AI Tasks

Generate Text

Inputs:

• prompt - Prompt (required)
• model - Model (required)
• temperature - Temperature (optional)
• maxTokens - Max tokens (optional)
• attachmentIds - Attachment ids (optional)
• client - Client (optional)

Outputs:

• text - Text (required)

Example:

task: "AI/GenerateText@1"
name: generateText
inputs:
  prompt:
    - role: "system"
      content: "You are a helpful assistant that can write a short description of the product."
    - role: "user"
      content:
        [
          {
            "type": "input_image",
            "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
          },
        ]
  model: "gpt-3.5-turbo"
  client:
    apiKey: "{{ secrets.OPENAI_API_KEY }}"
    baseUrl: "https://api.openai.com/v1"
  temperature: 0.5
  maxTokens: 100
outputs:
  text: "{{ parseJson result.text }}"

JSON response using parseJson

task: "AI/GenerateText@1"
name: generateJsonResponse
inputs:
  prompt:
    - role: "system"
      content: >
        You are a helpful data generator. Please respond **only** in valid JSON format without any extra text.
        The JSON object must contain the following keys:
        - "status": A string indicating the result (e.g., "success").
        - "message": A concise message.
        - "data": An object with arbitrary key-value pairs.
    - role: "user"
      content: >
        Generate a JSON response that confirms a successful operation and includes the current date under the "data" key.
  model: "gpt-3.5-turbo"
  client:
    apiKey: "{{ secrets.OPENAI_API_KEY }}"
    baseUrl: "https://api.openai.com/v1"
  temperature: 0.3
  maxTokens: 120
outputs:
  response: "{{ parseJson result.text }}"