pythonbeginner

OpenAI GPT-4 Vision Image Analysis

Analyse images from URLs or base64 with GPT-4 Vision for structured visual understanding.

pythonPress ⌘/Ctrl + Shift + C to copy

from openai import OpenAI
import base64
from pathlib import Path

client = OpenAI()

# Analyse from URL
response_url = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role':'user','content':[{'type':'text','text':'What is in this chart? Summarise key metrics.'},{'type':'image_url','image_url':{'url':'https://upload.wikimedia.org/wikipedia/commons/thumb/b/b6/Image_created_with_a_mobile_phone.png/640px-Image_created_with_a_mobile_phone.png','detail':'high'}}]}],
    max_tokens=300,
)
print(response_url.choices[0].message.content)

# Analyse local file
img_b64 = base64.b64encode(Path('chart.png').read_bytes()).decode()
response_local = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role':'user','content':[{'type':'text','text':'Describe this image.'},{'type':'image_url','image_url':{'url':f'data:image/png;base64,{img_b64}'}}]}],
    max_tokens=200,
)
print(response_local.choices[0].message.content)