Explore GPT-4o's Vision Capabilities

main.py

from dotenv import load_dotenv
api_key = os.getenv("OPENAI_API_KEY")
from openai import OpenAI

client = OpenAI()

model = 'gpt-4o'

response = client.chat.completions.create(
    model = model,
    messages = [
        {'role': 'system', 'content': 'You are a Sci-Fi writer'},
        {'role': 'user', 'content': 'Write a short story about the life on Earth in the year 2120'}
    ]
)

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

# Using Local Base64 Images as Input
import base64
import requests

model = 'gpt-4o'

system_message = 'You respond in english and then translate your response in dutch'
prompt = 'Write a short and concise description of this image'
image_url = 'https://images.pexels.com/photos/20659792/pexels-photo-20659792/free-photo-of-portrait-of-geese.jpeg'
image_data = requests.get(image_url).content
base64_image = base64.b64encode(image_data).decode('utf-8')

response = client.chat.completions.create(
    model = model,
    messages = [
        {'role': 'system', 'content': system_message},
        {'role': 'user', 'content': [
            {'type': 'text', 'text': prompt},
            {'type': 'image_url', 'image_url': {
                'url': f'data:image/jpg;base64,{base64_image}'}
            }
        ]}
    ],
    temperature = 0.0
)

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