User Profile

In the same vein - the sample code uses the line `self.cosineDistance(vector, queryVector)' which doesn't correlate to anything that intellisence offers. I am able to determine the distance between two strings directly with ' embedding.distance(between: string1, and: string2)' - but this is inefficient because I am ending up repeatedly recalculating the vectors for the sentence embeddings for the text corpus.

I agree that it's kind of unintuitive! From 'record types' you click on the 'edit indexes' button below the custom fields. Then you click 'add index'. This didn't make sense to me as a button label - but it immediately popped up 'record type' and a drop down to make it queryable. HTH