ask gpt4v

ask gpt4v via openai api
files = sorted(glob.glob("../data/cap_*.jpg"))
len(files), files[:9]
(482,
 ['../data/cap_2024.09.28_15:59:06_Presidentinlinna.jpg',
  '../data/cap_2024.09.28_16:00:11_Presidentinlinna.jpg',
  '../data/cap_2024.09.28_16:01:16_Etelasatama.jpg',
  '../data/cap_2024.09.28_16:02:21_Etelasatama.jpg',
  '../data/cap_2024.09.28_16:05:31_Olympiaterminaali.jpg',
  '../data/cap_2024.09.28_16:06:36_Olympiaterminaali.jpg',
  '../data/cap_2024.09.28_16:07:41_Torni.jpg',
  '../data/cap_2024.09.28_16:09:51_Tuomiokirkko.jpg',
  '../data/cap_2024.09.28_16:15:11_Presidentinlinna.jpg'])
Image(files[-1])


source

encode_image

 encode_image (fname:str)

encode an image file as base64

base64_image = encode_image(files[0])
base64_image[:9]
'/9j/4AAQS'
response = openai.chat.completions.create(
  model="gpt-4o",
  messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": question,},
            {
                "type": "image_url",
                "image_url": {"url": f"data:image/jpeg;base64,{encode_image(files[-1])}", "detail":"high",},
            },
        ],
    }],
  max_tokens=300,
)

source

info

 info (response)

source

ask_gpt4v

 ask_gpt4v (fn:str)
ask_gpt4v(files[-1])
info(response)
{'timestamp': '2024-10-30T12:45:22',
 'location': 'Tuomiokirkko',
 'dimensions': {'width': 1280, 'height': 720},
 'buildings': {'number_of_buildings': 15,
  'building_height_range': '1-6 stories'},
 'vehicles': {'number_of_vehicles': 0},
 'waterbodies': {'visible': False},
 'street_lights': {'number_of_street_lights': 0},
 'people': {'approximate_number': 0},
 'lighting': {'time_of_day': 'day', 'artificial_lighting': 'none'},
 'visibility': {'clear': True},
 'sky': {'visible': True, 'light_conditions': 'daylight'}}