在调用api进行图片推理时，如何从本地读取图片呢

[yutmdfeng]

System Info / 系統信息

Traceback (most recent call last): File "C:\Users\admin\glm-cookbook\test1.py", line 7, in response = client.chat.completions.create( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Anaconda\Anaconda3\envs\GLM4V\Lib\site-packages\zhipuai\api_resource\chat\completions.py", line 48, in create return self._post( ^^^^^^^^^^^ File "D:\Anaconda\Anaconda3\envs\GLM4V\Lib\site-packages\zhipuai\core_http_client.py", line 292, in post return self.request( ^^^^^^^^^^^^^ File "D:\Anaconda\Anaconda3\envs\GLM4V\Lib\site-packages\zhipuai\core_http_client.py", line 251, in request raise self._make_status_error(err.response) from None zhipuai.core._errors.APIRequestFailedError: Error code: 400, with error text {"error":{"code":"1210","message":"图片输入格式/解析错误"}}

Information / 问题信息

• [X] The official example scripts / 仓库中的示例脚本
• [ ] My own modified scripts / 我自己修改的脚本和任务

Reproduction / 复现过程

本地图片文件的路径

local_image_path = "C:/Users/admin/OneDrive/pic/download/rail/Snipaste_2024-04-18_21-33-56.png"

response = client.chat.completions.create( model="glm-4v", # 填写需要调用的模型名称 messages=[ { "role": "user", "content": [ { "type": "text", "text": "图里有什么" }, { "type": "image_url", "image_url": { "url" : local_image_path } } ] } ] )

Expected behavior / 期待表现

怎么从本地读取图片