vision-test.py

# test out the GPT-4 Vision model

import base64
import requests
import os

from openai import OpenAI
client = OpenAI()
api_key = os.environ["OPENAI_API_KEY"]

# Function to encode the image
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')

# Path to your image
image_path = "waterfall.jpg"

# Getting the base64 string
base64_image = encode_image(image_path)

headers = {
  "Content-Type": "application/json",
  "Authorization": f"Bearer {api_key}"
}

payload = {
  "model": "gpt-4-vision-preview",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Describe this scene"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": f"data:image/jpeg;base64,{base64_image}",
            "detail": "low" # low has a flat rate of 65 tokens, recommended image size is 512x512
          }
        }
      ]
    }
  ],
  "max_tokens": 300
}

response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)

print(response.json())