基于Qwen2.5-VL底座训练的统一多模态向量模型，支持文本、图片、视频单模态/混合模态输入，输出统一表征向量，适用于跨模态检索、图搜、视频检索、图像聚类、复杂多模态信息检索、打标等场景
curl https://api.yourplatform.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "undefined",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": true
}'