Skip to content

Descriptor

Justin42 edited this page May 21, 2023 · 3 revisions
name: Example
description: "Example dataset."

build:
  generateHashes: true
  verifyHashes: true

readers: # References only. Section is not directly read.
  - reader: &csv_example
      type: csv
      config:
        fields:
          conversation: 'thread_href'
          from: 'message_username'
          message: 'message'

writers: # References only. Section is not directly read.
  - writer: &fastchat_pretty
      type: fastchat
      config:
        indent: 2

debug_steps: # References only. Section is not directly read.
  - step: &debug_step1
      type: TransformerType1
      description: "Debug transformation"
      config:
        key: value1
        key2: value2

steps: # References only. Section is not directly read.
  - step: &step_name1
      type: TransformerType1
      description: "Example transformation 1"
      config:
        key1: value1
        key2: value2

  - step: &step_name2
      type: TransformerType2
      description: "Example transformation 2"
      config:
        key1: value1
        key2: value2

input:
  - path: "data/input.csv"
    description: "Example input."
    source: 'https://example.com/input.csv'
    #sha512: ...
    reader: *csv_example
    steps: [ *debug_step1, *step_name1 ]

output:
  - name: 'Example'
    path: 'out/example.json'
    description: 'Example output.'
    #sha512: ...
    writer: fastchat
    steps: [ *step_name2 ]

Clone this wiki locally