Files
ocr/Test103.py

80 lines
2.8 KiB
Python
Raw Permalink Normal View History

2025-08-14 16:04:59 +08:00
from zhipuai import ZhipuAI
client = ZhipuAI(api_key="78dc1dfe37e04f29bd4ca9a49858a969.gn7TIZTfzpY35nx9") # 填写您自己的APIKey
from utils.image_utils import encode_image
reasoning_content = "" # 定义完整思考过程
answer_content = "" # 定义完整回复
is_answering = False # 判断是否结束思考过程并开始回复
base64_image = encode_image(r"D:\ocr\QQ截图20250814093022.jpg")
prompt = """
你是一个初中数学图片的描述专家请将图片中的内容转换为文本
1注意数学公式需要用latex格式输出注意只输出文本内容不要输出任何解释
2如果图片中有图形请结合题干内容对图形进行描述只要描述不需要任何解释
3如果图片中有几何图形识别图片中的几何图形如三角形圆形矩形等请结合题干内容对图形进行详细描述包括形状大小位置关系等
3如果图片中是坐标系分析抛物线的开口方向和经过的象限并详细描述识别图片中的坐标系类型如直角坐标系极坐标系等
4要以markdown格式输出
输出格式为
题干
图形描述
"""
completion = client.chat.completions.create(
model="glm-4.1v-thinking-flash", # 填写需要调用的模型名称
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": prompt
},
{
"type": "image_url",
"image_url": {
# "url" : "https://dsideal.obs.cn-north-1.myhuaweicloud.com/wb/math.jpg"
'url': f'data:image/jpeg;base64,{base64_image}'
}
}
]
}
],
stream=True,
)
print("\n" + "=" * 20 + "思考过程" + "=" * 20 + "\n")
for chunk in completion:
# 如果chunk.choices为空则打印usage
if not chunk.choices:
print("\nUsage:")
print(chunk.usage)
else:
delta = chunk.choices[0].delta
# 打印思考过程
if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
print(delta.reasoning_content, end='', flush=True)
reasoning_content += delta.reasoning_content
else:
# 开始回复
if delta.content != "" and is_answering is False:
print("\n" + "=" * 20 + "完整回复" + "=" * 20 + "\n")
is_answering = True
# 打印回复过程
print(delta.content, end='', flush=True)
answer_content += delta.content
# print("=" * 20 + "完整思考过程" + "=" * 20 + "\n")
# print(reasoning_content)
# print("=" * 20 + "完整回复" + "=" * 20 + "\n")
# 保存成QvqResult.txt
with open("QvqResult.txt", "w", encoding='utf-8') as f:
f.write(answer_content)
# print(response.choices[0].message)