0.25" model_iou="0.7" />  
+```
+
+### Parameters for trackers 
+
+For an example of tracker parameters, see https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers. 
+
+The main parameter is `model_tracker` which can be set to 
+* `botsort` 
+* `bytetrack`
+* Or the name of any custom yaml file that you place into `models` directory (do not include the file extension `.yaml` when setting this parameter).  
+
+As long as they are available within the yaml file, you can specify tracker parameters directly from the labeling config. All parameters should be prefixed with `botsort_` or `bytetrack_`.
+
+For example: 
+```xml
+<VideoRectangle 
+    name="label" toName="video" 
+    model_tracker="botsort" 
+    botsort_track_low_thresh="0.1" botsort_track_high_thresh="0.2" 
+/>  
+```
+
+### Default model
+
+`yolov8n.pt` is the default object detection model. 
+
+### Recommendations
+
+* Video object tracking is a computationally intensive task. 
+Small models like `yolov8n.pt` are recommended for real-time tracking, however, they may not be as accurate as larger models.
+
+* Label Studio has timeout limits for ML backend requests. You can adjust the timeout in the Label Studio backend settings.
+
+<!-- TODO: https://github.com/HumanSignal/label-studio/pull/5414/files#diff-20432d8093df2c0400b0f41b004a6b772b856b985fa1f5fd1e1f909247c89fc6L30 -->
+
+* Or use the [CLI tool](#When-to-use-the-CLI) to run predictions asynchronously.
+
+<br>
+
+-------------------
+
+<br>
+
+## Run the YOLO ML backend
+
+
+### Running with Docker (recommended)
+
+1. Start the Machine Learning backend on `http://localhost:9090` with the prebuilt image:
+
+    ```bash
+    docker-compose up
+    ```
+
+2. Validate that the backend is running
+
+    ```bash
+    $ curl http://localhost:9090/
+    {"status":"UP"}
+    ```
+
+3. Create a project in Label Studio. Then from the **Model** page in the project settings, [connect the model](https://labelstud.io/guide/ml#Connect-the-model-to-Label-Studio). The default URL is `http://localhost:9090`.
+
+### Building from source (advanced)
+
+To build the ML backend from source, you have to clone the repository and build the Docker image:
+
+```bash
+docker-compose build
+```
+
+### Running without Docker (advanced)
+
+To run the ML backend without Docker, you have to clone the repository and install all dependencies using pip:
+
+```bash
+python -m venv ml-backend
+source ml-backend/bin/activate
+pip install -r requirements-base.txt
+pip install -r requirements.txt
+```
+
+Then you can start the ML backend:
+
+```bash
+label-studio-ml start ./dir_with_your_model
+```
+
+Also, you can check [Dockerfile](Dockerfile) for additional dependencies and install them manually. 
+
+### Parameters
+
+Check the `environment` section in the [`docker-compose.yml`](docker-compose.yml) file before running the container. 
+All available parameters are listed there.
+
+> Note: You can use lots of YOLO model parameters in labeling configurations directly, e.g. `model_path` or `model_score_threshold`.
+
+## Command line interface for the terminal
+
+### Overview
+
+This Command Line Interface (CLI) tool facilitates the integration of YOLO models with Label Studio for machine learning predictions. 
+It provides an alternative method for running YOLO predictions on tasks managed by Label Studio, 
+particularly useful for processing long videos or large datasets. 
+
+Running the model predictions directly from the CLI helps to avoid issues 
+like connection timeouts between Label Studio and the ML backend, 
+which can occur during lengthy processing times.
+
+### When to use the CLI
+
+When working with extensive media files such as long videos, processing times can be significant. 
+Label Studio may interrupt the connection with the ML backend if the request takes too long, resulting in incomplete predictions. 
+
+By running this CLI tool, you can execute model predictions asynchronously 
+without the need for Label Studio to maintain a constant connection to the backend. 
+This ensures that even large or complex tasks are processed fully, 
+and predictions are saved to Label Studio using SDK once completed.
+
+### How it works
+
+1. **Label Studio Connection**: The tool connects to a running instance of Label Studio using the provided API key and URL.
+2. **Task Preparation**: Tasks can be provided directly via a JSON file or as a list of task IDs. The tool fetches task data from Label Studio if task IDs are supplied.
+3. **Model Loading**: The YOLO model is loaded and initialized based on the project’s configuration.
+4. **Prediction Process**: For each task, the YOLO model generates predictions, which are then post-processed to Label Studio's expected format.
+5. **Asynchronous Upload**: The generated predictions are uploaded back to Label Studio, allowing for large tasks to be processed without timing out.
+
+### Usage
+
+```bash
+python cli.py --ls-url http://localhost:8080 --ls-api-key your_api_key --project 1 --tasks tasks.json
+```
+
+or 
+
+```bash
+python cli.py --ls-url http://localhost:8080 --ls-api-key YOUR_API_KEY --project 1 --tasks 1,2,3
+```
+
+### Parameters
+
+- **`--ls-url`**: The URL of the Label Studio instance. Defaults to `http://localhost:8080`.
+- **`--ls-api-key`**: The API key for Label Studio. Used to authenticate the connection.
+- **`--project`**: The ID of the Label Studio project where the tasks are managed. Defaults to `1`.
+- **`--tasks`**:
+
+  1. The path to a JSON file containing a list of tasks or task IDs, e.g.:
+
+    tasks_ids.json 
+    ```json
+    [1,2,3]
+    ```
+  
+    tasks.json
+    ```json
+    [{"id": 1, "data": {"image": "https://example.com/1.jpg"}}, {"id": 2, "data": {"image": "https://example.com/2.jpg"}}]
+    ```
+  
+  2. If a file is not provided, you can pass a comma-separated list of task IDs directly, e.g.: `1,2,3`
+
+### Logging
+
+Use `LOG_LEVEL=DEBUG` to get detailed logs. Example:
+
+```bash
+LOG_LEVEL=DEBUG python cli.py --ls-url http://localhost:8080 --ls-api-key YOUR_API_KEY --project 2 --tasks 1,2,3
+```
+
+## For developers
+
+The architecture of the project and development guidelines are described in the [README_DEVELOP.md](README_DEVELOP.md) file.
\ No newline at end of file