Text Generation Example

Learn how to generate text using different models and parameters with Lumia AI.

Code

Complete implementation with comments

import { generateText } from 'ai';
import { Lumia } from '@ai-sdk/Lumia';

// Basic text generation
async function generateBasicText() {
  const { text } = await generateText({
    model: Lumia('Lumia-V2-Pro'),
    prompt: 'Write a short story about AI',
    system: 'You are a creative writer.'
  });
  
  console.log(text);
}

generateBasicText();

Parameters Explained

Understanding the available configuration options

Temperature

Controls randomness in the output. Higher values (e.g., 0.8) make the output more creative, while lower values (e.g., 0.2) make it more focused and deterministic.

Max Tokens

The maximum length of the generated text. One token is roughly 4 characters of English text.

Top P

An alternative to temperature, controls diversity via nucleus sampling. Lower values (e.g., 0.1) make the output more focused.

Frequency Penalty

Reduces repetition by penalizing tokens based on their frequency in the text so far.