Cigs- Chainable AI Functions for TypeScript with OAI Structured Outputs
Cigs- Chainable AI Functions for TypeScript with OAI Structured Outputs
Hey HN! With the release of OpenAI [Structured Outputs]( https://openai.com/index/introducing-structured-outputs-in-t... ) it gave me an idea to build a library to make it easier to build Ai powered with functions. It's somewhat inspired by the many cool libraries in Python. [Fructose]( https://github.com/bananaml/fructose ), [Ask Marvin]( https://www.askmarvin.ai ) and others but has a few main differences * For Typescript! * Chain AI functions easily and get type safety throughout the entire chain * Call typescript functions with natural language (or structured inputs). If you define an input schema for your function, it will map the natural language input to that input schema * Specify output schema for a function. When you call a typescript function you can specify the output schema. (I guess sort of like graphql but for functions?) Not sure that makes much sense, but I have some examples on the repo! I'd love to hear your thoughts, feedback, and any creative ways you could use cigs in your own projects. Let’s discuss in the comments!
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Incorrect prediction on native model
Similar products
Cerialize – Typescript serialization by annotation
Scala-ts – Scala to TypeScript compiler
Hapi with Typescript
JSONSchema to TypeScript compiler
Transpile Scala to TypeScript
Get started modding Factorio in TypeScript
WebSockets Explained with TypeScript
A BubbleShooter Implementation in TypeScript
Binary Serialization with TypeScript
DuoCode 1.0 bridges the gap between C# and TypeScript