https://promptfoo.dev/ logo
golden data set csv translation
# ❓|questions
b
Hello, this is what I am attempting to do. I have my golden data set of english to x language translation. What can I do so that my assert passes for fuzzy match meaning if the translation matches a certain percentage of the words in the target language then it is good. Hope I am explaining it well.
right now this is kind of what I am doing (super simple example) and I find it very tedious source_sentence,translated_chunks Good morning,Buenos días,["Buenos" "días"]",
I still want it to "pass" even if the translation was Buenos dias amigo. ~75% accuracy
got it
use an __expected column "contains-any: parts of the sentence"
that does not seem to work 🙁
t
@[Promptfoo] Steve any idea?