Module 5: Getting Started with OpenAI API

What is the OpenAI API?

The OpenAI API allows you to access powerful large language models like GPT-3.5 and GPT-4 via a simple HTTP-based interface.

You can use it for:

• Chatbots
• Content creation
• Text summarization
• Translation
• Code generation
• Audio transcription
• Image generation
• Embedding generation

---

Create an OpenAI Account

1. Go to https://platform.openai.com
2. Sign up using your email, Google, or GitHub.
3. Navigate to https://platform.openai.com/account/api-keys
4. Click “Create new secret key”
5. Copy and store your key securely.

Warning

Your secret key starts with sk- and should never be shared publicly.

---

Install the OpenAI Python Package

pip install --upgrade openai

---

Set Up Your API Key in Python

You can use your API key in two ways:

Option 1: Set directly in code (for testing only)

import os
from openai import OpenAI

client = OpenAI(api_key="your-api-key-here")

Option 2: Use environment variables (recommended)

# In terminal
export OPENAI_API_KEY="your-api-key-here"

import os
from openai import OpenAI

client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

---

Available Functionalities in openai>=1.0.0

1. Chat Completion

response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain photosynthesis in simple words."}
    ]
)
print(response.choices[0].message.content)

---

2. Image Generation

response = client.images.generate(
    model="dall-e-3",
    prompt="A futuristic city floating in the sky",
    size="1024x1024",
    quality="standard",
    n=1
)
image_url = response.data[0].url
print(image_url)

---

3. Embeddings

response = client.embeddings.create(
    input="Machine learning is fun.",
    model="text-embedding-ada-002"
)
print(response.data[0].embedding)

---

4. Audio Transcription (Whisper)

with open("speech.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file
    )
print(transcript.text)

---

Summary

• Use OpenAI() to create a client with your API key.
• Modern usage recommends client.chat.completions.create() for chat interactions.
• You can also generate images, extract embeddings, and transcribe audio using a consistent client interface.