Hi! I made a small library which allows using AI models like they were just a Go function, but that Go function can be:
- defined with natural language description - example inputs with expected outputs - or both Internally, it then calls into an LLM to get the answer. So it is not fast, but it is an interesting new way to define your functions. Check it out, any feedback welcome: https://gitlab.com/tozd/go/fun Caveat: Current LLMs available still randomly return trash for some inputs, even if they work great for very similar other inputs. But hopefully that will improve through time. And there are some ways to check for this (using JSON Schema to validate outputs, comparing outputs of multiple models, etc.). Mitar -- https://mitar.tnode.com/ https://twitter.com/mitar_m https://noc.social/@mitar -- You received this message because you are subscribed to the Google Groups "golang-nuts" group. To unsubscribe from this group and stop receiving emails from it, send an email to golang-nuts+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/golang-nuts/CAKLmikPBH3ouhKbEt7v%3D2mBVwVxZ6DbKESSOZb6dfjMKk6BVoA%40mail.gmail.com.
