robot-project/image_read/image_read.py

import os
import base64
import cv2
import dashscope

# 各地域配置不同，请根据实际地域修改
dashscope.base_http_api_url = "https://dashscope.aliyuncs.com/api/v1"

camera_id = 10 # 摄像头ID

def capture_image_from_camera():
    cap = cv2.VideoCapture(camera_id)
    if not cap.isOpened():
        print(f"无法打开摄像头ID: {camera_id}")
        return None
    
    ret, frame = cap.read()
    cap.release()
    
    if not ret:
        print(f"无法捕获图像,camera_id: {camera_id}")
        return None
    
    _, buffer = cv2.imencode('.jpg', frame)
    image_base64 = base64.b64encode(buffer).decode('utf-8')
    return image_base64

image_base64 = capture_image_from_camera()
if image_base64 is None:
    print(f"摄像头捕获失败,camera_id: {camera_id}")
    exit(1)

messages = [
{
    "role": "user",
    "content": [
    {"image": f"data:image/jpeg;base64,{image_base64}"},
    {"text": "图中描绘的是什么景象?"}]
}]
response = dashscope.MultiModalConversation.call(
    # 若没有配置环境变量， 请用百炼API Key将下行替换为： api_key ="sk-xxx"
    # 各地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    api_key = os.getenv('DASHSCOPE_API_KEY'),
    model = 'qwen3.5-plus',  # 此处以qwen3.5-plus为例，可按需更换模型名称。模型列表：https://help.aliyun.com/zh/model-studio/models
    messages = messages
)
print(f'模型回复: {response.output.choices[0].message.content[0]["text"]}')