`language-models`

language-models provides a unified interface for working with various language models across different providers. It simplifies model selection and usage, providing a consistent API regardless of the underlying model provider.

The package abstracts away the differences between model providers, allowing you to switch between models without changing your application code. It supports a wide range of models from providers like OpenAI, Anthropic, Google, and more.

Usage Example


import { createModel } from 'language-models'
 
// Create a model interface
const model = createModel({
  provider: 'openai',
  modelName: 'gpt-4o',
  apiKey: process.env.OPENAI_API_KEY,
})
 
// Generate text
const response = await model.complete({
  prompt: 'Explain quantum computing in simple terms',
  maxTokens: 250,
  temperature: 0.7,
})
 
// Use a different model
const claudeModel = createModel({
  provider: 'anthropic',
  modelName: 'claude-3-opus',
  apiKey: process.env.ANTHROPIC_API_KEY,
})
 
// Use streaming for real-time responses
const stream = await claudeModel.streamComplete({
  prompt: 'Write a step-by-step guide for making bread',
  maxTokens: 1000,
})
 
for await (const chunk of stream) {
  console.log(chunk)
}