qqbot/pic_read.py

from openai import OpenAI
import requests
import base64
from config import key_get

siliflow_key = key_get('siliflow')

def pic_see(url):
  """
  调用图片识别api，获取群聊图片内容
  """
  # 1. 下载网络图片到本地临时文件
  try:
    response = requests.get(url)
    response.raise_for_status()  # 检查HTTP错误
  except requests.exceptions.RequestException as e:
    print(f"下载图片失败: {e}")
    return "图片识别失败"

  # 2. 保存为临时文件（例如保存到当前目录）
  img_path = "temp_image.jpg"  # 根据图片格式调整扩展名（jpg/png等）
  with open(img_path, "wb") as f:
    f.write(response.content)
  # 图片转base64编码
  with open(img_path, "rb") as path:
    try:
      base64_data = base64.b64encode(path.read()).decode("utf-8")
      data_uri = f"data:image/jpeg;base64,{base64_data}"
    except Exception as e:
      return "图片识别失败"


  client = OpenAI(
    base_url='https://api.siliconflow.cn/',
    api_key=siliflow_key,
  )

  completion = client.chat.completions.create(
    extra_headers={
      "HTTP-Referer": "<YOUR_SITE_URL>",  # Optional. Site URL for rankings on openrouter.ai.
      "X-Title": "<YOUR_SITE_NAME>",  # Optional. Site title for rankings on openrouter.ai.
    },
    extra_body={},
    model="Pro/Qwen/Qwen2.5-VL-7B-Instruct",
    messages=[
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "请为我详细描述这张图片的内容"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": data_uri
            }
          }
        ]
      }
    ]
  )
  ans = completion.choices[0].message.content
  print(ans)
  return (ans)