​Example guided tour

# Flow declaration with a mandatory unique identifier, a namespace, and an optional description.
# Flow identifier are unique inside a namespace.
id: kestra-tour
namespace: io.kestra.demo
description: Kestra guided tour


# Flow inputs: each input has a name, a type, and an optional default value.
inputs:
  # We define one input of name 'csvUrl' with as default value the URL of the test data file.
  # This test data is from the France Open Data portal and contains french electricity consumptions in CSV.
  - name: csvUrl
    type: STRING
    defaults: https://gist.githubusercontent.com/tchiotludo/2b7f28f4f507074e60150aedb028e074/raw/6b6348c4f912e79e3ffccaf944fd019bf51cba30/conso-elec-gaz-annuelle-par-naf-agregee-region.csv


# List of tasks that will be executed one after the other.
# Each task must have an identifier unique for the flow and a type.
# Depending on the type of the task, you may have to pass additional attributes.
tasks:
  # This is one of the simplest task: it echos a message in the log, like the 'echo' command.
  # The message is passed thanks to the 'format' attribute.
  - id: log
    type: io.kestra.core.tasks.debugs.Echo
    format: The flow starts

  # This task will download the CSV, it will be sent to Kestra's internal storage and available from the task output.
  - id: downloadData
    type: io.kestra.plugin.fs.http.Download
    # Here we use a variable from an input: '{{' and '}}' are separator of a Pebble expression in which we can access variables.
    # All inputs are available from the 'inputs' variable using there name.
    uri: "{{inputs.csvUrl}}"

  # This task will analyze the CSV data using a Python script with the Pandas library.
  - id: analyzeData
    type: io.kestra.core.tasks.scripts.Python
    inputFiles:
      # Here we define a file named 'data.csv' that will be available in the Python task working directory.
      # This file is fetched from the internal storage by using the 'uri' output of the 'downloadData' task.
      data.csv: "{{outputs.downloadData.uri}}"
      # 'main.py' is the Python script that will be executed.
      # It uses Pandas to read the CSV file, compute the sum of the 'conso' column, 
      # and set it as task output thanks to the Kestra Python library.
      main.py: |
        import pandas as pd
        from kestra import Kestra
        data = pd.read_csv("data.csv", sep=";")
        data.info()
        sumOfConsumption = data['conso'].sum()
        Kestra.outputs({'sumOfConsumption': int(sumOfConsumption)})
    # As the script require the Pandas library, we must list it in the requirements.
    requirements:
      - pandas