多模态模型 (Multimodal)

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.nonelinear.com/v1",
    api_key=os.environ.get("Nonelinear_API_KEY"),
)

image_url = (
    "https://ark-project.tos-cn-beijing.volces.com/doc_image/"
    "seedream4_imageToimage.png"
)

response = client.chat.completions.create(
    model="gpt-5.4-nano",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "请描述这张图片的内容"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": image_url
                    }
                }
            ]
        }
    ]
)
print(response.choices[0].message.content)

import os
import base64
from openai import OpenAI

client = OpenAI(
    base_url="https://api.nonelinear.com/v1",
    api_key=os.environ.get("Nonelinear_API_KEY"),
)

# 读取并编码本地图片
with open("image.jpg", "rb") as f:
    b64_image = base64.b64encode(f.read()).decode("utf-8")

response = client.chat.completions.create(
    model="gpt-5.4-nano",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "请描述这张图片的内容"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/jpeg;base64,{b64_image}"
                    }
                }
            ]
        }
    ]
)
print(response.choices[0].message.content)