Ango Hub Docs
Open Ango HubContact iMerit
  • Ango Hub Documentation
  • Video Guides
  • Changelog
  • FAQs & Troubleshooting
  • All Keyboard and Mouse Shortcuts
  • Core Concepts
    • Assets
    • Attachments
    • Batches
    • Benchmarks
    • Category Schema (Ontologies)
    • Frame Interpolation
    • Geofencing
    • Idle Time Detection & Time Tracking
    • Instructions
    • Issues
      • Issue Error Codes
    • Label Validation
    • Labeler Performance
    • Labeling
    • Labeling Queue
    • Multiple Classification
    • Notifications
    • Organizations
    • Projects
    • Requeuing
    • Reviewing
    • Review Queue
    • Skipping
    • Stage History
    • Tasks
    • Usage
    • User Roles
    • Workflow
      • Complete
      • Consensus
      • Hold
      • Label
      • Logic
      • Plugin
      • Review
      • Start
      • Webhook
  • Labeling
    • Managing Users in Projects
      • Profile Page
    • Managing the Project Ontology
    • Labeling Editor Interface
      • Audio Labeling Editor
      • Image Labeling Editor
      • Video Labeling Editor
      • DICOM Labeling Editor
      • Medical Labeling Editor
        • 3D Bounding Box
        • Fill Between Slices
        • Island Tools
        • Line (Tape Measure)
        • Smoothing
      • PDF Labeling Editor
      • Text (NER) Labeling Editor
      • LLM Chat Labeling Editor
      • Markdown Labeling Editor
      • 3D Multi-Sensor Fusion Labeling Editor
    • Labeling Classes
      • Tools
        • Bounding Box
        • Brush
        • Entity
        • Message
        • Nested Classifications
        • PCT
        • PDF Tool
        • Point
        • Polygon
        • Polyline
        • Rotated Bounding Box
        • Segmentation
        • Spline
        • Voxel Brush
      • Classification
        • Checkbox
        • Multiple Dropdown
        • Radio
        • Rank
        • Single Dropdown
        • Text
        • Tree Dropdown Tools (Single and Multiple Selection)
      • Relation
        • Single Relation
        • Group Relation
    • Magnetic Lasso
    • Performance & Compatibility Considerations
  • Data
    • Data in Ango Hub
      • Embedding Private Bucket Files in MD Assets
    • Importing Assets
      • Asset Builder
      • Bundled Assets
        • Importing Multiple Images as One Multi-Page Asset
        • Importing Multiple Single-Frame DICOM Files as One Multi-Page Asset
        • Importing multiple DICOM files to be annotated and displayed at once
        • Importing Multiple Single-Frame DICOM Files as a DICOM Series
        • Importing Multiple Markdown Files as One Multi-Page Asset
      • File Explorer
      • Supported Asset File Types & Codecs
      • Importing Cloud (Remote) Assets
      • Importing From Local Machine
      • Creating and Importing LLM Chat Assets
      • Importing Data in the 3D Multi-Sensor Fusion Labeling Tool
      • Bulk Importing Markdown/HTML Assets
      • Importing Attachments during Asset Import
      • Importing Annotations during Asset Import
      • contextData: Adding Extra Data to Assets
      • Importing Reference Images as Overlay
      • Importing Reference Medical Data During Asset Import
    • Importing and Exporting Annotations
      • Importing Annotations
        • Ango Import Format
        • Importing Brush Traces
        • Importing NRRD Annotations
      • Exporting Annotations
        • Ango Export Format
          • Asset
            • Task
              • Tools
              • Classifications
              • Relations
          • Stage History
    • Adding and Managing LLMs
    • Storages
      • Set up a storage integration with Azure
      • Set up a storage integration with AWS S3
      • Set up a storage integration with MinIO and S3-compatible custom storage services
      • Set up a storage integration with GCP (Google Cloud Platform)
      • Set up CORS
      • Validating Storage Integrations
    • Purging Data from Ango Hub
  • Plugins
    • Overview of Plugins in Ango Hub
      • Installing Plugins
      • Plugin Setting Presets
      • Monitoring Plugin Progress
    • First-Party Plugins
      • Ango Export Converter Plugins
      • Asset Converter Plugins
      • Ango to Mask Converter
      • Batch Assignment
      • ChatGPT
      • Column-Agnostic Markdown Generator
      • CSV Export for Classification
      • DALL-E
      • DALL-E (Model Plugin)
      • File Explorer Plugin
      • General Object Detector
      • General Object Segmenter
      • Markdown Generator
      • One-Click Segmentation
      • Open World Object Detection
      • Optical Character Recognition
      • TPT Export
      • YOLO | Instance Segmentation
      • YOLO | Pose Estimation
      • YOLO | Object Detection
      • YOLO | Image Classification
    • Plugin Developer Documentation
      • Export Plugins
      • Batch Model Plugins
      • Model Plugins
      • File Explorer Plugins
      • Markdown Generator Plugins
      • Plugin Logger
      • [WIP] Deploying your Plugin
      • Plugin 'Host' Information
  • SDK
    • SDK Documentation
      • Project Level SDK Functions
        • add_members_to_project
        • assign_batches
        • assign_task
        • create_attachment
        • create_batch
        • create_issue
        • create_label_set
        • create_project
        • delete_issue
        • export
        • exportV3
        • get_assets
        • get_batches
        • get_issues
        • get_metrics
        • get_project
        • get_project_performance
        • get_task
        • get_tasks
        • get_task_history
        • import_labels
        • list_projects
        • requeue_tasks
        • rerun_webhook
        • update_workflow_stages
        • upload_files
        • upload_files_cloud
        • upload_files_with_asset_builder
        • upload_chat_assets
      • Organization Level SDK Functions
        • create_storage
        • delete_organization_invites
        • delete_organization_members
        • delete_storage
        • get_organization_invites
        • get_organization_members
        • get_storages
        • invite_members_to_org
        • update_organization_members_role
    • SDK - Useful Snippets
    • SDK Changelog
  • API
    • API Documentation
  • How-To
    • Add Members
      • Add multiple users to a project
    • Annotate
      • Annotate 3D Point Cloud Files on Ango Hub
      • Perform targeted OCR on images
    • Export Data
      • Automatically send Ango Hub Webhook contents to Google Sheets, Email, Slack, and more with Zapier
      • Download a JSON of your project ontology
      • Download DICOM Segmentation Masks
      • Download your annotations in the COCO, KITTI, or YOLO format
      • Download your Segmentation Masks
      • Get your export as separate JSON files for each asset
    • Manage a Project
      • Get your API Key
      • Get your Organization ID
      • Mute your notifications
      • Open an asset provided the Asset ID
      • Pre-label assets
      • Share a filtered view of the Tasks table with others
      • Transfer project ontologies between projects
      • Transfer project workflows between projects
    • Perform Model Evaluation on Ango Hub
  • Troubleshooting
    • I get a "0 Tasks Labeled" alert when trying to pre-label tasks
    • I get a 'The data couldn't be loaded properly' error when opening certain assets
    • I get a "Unknown Classification" warning when opening a task
  • Feature Availability Status for projects of the 3D Multi-Sensor Fusion type
  • Comparison between QuickServe and Ango Hub
  • Changes from Ango Hub Legacy
  • Video V2 Breaking Changes and Transition
  • Data Access, Storage, and Security
  • Two-Factor Authentication
  • Single Sign-On (SSO) Support
  • Customer Support
  • Ango Hub Status Page
Powered by GitBook
On this page
  • How to add a Rank tool to your project
  • Populating Ranking Options
  • Automatic Ordering
  • Manual Ordering
  1. Labeling
  2. Labeling Classes
  3. Classification

Rank

Tool to rank different options in Ango Hub. Ideal for RLHF projects.

PreviousRadioNextSingle Dropdown

Last updated 9 months ago

The Rank tool allows you to have annotators rank different options. These options may include text, images, videos, or any custom HTML.

This tool is often used in RLHF (Reinforced Learning from Human Feedback) projects, where multiple LLM answers need to be ranked and/or rated.

How to add a Rank tool to your project

From your project's Settings tab, enter the Category Schema section. Click on Add Category, then click on Rank. This will add a Rank tool to your project.

By itself, this will not populate ranking options – it will only display to users the option titles. For example, if, in the project set up in the GIF above, we were to upload an asset normally, without including context data, the rank tool would appear this way:

Populating Ranking Options

Automatic Ordering

[
  {
    "externalId": "your-asset-external-id",
    "data": "What are the main features of the Python programming language?",
    "contextData": {
      "responses": [
        "Python is renowned for its simplicity and readability, which make it an excellent choice for beginners. It supports multiple programming paradigms, including procedural, object-oriented, and functional programming.",
        "Python has a vast ecosystem of libraries and frameworks, such as NumPy for numerical calculations, Pandas for data manipulation, and Django for web development, making it versatile for various applications.",
        "Python is an interpreted language, which means that it is executed line-by-line which can simplify debugging and testing. It also seamlessly integrates with other languages, allowing for more flexibility in software development."
      ]
    }
  },
  { ... }
]

The value of data may be plain text, any HTML, or a URL to a file.

The values in the responses array may be plain text or any HTML.

When a JSON is imported this way, Ango Hub will make the assumption that the ranking options are presented in order. So for example, if, in your category schema, you have created three ranking options "Response 1", "Response 2", and "Response 3", Ango Hub will assume that in the responses list, the first item is "Response 1", the second "Response 2", and so on.

Manual Ordering

If the responses in the JSON are not ordered, or you wish to maintain one order in the JSON and another order on Ango Hub, you may alternatively import the JSON with the following format:

{
    "externalId": "Test Ranking Asset 2",
    "data": "What are the main features of the Python programming language?",
    "contextData": {
      "responses": [
        {
          "id": "Response 1",
          "label": "Python is renowned for its simplicity and readability, which make it an excellent choice for beginners. It supports multiple programming paradigms, including procedural, object-oriented, and functional programming."
        },
        {
          "id": "Response 2",
          "label": "Python has a vast ecosystem of libraries and frameworks, such as NumPy for numerical calculations, Pandas for data manipulation, and Django for web development, making it versatile for various applications."
        }
      ]
    }
  }

Where id is the name of the option as created in the Category Schema section of the project settings, and label is the content of the ranking option.

Once ranking options are populated, they will display the following way:

To include text, or any HTML in the ranking options itself, please follow the instructions in the section below.

To enrich ranking options to include content of any HTML-supported type, you must upload your asset using the option and by including in the format below:

JSON Import
contextData
Populating Ranking Options