رابط برنامه‌نویسی وب LiteRT-LM

<div id="out" style="white-space: pre-wrap; font-family: monospace;"></div>
<input id="in" onkeydown="if(event.key === 'Enter') repl(this)">

<script type="module">
  import { Engine } from 'https://cdn.jsdelivr.net/npm/@litert-lm/core/+esm';
  const engine = await Engine.create({
    // Load the Gemma 4 E2B model
    model: 'https://huggingface.co/litert-community/gemma-4-E2B-it-litert-lm/resolve/main/gemma-4-E2B-it-web.litertlm'
    // Or use the E4B model by swapping in this line
    // model: 'https://huggingface.co/litert-community/gemma-4-E4B-it-litert-lm/resolve/main/gemma-4-E4B-it-web.litertlm'
  });
  const chat = await engine.createConversation();

  window.repl = async (el) => {
    const text = el.value;
    el.value = ''; // Clear immediately
    out.append(`\n>>> ${text}\nAI: `);

    for await (const chunk of chat.sendMessageStreaming(text)) {
      out.append(chunk.content[0].text);
    }
  };
</script>

# From npm
npm i --save @litert-lm/core

# From a CDN (in your JavaScript file)
import * as litertlm from 'https://cdn.jsdelivr.net/npm/@litert-lm/core/+esm';

import {Engine, EngineSettings} from '@litert-lm/core';

const engineSettings = {
  model: 'url/path/to/model.litertlm', // or a ReadableStream, or a Blob

  // You can configure context length and other settings here
  mainExecutorSettings: {
    maxNumTokens: 8192,
  },
} satisfies EngineSettings;

const engine = await Engine.create(engineSettings);

// ... Use the engine to create a conversation ...

// Delete the engine when done.
await engine.delete();

const conversation = await engine.createConversation({
  preface: {
    messages: [
      {role: 'system', content: 'You are a helpful assistant'}
    ]
  }
});

conversation.sendMessage({
  role: 'user',
  content: 'Write a poem',
});

// Simple string input
let response = await conversation.sendMessage("What is the capital of France?");
console.log(response.content[0].text);

// Or with full message structure
response = await conversation.sendMessage({role: 'user', content: '...'});

// sendMessageStreaming returns a ReadableStream of response chunks
const stream = conversation.sendMessageStreaming('Tell me a long story.');

for await (const chunk of stream) {
  // Chunks are Records containing pieces of the response
  for (const item of chunk.content) {
    if (item.type === 'text') {
      console.log(item.text);
    }
  }
}

// Cancel any ongoing generation
conversation.cancel();

for await (const chunk of stream) {
  if (shouldStop()) {
    break; // Cancels the stream and underlying generation
  }
}