Ask HN: Tell us about your project that's not done yet but you want feedback on

Re:Ask HN: Tell us about your project that's not done yet bu... by J_Shelby_J on Thursday August 17, 2023 @12:20AM (#37157167)

Hey, so I got pretty far into implementing open api specs for LLMs. To the point where you can point to an open api spec, ingest it, and then it’s available for GPT to select to satisfy user requests.

I do this by minify the specs and building an index to feed it that it selects from using logit bias.

Im at pause point on it while I figure out how to actually have GPT build the calls, but I think something like you have might solve that.

https://github.com/ShelbyJenkins/LLM-OpenAPI-minifier

[ Parent | on HN ]

Re:Ask HN: Tell us about your project that's not done yet bu... by dinp on Thursday August 17, 2023 @12:54AM (#37157412)

Before the function calling update[0] it was possible for the gpt models to use tools using specific prompts but it was unreliable. Have you tried using function calling to let the model build the calls?

[0] https://openai.com/blog/function-calling-and-other-api-updat...

[ Parent | on HN ]