Transformation: `transform_type`

​

Parse

transform_type = 'parse'

The one and only transform_type you should upload your documents into. The parse transform will parse your PDFs, audio, HTML or any other type of data into a uniform text format, priming the rest of your document workflow.

{
  "column_name": "invoice",
  "column_type": "assets",
  "transform_type": "parse",
  "task_description": "N/A"
}

​

Extract

transform_type = 'extraction'

Considered the most common data transformation. Used to extract information from your assets columns. You can extract data small and large, and the data can be ready-to-use (the name from a contract) or the first step of a processing pipeline (a table of transactions on an invoice).

{
  "column_name": "invoice_amount",
  "column_type": "number",
  "transform_type": "extraction",
  "task_description": "Extract the invoice amount from the {{invoice}}"
}

​

Classify

transform_type = 'classification'

As simple as it sounds - classify data into one of several categories. Works best in pipelines downstream from extraction columns.

{
  "column_name": "type",
  "column_type": "text",
  "output_values": {
    "Large": "Above 10,000 dollars",
    "Small": "under 1,000 dollars",
    "Medium": "Between 1,000 and 10,000 dollars",
    "Unknown": "Can't find the invoice amount"
  },
  "has_default": true,
  "default_value": {
    "value": "Unknown"
  },
  "transform_type": "classification",
  "task_description": "Classify the {{invoice_amount}}",
}

​

Generate

transform_type = 'generation'

Used to imagine new data from existing data. Use cases including drafting short blurbs from documents - for example, a matching memo for a particular invoice.

{
  "column_name": "memo",
  "column_type": "text",
  "transform_type": "generation",
  "task_description": "Generate a concise memo justifying {{invoice}}"
}

​

Manual

transform_type = 'manual'

For data that you want to establish manually. Use cases include manually assigning an approver for a particular invoice.

{
  "column_name": "approver",
  "column_type": "text",
  "has_default": true,
  "default_value": {
    "value": "John"
  },
  "transform_type": "manual",
  "task_description": "N/A",
}

​

API Requests

transform_type = 'api_request'

Use data anywhere along your document extraction pipeline in the body of an API request. Can only be created on the Trellis Dashboard.

​

Lambda Functions

transform_type = 'run_function'

Use data anywhere along your document extraction pipeline in lambda functions for deterministic, programmable results. Can only be created on the Trellis dashboard.