How to Use the GPT-4o API for Vision and Text?

What is GPT-4o?

GPT-4o is OpenAI’s latest and greatest AI model. This isn’t just another step in AI chatbots; it’s a leap forward with a groundbreaking feature called multimodal capabilities.

GPT-4o

• Text: This remains a core strength, allowing GPT-4o to converse, answer your questions, and generate creative text formats like poems or code.
• Audio: Imagine playing GPT-4o a song and having it analyze the music, describe the emotions it evokes, or even write lyrics inspired by it! GPT-4o can understand the spoken word, including tone and potentially background noise.
• Vision: Show GPT-4o a picture, and it can analyze the content, describe the scene, or even tell you a story based on the image. This opens doors for applications like image classification or generating captions for videos.

How to Use the GPT-4o API for Vision and Text?

Let’s Get started 🚀

API for Text Model 🗒️

• Installing necessary library

!pip install openai

• Importing openai library and Authentication

import openai
openai.api_key  = "<Your API KEY>"

• For Chat Completion

response = openai.chat.completions.create(
  model="gpt-4o",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"},
    {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
    {"role": "user", "content": "Where was it played?"}
  ]
)

• Output

print(response.choices[0].message.content)

API for Vision Model 🖼️

• For Chat Completion

response = openai.chat.completions.create(
  model="gpt-4o",
  messages=[
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "What’s in this image?"},
        {
          "type": "image_url",
          "image_url": {
            "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
          },
        },
      ],
    }
  ],
  max_tokens=300,
)

• Output

print(response.choices[0])

I hope you liked this article; if you have any suggestions or feedback, then comment below. For more articles like this, explore our blog section today!

You can Follow me on,

• GitHub
• Kaggle