OpenAI API

request_local.py

from openai import OpenAI
import os
import ipdb
import base64

api_key = os.getenv('OPENAI_API_KEY')
client = OpenAI()
client.api_key = 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 = "./dgh.jpeg"

# Getting the base64 string
base64_image = encode_image(image_path)


response = client.chat.completions.create(
  model="gpt-4o",
  messages=[
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "There are A number of person and B number of animal in this image. What is A and B. Answer in this in json format"}, 
        {
          "type": "image_url",
          "image_url": {
                "url": f"data:image/jpeg;base64,{base64_image}",
                "detail": "low"
          }
        },
      ],
    }
  ],
  max_tokens=200,
)

response.model_dump().keys() # dict_keys(['id', 'choices', 'created', 'model', 'object', 'service_tier', 'system_fingerprint', 'usage'])

print(response.model_dump_json())
# Get content
print(response.choices[0].model_dump()['message']['content'])

request_url.py

from openai import OpenAI
import os
import ipdb

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

response = client.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,
)

response.model_dump().keys() # dict_keys(['id', 'choices', 'created', 'model', 'object', 'service_tier', 'system_fingerprint', 'usage'])

# Get content
print(response.choices[0].model_dump()['message']['content'])