Re:Show HN: A lightweight LLM proxy to get structured result...
by alboaie on Thursday February 27, 2025 @02:04PM
(#43197360)
Looks usefull. Could you explain how it works? you have to chain it after the call from other LLM ?
[ Parent
| on HN ]
Re:Show HN: A lightweight LLM proxy to get structured result...
by lunarcave on Thursday February 27, 2025 @03:41PM
(#43198276)
Thanks.
We use a minimal schema[1] to prompt the LLM under the hood. We were inspired by BAML [2]. Then the output is wrangled with a converter and ajv [3].
[1] https://github.com/inferablehq/l1m/blob/main/api/src/schema....