[
{
"name": "Values in 'top_k_contexts' should be in 'correct_context' for every row",
"description": "Asserts that the list of strings in 'top_k_contexts' contains the string in 'correct_context' on a per-row basis.",
"type": "integrity",
"subtype": "expectColumnAToBeInColumnB",
"thresholds": [
{
"insightName": "expectColumnAToBeInColumnB",
"insightParameters": [
{
"name": "column_a_name",
"value": "correct_context" // Selects column A (`correct_context`)
},
{
"name": "column_b_name",
"value": "top_k_contexts" // Selects column B (`top_k_contexts`)
}
],
"measurement": "failingRowCount", // Use the absolute row count
"operator": "<=",
"value": 0
}
],
"subpopulationFilters": null,
"mode": "development",
"usesValidationDataset": true, // Apply test to the validation set
"usesTrainingDataset": false,
"usesMlModel": false,
"syncId": "b4dee7dc-4f15-48ca-a282-63e2c04e0689" // Some unique id
},
{
"name": "Values in 'top_k_contexts' should be in 'correct_context' for at least 80% of the rows",
"description": "Asserts that the list of strings in 'top_k_contexts' contains the string in 'correct_context' on a per-row basis.",
"type": "integrity",
"subtype": "expectColumnAToBeInColumnB",
"thresholds": [
{
"insightName": "expectColumnAToBeInColumnB",
"insightParameters": [
{
"name": "column_a_name",
"value": "correct_context" // Selects column A (`correct_context`)
},
{
"name": "column_b_name",
"value": "top_k_contexts" // Selects column B (`top_k_contexts`)
}
],
"measurement": "failingRowPercentage", // Use the row percentage
"operator": "<",
"value": 0.2
}
],
"subpopulationFilters": null,
"mode": "development",
"usesValidationDataset": true, // Apply test to the validation set
"usesTrainingDataset": false,
"usesMlModel": false,
"syncId": "96622fba-ea00-4e42-8f42-5e8f5f60805f" // Some unique id
}
]