ADVERTISEMENT
Google AdSense Slot (headerLeaderboard)
Set your Publisher ID in src/config/ads.ts to display live ads.
ChatGPT & LLM AI Engineering Guide• 6 min read
Calling LLM APIs in JavaScript & Python
Learn how to integrate OpenAI GPT-4 and Google Gemini APIs into real web applications with streaming responses and JSON schema.
Calling the Chat Completion API
Modern LLM endpoints accept an array of message objects: system (rules & persona), user (the query), and assistant (prior conversation history).
Calling OpenAI API in Node.js / TypeScript
import OpenAI from 'openai';
const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
async function generateSummary(text) {
const completion = await openai.chat.completions.create({
model: 'gpt-4o-mini',
messages: [
{ role: 'system', content: 'You are a concise technical editor.' },
{ role: 'user', content: `Summarize this article in 3 bullet points:\n${text}` }
],
temperature: 0.2, // Low temperature for deterministic output
});
return completion.choices[0].message.content;
}ADVERTISEMENT
Google AdSense Slot (inContentBanner)
Set your Publisher ID in src/config/ads.ts to display live ads.
Test Yourself With Exercise
Which API parameter controls randomness, where 0.0 is deterministic and 1.0+ is highly creative?