gpt-4-turbo-2024-04-09で手書き画像から文字認識を試してみた

import os
from dotenv import load_dotenv
from openai import OpenAI
import base64
import requests

load_dotenv()

# OpenAI API Key
api_key = os.environ.get("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 = "./image/tegaki.png"

# Getting the base64 string
base64_image = encode_image(image_path)

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

payload = {
"model": "gpt-4-turbo", # gpt-4-turbo-2024-04-09 と同等
"messages": [
    {
    "role": "user",
    "content": [
        {
        "type": "text",
        "text": "画像に何がかかれている?"
        },
        {
        "type": "image_url",
        "image_url": {
            "url": f"data:image/jpeg;base64,{base64_image}"
        }
        }
    ]
    }
],
"max_tokens": 300
}

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

response_json = response.json()
print(f"response_txt: ", response_json["choices"][0]["message"]["content"])