import { transformers } from '@localmode/transformers';
import { embed, rerank } from '@localmode/core';

// Text Embeddings
const embeddingModel = transformers.embedding('Xenova/all-MiniLM-L6-v2');
const { embedding } = await embed({ model: embeddingModel, value: 'Hello world' });

// Reranking for RAG
const rerankerModel = transformers.reranker('Xenova/ms-marco-MiniLM-L-6-v2');
const { results } = await rerank({
  model: rerankerModel,
  query: 'What is machine learning?',
  documents: ['ML is a subset of AI...', 'Python is a language...'],
  topK: 5,
});

const model = transformers.embedding('Xenova/all-MiniLM-L6-v2', {
  quantized: true, // Use quantized model (smaller, faster)
  revision: 'main', // Model revision
  progress: (p) => {
    console.log(`Loading: ${(p.progress * 100).toFixed(1)}%`);
  },
});

import { preloadModel, isModelCached, getModelStorageUsage } from '@localmode/transformers';

// Check if model is cached
const cached = await isModelCached('Xenova/all-MiniLM-L6-v2');

// Preload model with progress
await preloadModel('Xenova/all-MiniLM-L6-v2', {
  onProgress: (p) => console.log(`${p.progress}% loaded`),
});

// Check storage usage
const usage = await getModelStorageUsage();

import { isWebGPUAvailable, getOptimalDevice } from '@localmode/transformers';

// Check if WebGPU is available
const webgpuAvailable = await isWebGPUAvailable();

if (webgpuAvailable) {
  console.log('WebGPU available, using GPU acceleration');
} else {
  console.log('Falling back to WASM');
}

// Get optimal device automatically
const device = await getOptimalDevice(); // 'webgpu' or 'wasm'

const model = transformers.embedding('Xenova/all-MiniLM-L6-v2', {
  device, // Uses WebGPU if available, otherwise WASM
});