Примеры кода

// npm install @mlc-ai/web-llm
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:', Math.round(progress.progress * 100) + '%');
    }
  }
);

// 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);

// npm install @browserai/browserai
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 || '');
}

# Terminal
ollama pull llama3.2:1b
ollama run llama3.2:1b "Hello, world!"

// Discover the identifiers exposed by this LM Studio server
const modelsResponse = await fetch('http://localhost:1234/v1/models');
if (!modelsResponse.ok) throw new Error('Model list failed: ' + modelsResponse.status);
const models = await modelsResponse.json();
const model = models.data?.[0]?.id;
if (!model) throw new Error('Load at least one model in LM Studio');

const response = await fetch('http://localhost:1234/v1/chat/completions', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    model,
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Hello!' }
    ],
    temperature: 0.7,
    max_tokens: 100
  })
});

if (!response.ok) throw new Error('Completion failed: ' + response.status);
const data = await response.json();
console.log(data.choices[0].message.content);

// npm install together-ai
import Together from "together-ai";

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

const model = process.env.TOGETHER_MODEL;
if (!model) throw new Error("Set TOGETHER_MODEL to an ID from the current serverless catalog");

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,
  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 || '');
}