When you want to label or categorize text into a set number of buckets - you can use the PromptLoop Label function. This function will return the most likely match to a text string in your labels list.
- List the labels or categories you want to sort your data into, this will depend on the type of data or goal of the analysis. For most cases look to make the options collectively exhaustive (list all possible options as labels) and mutually exclusive (Do not list overlapping categories like human and person unless specifically needed)
- Select the target cell or cells that you want to add a label too as the first parameter ( target , inputLabels )
- Select the list of labels which should be the same for the whole dataset.
- Analyze the results - use a pivot table or =COUNTIF to understand your categories.
=PROMPTLOOP_LABEL( target, inputLabels )
This is similar to the main PromptLoop function but will only return items in the label set, is much faster, and requires far fewer credits.
This function uses our own algorithm to deliver the fastest, and cheapest (uses 3-5 credits) labeling and categorization solution available delivering fast and reliable order to the chaos of text data.
Labeling works off of semantic similarity. So labeling "I like apples" with "fruit" instead of a number or code will perform better.