From a0bbc8d2b66e95d5b83df1140d2819df6d8e65b0 Mon Sep 17 00:00:00 2001 From: makseq-ubnt Date: Sat, 7 Sep 2024 01:56:08 +0100 Subject: [PATCH] Fixes --- docs/source/guide/ml_tutorials.html | 370 ++++++++++++++-------------- scripts/update_ml_tutorials.py | 2 +- 2 files changed, 186 insertions(+), 186 deletions(-) diff --git a/docs/source/guide/ml_tutorials.html b/docs/source/guide/ml_tutorials.html index 216cffe9c040..a3dd1c1445e0 100644 --- a/docs/source/guide/ml_tutorials.html +++ b/docs/source/guide/ml_tutorials.html @@ -1,53 +1,51 @@ --- cards: - categories: - - Generative AI - - Large Language Model - - Text Generation + - Natural Language Processing + - Text Classification + - BERT - Hugging Face 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/bert.png + meta_description: Tutorial on how to use BERT-based text classification with your + Label Studio project + meta_title: BERT-based text classification + order: 35 tier: all - title: Hugging Face Large Language Model (LLM) + title: Classify text with a BERT model type: guide - url: /tutorials/huggingface_llm.html + url: /tutorials/bert_classifier.html - categories: - Computer Vision - - Video Annotation - - Object Detection - - Segment Anything Model + - Optical Character Recognition + - EasyOCR hide_frontmatter_title: true hide_menu: true - image: /tutorials/sam2-video.png - meta_title: Using SAM2 with Label Studio for Video Annotation - order: 15 + 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: SAM2 with Videos + title: Transcribe text from images with EasyOCR type: guide - url: /tutorials/segment_anything_2_video.html + url: /tutorials/easyocr.html - categories: - - Audio/Speech Processing - - Automatic Speech Recognition - - NeMo - - NVidia + - Natural Language Processing + - Named Entity Recognition + - Flair 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/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: Automatic Speech Recognition with NVidia NeMo + title: NER labeling with Flair type: guide - url: /tutorials/nemo_asr.html + url: /tutorials/flair.html - categories: - Natural Language Processing - Named Entity Recognition @@ -66,95 +64,59 @@ type: guide url: /tutorials/gliner.html - categories: - - Natural Language Processing - - Text Classification - - BERT - - Hugging Face + - Computer Vision + - Image Annotation + - Object Detection + - Grounding DINO hide_frontmatter_title: true hide_menu: true - image: /tutorials/bert.png - meta_description: Tutorial on how to use BERT-based text classification with your - Label Studio project - meta_title: BERT-based text classification - order: 35 + 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: Classify text with a BERT model + title: Zero-shot object detection and image segmentation with Grounding DINO type: guide - url: /tutorials/bert_classifier.html + url: /tutorials/grounding_dino.html - categories: - Computer Vision - Image Annotation - Object Detection + - Zero-shot Image Segmentation + - Grounding DINO - Segment Anything Model hide_frontmatter_title: true hide_menu: true - image: /tutorials/sam2-images.png - meta_title: Using SAM2 with Label Studio for Image Annotation + 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: SAM2 with Images + title: Zero-shot object detection and image segmentation with Grounding DINO and + SAM type: guide - url: /tutorials/segment_anything_2_image.html + url: /tutorials/grounding_sam.html - categories: - Generative AI - Large Language Model - - OpenAI - - Azure - - Ollama - - ChatGPT - 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 - tier: all - title: Interactive LLM labeling with GPT - type: guide - url: /tutorials/llm_interactive.html -- categories: - - Natural Language Processing - - Named Entity Recognition - - SpaCy - 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 - tier: all - title: spaCy models for NER - type: guide - url: /tutorials/spacy.html -- categories: - - Natural Language Processing - - Named Entity Recognition - - Flair - 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 - tier: all - title: NER labeling with Flair - type: guide - url: /tutorials/flair.html -- categories: - - Computer Vision - - Large Language Model - - WatsonX + - Text Generation + - Hugging Face hide_frontmatter_title: true hide_menu: true - image: /tutorials/watsonx.png - meta_title: Integrate WatsonX with Label Studio - order: 15 + 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: Integrate WatsonX with Label Studio + title: Hugging Face Large Language Model (LLM) type: guide - url: /tutorials/watsonx_llm.html + url: /tutorials/huggingface_llm.html - categories: - Natural Language Processing - Named Entity Recognition @@ -171,35 +133,55 @@ type: guide url: /tutorials/huggingface_ner.html - categories: - - Computer Vision - - Optical Character Recognition - - Tesseract + - Natural Language Processing + - Named Entity Recognition + - Interactive matching 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/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: Interactive bounding boxes OCR with Tesseract + title: Interactive substring matching for NER tasks type: guide - url: /tutorials/tesseract.html + url: /tutorials/interactive_substring_matching.html - categories: - - Natural Language Processing - - Text Classification - - Scikit-learn + - Generative AI + - Retrieval Augmented Generation + - Google + - OpenAI + - Langchain 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/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: Sklearn Text Classifier model + title: RAG with a Langchain search agent type: guide - url: /tutorials/sklearn_text_classifier.html + url: /tutorials/langchain_search_agent.html +- categories: + - Generative AI + - Large Language Model + - OpenAI + - Azure + - Ollama + - ChatGPT + 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 + tier: all + title: Interactive LLM labeling with GPT + type: guide + url: /tutorials/llm_interactive.html - categories: - Computer Vision - Object Detection @@ -218,73 +200,49 @@ type: guide url: /tutorials/mmdetection-3.html - categories: - - Computer Vision - - Image Annotation - - Object Detection - - Grounding DINO + - Audio/Speech Processing + - Automatic Speech Recognition + - NeMo + - NVidia 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 + 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: Zero-shot object detection and image segmentation with Grounding DINO + title: Automatic Speech Recognition with NVidia NeMo type: guide - url: /tutorials/grounding_dino.html + url: /tutorials/nemo_asr.html - categories: - Computer Vision - Image Annotation - Object Detection - - Zero-shot Image Segmentation - - Grounding DINO - Segment Anything Model 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 + image: /tutorials/sam2-images.png + meta_title: Using SAM2 with Label Studio for Image Annotation order: 15 tier: all - title: Zero-shot object detection and image segmentation with Grounding DINO and - SAM + title: SAM2 with Images type: guide - url: /tutorials/grounding_sam.html + url: /tutorials/segment_anything_2_image.html - categories: - Computer Vision + - Video Annotation - Object Detection - - Image Segmentation - - YOLO - hide_frontmatter_title: true - hide_menu: true - 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: YOLO ML Backend for Label Studio - type: guide - url: /tutorials/yolo.html -- categories: - - Computer Vision - - Optical Character Recognition - - EasyOCR + - Segment Anything Model 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/sam2-video.png + meta_title: Using SAM2 with Label Studio for Video Annotation + order: 15 tier: all - title: Transcribe text from images with EasyOCR + title: SAM2 with Videos type: guide - url: /tutorials/easyocr.html + url: /tutorials/segment_anything_2_video.html - categories: - Computer Vision - Object Detection @@ -304,37 +262,79 @@ type: guide url: /tutorials/segment_anything_model.html - categories: - - Generative AI - - Retrieval Augmented Generation - - Google - - OpenAI - - Langchain + - Natural Language Processing + - Text Classification + - Scikit-learn 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/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: RAG with a Langchain search agent + title: Sklearn Text Classifier model type: guide - url: /tutorials/langchain_search_agent.html + url: /tutorials/sklearn_text_classifier.html - categories: - Natural Language Processing - Named Entity Recognition - - Interactive matching + - SpaCy 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/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: Interactive substring matching for NER tasks + title: spaCy models for NER type: guide - url: /tutorials/interactive_substring_matching.html + url: /tutorials/spacy.html +- categories: + - Computer Vision + - Optical Character Recognition + - Tesseract + 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 + tier: all + title: Interactive bounding boxes OCR with Tesseract + type: guide + url: /tutorials/tesseract.html +- categories: + - Computer Vision + - Large Language Model + - WatsonX + hide_frontmatter_title: true + hide_menu: true + image: /tutorials/watsonx.png + meta_title: Integrate WatsonX with Label Studio + order: 15 + tier: all + title: Integrate WatsonX with Label Studio + type: guide + url: /tutorials/watsonx_llm.html +- categories: + - Computer Vision + - Object Detection + - Image Segmentation + - YOLO + hide_frontmatter_title: true + hide_menu: true + 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: YOLO ML Backend for Label Studio + type: guide + 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/scripts/update_ml_tutorials.py b/scripts/update_ml_tutorials.py index 721608442071..f15c51da5310 100644 --- a/scripts/update_ml_tutorials.py +++ b/scripts/update_ml_tutorials.py @@ -36,7 +36,7 @@ def get_readme_files() -> List: p = Path(ML_REPO_PATH) / 'label_studio_ml' / 'examples' - return list(Path(p).rglob('README.md')) + return sorted(list(Path(p).rglob('README.md'))) def parse_readme_file(file_path: str) -> dict: