Configuration

Direct link to heading

Configuration Details

{
    "id": "io.infomaker.wingman",
    "name": "im-wingman",
    "style": "https://plugins.writer.infomaker.io/v1/infomaker/im-wingman/1.2.0/style.css",
    "url": "https://plugins.writer.infomaker.io/v1/infomaker/im-wingman/1.2.0/index.js",
    "mandatory": false,
    "enabled": true,
    "data": {
        "host": "https://ai-eu-west-1.saas-prod.infomaker.io",
        "contextLimit": 2,
        "encryptedKeyPhrase": "somePhrase",
        "widgets": [
            "generic",
            "headline",
            "summary"
        ],
        "widgetConfig": {
            "headline": {
                "digital": {
                    "preText": "Generate a headline",
                    "creativity": 5,
                    "headlineCount": 10,
                    "digitalHeadlineWordCount": 20,
                    "checkBoxDefault": false,
                    "providerAccessToken": "someToken",
                    "serviceProvider": "openai",
                    "modelId": "gpt-3.5-turbo"
                },
                "print": {
                    "preText": "Suggest headlines for the article provided in XML tag. If the article has a strong local connection, reflect this in the headline.",
                    "creativity": 5,
                    "headlineCount": 10,
                    "printHeadlineWordCount": 8,
                    "checkBoxDefault": false,
                    "providerAccessToken": "",
                    "serviceProvider": "Bedrock",
                    "modelId": "anthropic.claude-3-sonnet-20240229-v1:0"
                }
            },
            "summary": {
                "digital": {
                    "preText": "Generate a summary",
                    "creativity": 5,
                    "summaryCount": 5,
                    "digitalSummaryWordCount": 40,
                    "checkBoxDefault": false,
                    "providerAccessToken": "someToken",
                    "serviceProvider": "openai",
                    "modelId": "gpt-3.5-turbo"
                },
                "print": {
                    "preText": "Suggest summaries for the article provided in XML tag. Act as a news editor and your task is to suggest a summary for the article.",
                    "creativity": 5,
                    "summaryCount": 5,
                    "printSummaryWordCount": 100,
                    "checkBoxDefault": false,
                    "providerAccessToken": "",
                    "serviceProvider": "Bedrock",
                    "modelId": "anthropic.claude-v2:1"
                }
            },
            "generic": {
                "digital": {
                    "preText": "Generate a headline",
                    "creativity": 5,
                    "checkBoxDefault": false,
                    "providerAccessToken": "someToken",
                    "serviceProvider": "openai",
                    "modelId": "gpt-3.5-turbo"
                },
                "print": {
                    "preText": "You are a News Editor of a News Firm and your task is to suggest headlines for the article provided in  XML tag.\n\nPlease use professional tone while generating headlines.",
                    "creativity": 5,
                    "checkBoxDefault": false,
                    "providerAccessToken": "",
                    "serviceProvider": "Bedrock",
                    "modelId": "anthropic.claude-3-sonnet-20240229-v1:0"
                }
            }
        }
    }
}
  • contextLimit: Max. limit of context tags that can be sent in the prompt.

  • encryptedKeyPhrase: Encryption Key Phrase for sending encrypted API Key.

  • widgets: Widgets that should be enabled in Wingman plugin.


Headline Configuration Details

"widgetConfig": {
  "headline": {
    "digital": {
      "preText": "Generate a headline",
      "creativity": 5,
      "headlineCount": 10,
      "digitalHeadlineWordCount": 20,
      "checkBoxDefault": false,
      "providerAccessToken": "someToken",
      "serviceProvider": "openai",
      "modelId": "gpt-3.5-turbo"
    },
    "print": {
      "preText": "Suggest headlines for the article provided in XML tag. If the article has a strong local connection, reflect this in the headline.",
      "creativity": 5,
      "headlineCount": 10,
      "printHeadlineWordCount": 8,
      "checkBoxDefault": false,
      "providerAccessToken": "",
      "serviceProvider": "Bedrock",
      "modelId": "anthropic.claude-3-sonnet-20240229-v1:0"
    }
  },
  ...
}
  • PreText: Field where the user sends the custom prompt to generate the headline.

Note: For AWS Bedrock, end your custom prompt with these words: ‘in the XML tag’. Do not add these words for ChatGPT models.

  • creativity: Determines temperature, between 1–5 (1 = least randomness, 5 = most).

  • headlineCount: Total headline results to generate.

  • digitalHeadlineWordCount: Approx. word count for digital headlines.

  • printHeadlineWordCount: Approx. word count for print headlines.

  • checkBoxDefault: Default state of checkbox (false means unchecked by default).

  • providerAccessToken: Currently applicable for ChatGPT when an organization wants to use their own API key instead of Naviga's (if available).

  • serviceProvider: AI provider for prompt ("openai" for ChatGPT, "Bedrock" for AWS).

  • modelId: Model to be used for the prompt.


Summary Configuration Details

"summary": {
  "digital": {
    "preText": "Generate a summary",
    "creativity": 5,
    "summaryCount": 5,
    "digitalSummaryWordCount": 40,
    "checkBoxDefault": false,
    "providerAccessToken": "someToken",
    "serviceProvider": "openai",
    "modelId": "gpt-3.5-turbo"
  },
  "print": {
    "preText": "Suggest summaries for the article provided in XML tag. Act as a news editor and your task is to suggest a summary for the article.",
    "creativity": 5,
    "summaryCount": 5,
    "printSummaryWordCount": 100,
    "checkBoxDefault": false,
    "providerAccessToken": "",
    "serviceProvider": "Bedrock",
    "modelId": "anthropic.claude-v2:1"
  }
}
  • PreText: Field where the user sends the custom prompt to generate the summary.

Note: For AWS Bedrock it is recommended to end your custom prompt with these words: ‘in the XML tag’. Do not add these words for ChatGPT models.

  • creativity: Determines temperature, between 1–5 (1 = least randomness, 5 = most).

  • summaryCount: Total summary results to generate.

  • digitalSummaryWordCount: Approx. word count for digital summaries.

  • printSummaryWordCount: Approx. word count for print summaries.

  • displayCount: Number of results displayed before a "show more" button.

  • checkBoxDefault: Default state of checkbox (false means unchecked by default).

  • providerAccessToken: Currently applicable for ChatGPT when an organization wants to use their own API key instead of Naviga's (if available).

  • serviceProvider: AI provider for prompt ("openai" for ChatGPT, "Bedrock" for AWS).

  • modelId: Model to be used for the prompt.


Generic Configuration Details

"generic": {
  "digital": {
    "preText": "Generate a headline",
    "creativity": 5,
    "checkBoxDefault": false,
    "providerAccessToken": "someToken",
    "serviceProvider": "openai",
    "modelId": "gpt-3.5-turbo"
  },
  "print": {
    "preText": "You are a News Editor of a News Firm and your task is to suggest headlines for the article provided in  XML tag.\n\nPlease use professional tone while generating headlines.",
    "creativity": 5,
    "checkBoxDefault": false,
    "providerAccessToken": "",
    "serviceProvider": "Bedrock",
    "modelId": "anthropic.claude-3-sonnet-20240229-v1:0"
  }
}
  • PreText: Field where the user sends the custom prompt to generate generic results.

Note: For AWS Bedrock it is recommended to end your custom prompt with these words: ‘in the XML tag’. Do not add these words for ChatGPT models.

  • creativity: Determines temperature, between 1–5 (1 = least randomness, 5 = most).

  • checkBoxDefault: Default state of checkbox (false means unchecked by default).

  • providerAccessToken: Currently applicable for ChatGPT when an organization wants to use their own API key instead of Naviga's (if available).

  • serviceProvider: AI provider for prompt ("openai" for ChatGPT, "Bedrock" for AWS).

  • modelId: Model to be used for the prompt.

Was this helpful?