Local Base64 Images as Input

main.py

from IPython.display import Image, display
image_path = 'images/triangle2.jpg'
display(Image(image_path, width=400))

import base64
def encode_image(image_path):
    with open(image_path, 'rb') as image_file:
        image_binary_data = image_file.read()
        return base64.b64encode(image_binary_data).decode('utf-8')


base64_image = encode_image(image_path)
system_message = 'You are a math tutor'
# prompt = 'What is the perimeter of the triangle?'
prompt = 'Solve this problem.'

model = 'gpt-4o'

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)