Vision Language Models

{
  "role": "user",
  "content": [
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/image.png",
        "detail": "high"
      }
    },
    {
      "type": "text",
      "text": "Please describe the scene in the image."
    }
  ]
}

{
  "role": "user",
  "content": [
    {
      "type": "image_url",
      "image_url": {
        "url": "data:image/jpeg;base64,{base64_image}",
        "detail": "low"
      }
    },
    {
      "type": "text",
      "text": "What text is present in the image?"
    }
  ]
}

import base64
from PIL import Image
import io

def image_to_base64(image_path):
    with Image.open(image_path) as img:
        buffered = io.BytesIO()
        img.save(buffered, format="JPEG")
        return base64.b64encode(buffered.getvalue()).decode('utf-8')

base64_image = image_to_base64("path/to/your/image.jpg")

{
  "role": "user",
  "content": [
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/image1.png"
      }
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "data:image/jpeg;base64,{base64_image}"
      }
    },
    {
      "type": "text",
      "text": "Compare the common features of these two images."
    }
  ]
}

from openai import OpenAI

client = OpenAI(api_key="YOUR_KEY", base_url="https://api.novita.ai/openai")

response = client.chat.completions.create(
    model="qwen/qwen2.5-vl-72b-instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/cityscape.jpg"
                    }
                },
                {
                    "type": "text",
                    "text": "Describe the main buildings in the image."
                }
            ]
        }
    ],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

response = client.chat.completions.create(
    model="qwen/qwen2.5-vl-72b-instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/product1.jpg"
                    }
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/product2.jpg"
                    }
                },
                {
                    "type": "text",
                    "text": "Please compare the key differences between these two products."
                }
            ]
        }
    ],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="", flush=True)