How to write Code for Open AI SDK

[uvpatel]

Discussion Type

Question

Discussion Content

Discuss on Agentic AI

[mecodeatlas]

Thanks for posting in the GitHub Community, @uvpatel!

We're happy you're here. You are more likely to get a useful response if you are posting your question in the applicable category, the Discussions category is solely related to conversations around the GitHub product Discussions. This question should be in the Programming Help category. I've gone ahead and moved it for you. Good luck!

[mdimranreza-cyber]

How to write Code for Open AI SDK

Writing code using the OpenAI SDK depends on the language you’re using (most commonly Python or JavaScript). I’ll walk you through the basics in a simple way so you can get started quickly.

🚀 1. Install the OpenAI SDK
Python
pip install openai
JavaScript (Node.js)
npm install openai

🔑 2. Set Your API Key
You get your API key from OpenAI.

Linux / Mac
export OPENAI_API_KEY="your_api_key_here"
Windows
setx OPENAI_API_KEY "your_api_key_here"

🧠 3. Basic Example – Python
from openai import OpenAI

client = OpenAI()

response = client.responses.create(
model="gpt-5.3",
input="Write a short poem about technology."
)

print(response.output_text)

💻 4. Basic Example – JavaScript
import OpenAI from "openai";

const client = new OpenAI();

const response = await client.responses.create({
model: "gpt-5.3",
input: "Explain AI in simple terms"
});

console.log(response.output_text);

💬 5. Chat-style Conversation Example
Python
response = client.responses.create(
model="gpt-5.3",
input=[
{"role": "user", "content": "What is machine learning?"}
]
)

print(response.output_text)

🧩 6. Example with Instructions (System Prompt)
response = client.responses.create(
model="gpt-5.3",
input="Explain gravity like I'm 10 years old.",
temperature=0.7
)

print(response.output_text)

⚙️ 7. Useful Parameters
model → which AI model to use

input → your prompt

temperature → creativity (0 = strict, 1 = creative)

max_output_tokens → limit response length

🧪 8. More Advanced (JSON Output Example)
response = client.responses.create(
model="gpt-5.3",
input="Give me a JSON with name and age of a person"
)

print(response.output_text)
✅ Tips
Always keep your API key private

Use .env files for security in real projects

Handle errors with try/catch (JS) or try/except (Python)