What is UniLLM?

UniLLM allows you to call any LLM using the OpenAI API, with 100% type safety.

Benefits

• ✨ Integrate with any provider and model using the OpenAI API
• 💬 Consistent chatCompletion responses and logs across all models and providers
• 💯 Type safety across all providers and models
• 🔁 Seamlessly switch between LLMs without rewriting your codebase
• ✅ If you write tests for your service, you only need to test it once
• 🔜 (Coming Soon) Request caching and rate limiting
• 🔜 (Coming Soon) Cost monitoring and alerting

Getting Started

npm i unillm

import { UniLLM } from 'unillm';
 
/*
  #SETUP#
*/
 
// Setup UniLLM
const unillm = new UniLLM();
 
// Use any LLM provider and model
const response = await unillm.createChatCompletion("#MODEL#", {
  stream: true,
  temperature: 0,
  messages: [
    {
      role: "user",
      content: "How are you?"
    }
  ],
})

Supported Providers & Models

Below is a list of models that are currently supported by UniLLM. If you would like to see a model added to the roadmap, please open an issue on GitHub (opens in a new tab).