←back to thread

Every Way to Get Structured Output from LLMs

(www.boundaryml.com)
169 points constantinum | 1 comments | 18 Jun 24 04:01 UTC | HN request time: 0s | source
1. bobosha ◴[18 Jun 24 11:04 UTC] No.40716279[source]▶
does anyone know if any of these tools offer support for a qualitative scores for the results? For example, if I have a text "my little pony.."

returns {"childrens comic": 99, "adult comedy":1,...}