File size: 2,238 Bytes
e0f6bc4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
import cv2
import base64
import requests
import numpy as np
META_PROMPT = '''
- For any marks mentioned in your answer, please highlight them with [].
'''
API_URL = "https://api.openai.com/v1/chat/completions"
def encode_image_to_base64(image: np.ndarray) -> str:
"""
Encodes an image into a base64-encoded string in JPEG format.
Parameters:
image (np.ndarray): The image to be encoded. This should be a numpy array as
typically used in OpenCV.
Returns:
str: A base64-encoded string representing the image in JPEG format.
"""
success, buffer = cv2.imencode('.jpg', image)
if not success:
raise ValueError("Could not encode image to JPEG format.")
encoded_image = base64.b64encode(buffer).decode('utf-8')
return encoded_image
def compose_headers(api_key: str) -> dict:
return {
"Content-Type": "application/json",
"Authorization": f"Bearer {api_key}"
}
def compose_payload(image: np.ndarray, prompt: str) -> dict:
base64_image = encode_image_to_base64(image)
return {
"model": "gpt-4-vision-preview",
"messages": [
{
"role": "user",
"content": [
{
"role": "system",
"content": [
META_PROMPT
]
},
{
"type": "text",
"text": prompt
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{base64_image}"
}
}
]
}
],
"max_tokens": 800
}
def prompt_image(api_key: str, image: np.ndarray, prompt: str) -> str:
headers = compose_headers(api_key=api_key)
payload = compose_payload(image=image, prompt=prompt)
response = requests.post(url=API_URL, headers=headers, json=payload).json()
if 'error' in response:
raise ValueError(response['error']['message'])
return response['choices'][0]['message']['content']
|