"type": "image",
"image": {
    "url": "https://image.com/img.jpg",
}

from pathlib import Path
from llama_cpp import Llama
from llama_cpp.llama_chat_format import Gemma3ChatHandler

def image_to_base64_uri(image: bytes | str):
  import base64
  import urllib.request as request

  if isinstance(image, bytes):
    data = base64.b64encode(image).decode('utf-8')
  else:
    with request.urlopen(image) as f:
      data = base64.b64encode(f.read()).decode('utf-8')
  return f'data:image/png;base64,{data}'

chat_handler = Gemma3ChatHandler(clip_model_path='path/to/mmproj')
llama = Llama(
    model_path='path/to/model',
    chat_handler=chat_handler,
    n_ctx=2048,  # n_ctx should be increased to accommodate the image embedding
)

messages = [
    {
        'role': 'user',
        'content': [
            {'type': 'text', 'text': 'please compare these pictures'},
            {'type': 'image_url', 'image_url': 'https://xxxx/img1.jpg'},
            {'type': 'image_url', 'image_url': {'url': 'https://xxxx/img2.png'}},
            {'type': 'image_url', 'image_url': image_to_base64_uri(Path('path/to/img3.jpg').read_bytes())},
            {'type': 'image_url', 'image_url': {'url': image_to_base64_uri(Path('path/to/img4.png').read_bytes())}},
            {'type': 'text', 'text': 'and then tell me which one looks the best'},
        ]
    }
]

output = llama.create_chat_completion(
    messages,
    stop=['<end_of_turn>', '<eos>'],
    max_tokens=500,
    stream=True,
)

for chunk in output:
  delta = chunk['choices'][0]['delta']
  if 'role' in delta:
    print(delta['role'], end=':\n')
  elif 'content' in delta:
    print(delta['content'], end='')

llama._sampler.close()
llama.close()

import json
from llama_cpp import Llama
from llama_cpp.llama_chat_format import Gemma3ChatHandler

chat_handler = Gemma3ChatHandler(clip_model_path='path/to/mmproj')
llama = Llama(
    model_path='path/to/model',
    chat_handler=chat_handler,
    n_ctx=2048,  # n_ctx should be increased to accommodate the image embedding
)


def analyze_image(image_id: str, description: str):
  print('image_id:', image_cache.get(image_id))
  print('description:', description)
  ...


image_cache = {'img_01': 'https://xxxx/img_01.jpg'}
function_table = {'analyze_image': analyze_image}

# input arg1
image_id = 'img_01'
# input arg2
question = f'Here is the image with ID `img_01`. Please analyze it.'

output = llama.create_chat_completion(
    [
        {
            'role': 'system',
            'content': '''You can call the following function:
- analyze_image(image_id: str, description: str)

You will be shown an image. First, analyze and describe its content in detail.
Then, return a function call with:
- the assigned image_id (provided in the input)
- a description of what the image shows (your own analysis)

Respond only with a JSON (without code blocks) function call like:
{
  "function": "analyze_image",
  "arguments": {
    "image_id": "<image id>",
    "description": "<description of the image>"
  }
}
'''
        },
        {
            'role': 'user',
            'content': [
                {'type': 'text', 'text': question},
                {'type': 'image_url', 'image_url': image_cache[image_id]},
            ]
        }
    ],
    stop=['<end_of_turn>', '<eos>'],
    max_tokens=500,
)

data = json.loads(output['choices'][0]['message']['content'])
result = function_table[data['function']](**data['arguments'])
...