Structure - Markifact

Use AI to convert unstructured text or documents into structured JSON data using custom schemas fields you provide.


App	AI
Operation ID	`ai_structure`
Type	Action
Connection	None
Credits per run	2

Inputs

Field	Type	Required	Default	Description
`prompt`	string	Yes	-	Instructions for how to structure the data. This is a multi-line text area where you can: - Describe what data to extract or analyze - Reference dynamic data from other nodes using {{nodeId__data}} syntax - Specify formatting requirements - Use line breaks to structure complex instructions Example: “Structure this customer data: {{customerNodeId__data}} Extract key information and organize it properly”
`model`	string or SelectableOption	Yes	-	The AI model to use for data structuring. Some available options: ‘gpt-5.2’ - Latest openai model with advanced capabilities ‘gemini-3.1-pro-preview’ - Google’s most powerful model ‘gemini-3.5-flash’ - Fast, efficient Gemini 3 variant Note: Some models require Advanced tier subscription.
`schema_type`	string or SelectableOption	No	-	The type of structured output format. Available options: ‘object’ - Return one structured object ‘array’ - Return multiple structured objects Choose based on whether you expect one result or multiple results.
`schema_fields`	array of SchemaField	Yes	-	Define the structure for the output data. Each field specifies: - name: The variable name for this field - type: The data type (text, number, boolean, etc.) - description: What this field should contain This ensures the AI returns data in the exact format you need for downstream processing.

SchemaField

Field	Type	Required	Default	Description
`name`	string	Yes	-	The name of the field.
`type`	string	Yes	-	Data type of the field, available types: text, number, boolean, object, list.
`description`	string	Yes	-	Description of the field.

SelectableOption

Field	Type	Required	Default	Description
`value`	string	Yes	-
`label`	string	Yes	-

Output

Type: List[Dict] | Dict Returns structured data matching the provided schema_fields. Output is either a list or single object based on ‘schema_type’ set by user. Fields: dynamic (depend on the inputs) Example:

[
  {
    "name": "John",
    "email": "john@example.com",
    "score": 85
  }
]