Claude

Overview

The Claude Plugin enables seamless integration of Anthropic's language and multimodal models into your annotation workflows on Ango Hub. This plugin is designed to support a wide range of use cases, including text processing, image understanding, and named entity recognition (NER).

Claude

Plugin Functionality

The Claude Plugin processes assets and generates outputs based on the selected mode, model, and prompt configuration.

• Text Processing: Generate summaries, classifications, structured outputs, or rewritten content from text inputs.

• Image Understanding: Analyze visual content and generate descriptions, extract text (OCR-style), or answer questions about images.

• Named Entity Recognition (NER): Identify and extract structured entities such as names, organizations, locations, and dates from text.

Prompt Construction

The plugin dynamically constructs the final prompt using:

[prompt_prefix] + [input content] + [prompt_suffix]

• prompt_prefix defines the task or instruction

• Input content comes from the asset or annotation

• prompt_suffix refines output format or constraints

This flexible structure allows you to standardize instructions across all assets.

Supported Modes

Workflow-1: Text Processing (Asset)

{
  "mode": "text-prompt",
  "model_name": "claude-sonnet-4-6",
  "anthropic_api_key": "<YOUR_ANTHROPIC_API_KEY>",
  "prompt_prefix": "Summarize the following text in one sentence: ",
  "prompt_suffix": ""
}

Category Schema

{
  "tools": [],
  "classifications": [
    {
      "schemaId": "746971b8c6130e3e67aa164",
      "tool": "text",
      "title": "Summary",
      "required": false,
      "classifications": [],
      "multiple": false,
      "options": [],
      "shortcutKey": "1",
      "frameSpecific": false,
      "richText": false,
      "katex": false,
      "katexBottom": true,
      "regex": ""
    }
  ],
  "relations": []
}

Workflow-2: Text Processing (Text Tool)

{
  "mode": "text-prompt",
  "model_name": "claude-sonnet-4-6",
  "anthropic_api_key": "<YOUR_ANTHROPIC_API_KEY>",
  "prompt_prefix": "What is the capital of ",
  "prompt_suffix": "? Provide only the city name."
}

Category Schema

{
  "tools": [],
  "classifications": [
    {
      "schemaId": "0dbcd5baf0e3bdd94a43241",
      "tool": "text",
      "title": "Input Prompt",
      "required": false,
      "classifications": [],
      "multiple": false,
      "options": [],
      "shortcutKey": "1",
      "frameSpecific": false,
      "richText": false,
      "katex": false,
      "katexBottom": true,
      "regex": ""
    },
    {
      "schemaId": "cfa74f8424770119a0cd684",
      "tool": "text",
      "title": "Response",
      "required": false,
      "classifications": [],
      "multiple": false,
      "options": [],
      "shortcutKey": "2",
      "frameSpecific": false,
      "richText": false,
      "katex": false,
      "katexBottom": true,
      "regex": ""
    }
  ],
  "relations": []
}

Workflow-3: Image Understanding

{
  "mode": "image-prompt",
  "model_name": "claude-sonnet-4-6",
  "anthropic_api_key": "<YOUR_ANTHROPIC_API_KEY>",
  "prompt_prefix": "Describe this image in detail, including objects, colors, and environment.",
  "prompt_suffix": ""
}

Category Schema

{
  "tools": [],
  "classifications": [
    {
      "schemaId": "48ad366ed63db5859587335",
      "tool": "text",
      "title": "Response",
      "required": false,
      "classifications": [],
      "multiple": false,
      "options": [],
      "shortcutKey": "1",
      "frameSpecific": false,
      "richText": false,
      "katex": false,
      "katexBottom": true,
      "regex": ""
    }
  ],
  "relations": []
}

Workflow-4: Named Entity Recognition

{
  "mode": "ner",
  "model_name": "claude-sonnet-4-6",
  "anthropic_api_key": "<YOUR_ANTHROPIC_API_KEY>",
  "prompt_prefix": "",
  "prompt_suffix": ""
}

In the "ner" mode, class mapping is not required. The plugin automatically assigns entity labels based on the project's category schema, so no manual mapping configuration is needed.

Category Schema

{
  "tools": [
    {
      "schemaId": "796d1292cfbf6229e793571",
      "tool": "ner",
      "title": "Adjective",
      "required": false,
      "classifications": [],
      "multiple": false,
      "color": "#f44336",
      "shortcutKey": "1"
    },
    {
      "schemaId": "fd74cf3157e7805f080f405",
      "tool": "ner",
      "title": "Verb",
      "required": false,
      "classifications": [],
      "multiple": false,
      "color": "#03a9f4",
      "shortcutKey": "2"
    },
    {
      "schemaId": "c956228f2b8e2effebac917",
      "tool": "ner",
      "title": "Noun",
      "required": false,
      "classifications": [],
      "multiple": false,
      "color": "#9c27b0",
      "shortcutKey": "3"
    }
  ],
  "classifications": [],
  "relations": []
}

Supported Data Types

• Image (image-prompt)

• Text (NER, text-prompt+asset source)

• Any Data Type (text-prompt+text annotation source)

Supported Annotation Tools

• Text

• Entity

• Radio

• Checkbox

• Single-Select Dropdown

• Multi-Select Dropdown

Plugin Configuration

The Overwrite setting in model plugins controls whether existing annotations are replaced or kept. When enabled, the plugin replaces all existing annotations with new model predictions; when disabled, it simply adds the new results without deleting what’s already there.

In the class mapping, the Claude plugin uses two fields: “Prompt Body” and “Reply Text”.

• Prompt Body refers to the text tool from which the main content of the prompt is retrieved.

• Reply Text refers to the text tool where the Claude response will be written.

Claude plugin integration to the workflow

You may vary a number of settings related to the model plugin from the Config JSON field. Each option is detailed below:

{
  "mode": "text-prompt",
  "model_name": "claude-3-5-haiku-latest",
  "anthropic_api_key": "",
  "prompt_prefix": "",
  "prompt_suffix": ""
}

• "mode": Defines the operating mode of the plugin. The selected mode determines the type of input the plugin processes and the kind of task it performs.

  • Options:

    • "text-prompt"

    • "image-prompt"

    • "ner"

  • Example:

    • "mode": "text-prompt"

• "model_name": Specifies the Anthropic model that the plugin will use for inference. See the Anthropic models and pricing pages for available options and details.

  • Options:

    • "claude-3-5-haiku-latest"

    • "claude-fable-5"

    • "claude-mythos-5"

    • "claude-opus-4-8"

    • "claude-sonnet-4-6"

    • "claude-haiku-4-5-20251001"

    • ...

  • Example:

    • "model_name": "claude-sonnet-4-6"

• "anthropic_api_key": Specifies the Anthrophic API key used to authenticate requests sent by the plugin. You can generate and manage your API keys from the Anthropic dashboard.

  • Example:

    • "anthropic_api_key": "<YOUR_ANTHROPIC_API_KEY>"

• "prompt_prefix": A text string added before the main input content when constructing the prompt sent to the model.

  • Example:

    • "prompt_prefix": "Extract all company names from the following text:"

• "prompt_suffix": A text string added after the main input content when constructing the prompt sent to the model.

  • Example:

    • "prompt_suffix": "Return the result as a JSON array."