基于OpenAI API接口向GPT4v上传图像进行图像分析

合集 - 一些代码(14)

1.MXnet深度学习环境及GluonCV深度学习包的安装2023-07-262.Python遍历文件夹中的文件并根据文件类型将文件分类储存2023-09-063.对ERA5数据进行区域提取及时间处理2023-09-134.基于街景全景照片数据计算SVF（天空开阔度）2023-09-225.基于transbigdata包获取交通线路和站点的邻接表及shp文件2023-09-226.gephi导入networkx：使用经纬度绘图并根据情景计算节点指标与网络整体指标（关联gephi导入networkx一文）2023-09-227.备忘：爬取poi代码2023-09-238.基于Python+MXnet预训练模型的街景图像语义分割代码2023-11-079.基于Python Sklearn的机器学习代码（备忘）2023-12-09

10.基于OpenAI API接口向GPT4v上传图像进行图像分析2024-06-02

11.保持校园网自动登录的代码备忘: 基于webdriver和chrome2024-07-0312.Python Selenium+cookie+XPATH爬取数据2024-07-1013.Python web自动化爬虫-selenium/处理验证码/Xpath2024-07-1814.0803/代码2024-08-03

收起

import openai
import base64
from openai import OpenAI


client = OpenAI(
    api_key='xxxxxxxxx',  
    base_url='https://api.openai.com/v1'#可根据镜像站修改
)

#图片转base64函数
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')
 
#输入图片路径
image_path = "xxxxxx"
 
#原图片转base64
base64_image = encode_image(image_path)


#提交信息至GPT4o
response = client.chat.completions.create(
    model="xxx",#选择模型
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content":[
            {
          "type": "text",
          "text": "xxxxxxxxxxxxxxxxxx"
        },
                    {
          "type": "image_url",
          "image_url":{
            "url": f"data:image/jpeg;base64,{base64_image}"
          }
        },
        ]
        }
    ],
    stream=True,
)

reply = ""
for res in response:
    content = res.choices[0].delta.content
    if content:
        reply += content
        print(content)

print('reply:',reply)