🧠 LLM Runner Router

// Simple Mode - For Rapid Prototyping
import { quick } from 'llm-runner-router';

const response = await quick("Explain quantum computing to a goldfish");
console.log(response.text);

// Advanced Mode - For Production Systems
import LLMRouter from 'llm-runner-router';

const router = new LLMRouter({
  strategy: 'quality-first',
  fallbacks: ['gpt-3.5', 'local-llama'],
  cacheEnabled: true
});

// Load multiple models
await router.load('huggingface:meta-llama/Llama-2-7b');
await router.load('local:./models/mistral-7b.gguf');

// Intelligent routing in action
const response = await router.advanced({
  prompt: "Write a haiku about JavaScript",
  temperature: 0.8,
  maxTokens: 50,
  streaming: true
});

// Stream tokens in real-time
for await (const token of response) {
  process.stdout.write(token);
}