←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
Show context
CraftingLinks ◴[18 Jun 24 06:55 UTC] No.40714816[source]▶
We just use openai function calls (tools) and then use Pydantic to verify the JSON. When validation fails we try the prompt again.
replies(2): >>40714832 #>>40715169 #
1. knallfrosch ◴[18 Jun 24 07:52 UTC] No.40715169[source]▶
Same here. I send a JSON schema along with the prompt to ChatGPT as function_call and then verify with NodeJS + Ajv against the same schema again.