import { loadModel } from '@fugood/llama.node'

// Initial a Llama context with the model (may take a while)
const context = await loadModel({
  model: 'path/to/gguf/model',
  use_mlock: true,
  n_ctx: 2048,
  n_gpu_layers: 1, // > 0: enable GPU
  // embedding: true, // use embedding
  // lib_variant: 'opencl', // Change backend
})

// Do completion
const { text } = await context.completion(
  {
    prompt: 'This is a conversation between user and llama, a friendly chatbot. respond in simple markdown.\n\nUser: Hello!\nLlama:',
    n_predict: 100,
    stop: ['</s>', 'Llama:', 'User:'],
    // n_threads: 4,
  },
  (data) => {
    // This is a partial completion callback
    const { token } = data
  },
)
console.log('Result:', text)