import { CreateMLCEngine } from "@mlc-ai/web-llm";

// Initialize the engine
const engine = await CreateMLCEngine(
  "Llama-3.2-1B-Instruct-q4f32_1-MLC",
  { 
    initProgressCallback: (progress) => {
      console.log('Loading:', progress.progress + '%');
    }
  }
);

// Generate text
const response = await engine.chat.completions.create({
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello! How are you?" }
  ],
  temperature: 0.8,
  max_tokens: 100
});

console.log(response.choices[0].message.content);

import { BrowserAI } from '@browserai/browserai';

const browserAI = new BrowserAI();

// Load model with progress tracking
await browserAI.loadModel('llama-3.2-1b-instruct', {
  quantization: 'q4f16_1',
  onProgress: (progress) => console.log('Loading:', progress.progress + '%')
});

// Generate text
const response = await browserAI.generateText('Hello, how are you?');
console.log(response.choices[0].message.content);

// Streaming example
const chunks = await browserAI.generateText('Write a story', {
  stream: true,
  temperature: 0.8
});

for await (const chunk of chunks) {
  console.log(chunk.choices[0]?.delta.content || '');
}

# Install and run Ollama
curl -fsSL https://ollama.ai/install.sh | sh
ollama serve

# Pull and run a model
ollama pull llama3.2:1b
ollama run llama3.2:1b "Hello, world!"

# Use the REST API
fetch('http://localhost:11434/api/generate', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    model: 'llama3.2:1b',
    prompt: 'Hello!',
    stream: false
  })
}).then(r => r.json()).then(console.log);

// LM Studio provides a local server compatible with OpenAI API
const response = await fetch('http://localhost:1234/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer lm-studio'
  },
  body: JSON.stringify({
    model: 'llama-3.2-1b-instruct',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Hello!' }
    ],
    temperature: 0.7,
    max_tokens: 100
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

import Together from "together-ai";

const together = new Together({
  apiKey: process.env.TOGETHER_API_KEY,
});

const response = await together.chat.completions.create({
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain quantum computing in simple terms." }
  ],
  model: "meta-llama/Llama-3.2-3B-Instruct-Turbo",
  max_tokens: 500,
  temperature: 0.7,
  stream: true,
});

// Handle streaming response
for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

import { CreateMLCEngine } from "@mlc-ai/web-llm";

// Load a vision-language model
const engine = await CreateMLCEngine("Llava-1.5-7B-q4f16_1-MLC");

// Process image and text
const response = await engine.chat.completions.create({
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "What do you see in this image?" },
        {
          type: "image_url",
          image_url: { url: "data:image/jpeg;base64,..." }
        }
      ]
    }
  ]
});

console.log(response.choices[0].message.content);