Hi,
I have been given a task to document what I have done with regard to building out a data pipeline with Azure Data Factory.
I thought I would get chatGPT to help with the documentation by giving GPT the JSON code used to build the pipeline and then writing up the documentation for me (or at least provide the framework of the documentation.
I started the chat with the following:
You are to act as a professional Data Engineer that specializes in Microsoft Azure Cloud Platforms. You have deep understanding of Azure Data Factory. You first task is to review the Azure Data Factory JSON code and let me know when you’re ready for the next steps?
{
"name": "ADX_2-ADLS",
"properties": {
"activities": [
{
"name": "ADX_AdsInputFiles",
"description": "GiftCommitmentsSilverRegularGivingMandates",
"type": "Copy",
"dependsOn": [],
"policy": {
"timeout": "0.12:00:00",
"retry": 0,
"retryIntervalInSeconds": 30,
"secureOutput": false,
"secureInput": false
},
"userProperties": [],
"typeProperties": {
"source": {
"type": "AzureDataExplorerSource",
"query": "database('Silver').SilverRegularGivingMandates\n| join kind = inner (f "enableStaging": false,
"translator": {
"type": "TabularTranslator",
"typeConversion": true,
"typeConversionSettings": {
"allowDataTruncation": true,
"treatBooleanAsNumber": false
}
}
},
"inputs": [
{
"referenceName": "DS_SilverPrizes",
"type": "DatasetReference"
}
],
"outputs": [
{
"referenceName": "DS_SilverPrizes_ADLS",
"type": "DatasetReference"
}
]
}
],
"annotations": []
}
}
I then ask the chatGPT to carry out the following request:
Now that you understand the code, please document what the code sets out to achieve. The document should be written a format that is to be delivered or read by individuals that aren’t necessarily experts or familiar with ADF but needs to understand what it sets out to achieve
Can someone help reword the prompt the give a more broad outcome please