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

const embeddingModel = transformers.embedding('Xenova/bge-small-en-v1.5');

const { embedding } = await embed({ model: embeddingModel, value: 'Hello world' });
const { embeddings } = await embedMany({ model: embeddingModel, values: ['Hello', 'World'] });

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

const model = transformers.multimodalEmbedding('Xenova/clip-vit-base-patch32');

// Text embedding
const { embedding: textVec } = await embed({ model, value: 'a photo of a cat' });

// Image embedding (same vector space)
const { embedding: imgVec } = await embedImage({ model, image: catImageBlob });

// Cross-modal similarity
const similarity = cosineSimilarity(textVec, imgVec);

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

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,
});

import { classify, extractEntities } from '@localmode/core';
import { transformers } from '@localmode/transformers';

const sentiment = await classify({
  model: transformers.classifier('Xenova/distilbert-base-uncased-finetuned-sst-2-english'),
  text: 'I love this product!',
});

const entities = await extractEntities({
  model: transformers.ner('Xenova/bert-base-NER'),
  text: 'John works at Microsoft in Seattle',
});

import { transcribe, synthesizeSpeech } from '@localmode/core';
import { transformers } from '@localmode/transformers';

const transcription = await transcribe({
  model: transformers.speechToText('onnx-community/moonshine-tiny-ONNX'),
  audio: audioBlob,
  returnTimestamps: true,
});

const { audio, sampleRate } = await synthesizeSpeech({
  model: transformers.textToSpeech('onnx-community/Kokoro-82M-v1.0-ONNX'),
  text: 'Hello, how are you?',
});

import { classifyImage, captionImage } from '@localmode/core';
import { transformers } from '@localmode/transformers';

const classification = await classifyImage({
  model: transformers.imageClassifier('Xenova/vit-base-patch16-224'),
  image: imageBlob,
});

const caption = await captionImage({
  model: transformers.captioner('onnx-community/Florence-2-base-ft'),
  image: imageBlob,
});

import { generateText, streamText } from '@localmode/core';
import { transformers } from '@localmode/transformers';

const model = transformers.languageModel('onnx-community/Qwen3.5-0.8B-ONNX');

// Single-shot generation
const { text } = await generateText({ model, prompt: 'What is 2+2?' });

// Streaming generation
const result = await streamText({ model, prompt: 'Write a haiku' });
for await (const chunk of result.stream) {
  process.stdout.write(chunk.text);
}

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

const cached = await isModelCached('Xenova/bge-small-en-v1.5');

await preloadModel('Xenova/bge-small-en-v1.5', {
  onProgress: (p) => console.log(`${p.progress}% loaded`),
});

const usage = await getModelStorageUsage();

import {
  MODELS,                      // All models organized by task
  EMBEDDING_MODELS,
  CLASSIFICATION_MODELS,
  ZERO_SHOT_MODELS,
  NER_MODELS,
  RERANKER_MODELS,
  SPEECH_TO_TEXT_MODELS,
  TEXT_TO_SPEECH_MODELS,
  IMAGE_CLASSIFICATION_MODELS,
  ZERO_SHOT_IMAGE_MODELS,
  IMAGE_CAPTION_MODELS,
  TRANSLATION_MODELS,
  SUMMARIZATION_MODELS,
  FILL_MASK_MODELS,
  QUESTION_ANSWERING_MODELS,
  OBJECT_DETECTION_MODELS,
  SEGMENTATION_MODELS,
  OCR_MODELS,
  DOCUMENT_QA_MODELS,
  IMAGE_TO_IMAGE_MODELS,
  IMAGE_FEATURE_MODELS,
} from '@localmode/transformers';

// Use with provider
const model = transformers.embedding(EMBEDDING_MODELS.BGE_SMALL_EN);

const model = transformers.embedding('Xenova/bge-small-en-v1.5', {
  quantized: true, // Use quantized model (smaller, faster)
  device: 'webgpu', // Use WebGPU for acceleration (falls back to WASM)
});

const { embedding } = await embed({
  model: transformers.embedding('Xenova/bge-small-en-v1.5'),
  value: 'Hello world',
  providerOptions: {
    transformers: {
      // Any Transformers.js specific options
    },
  },
});

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

if (!(await isModelCached('Xenova/bge-small-en-v1.5'))) {
  await preloadModel('Xenova/bge-small-en-v1.5', {
    onProgress: (p) => console.log(`Loading: ${p.progress}%`),
  });
}

// Subsequent calls are instant (loaded from cache)
const embeddingModel = transformers.embedding('Xenova/bge-small-en-v1.5');
const { embedding } = await embed({ model: embeddingModel, value: 'Hello' });

import {
  TransformersEmbeddingModel,
  TransformersClassificationModel,
  TransformersZeroShotModel,
  TransformersNERModel,
  TransformersRerankerModel,
  TransformersSpeechToTextModel,
  TransformersImageClassificationModel,
  TransformersZeroShotImageModel,
  TransformersCaptionModel,
} from '@localmode/transformers';

import {
  TransformersSegmentationModel,
  TransformersObjectDetectionModel,
  TransformersImageFeatureModel,
  TransformersImageToImageModel,
  TransformersTextToSpeechModel,
  TransformersAudioClassificationModel,
  TransformersZeroShotAudioClassificationModel,
  TransformersTranslationModel,
  TransformersSummarizationModel,
  TransformersFillMaskModel,
  TransformersQuestionAnsweringModel,
  TransformersOCRModel,
  TransformersDocumentQAModel,
  TransformersDepthEstimationModel,
} from '@localmode/transformers/implementations';