laya-vision

import laya
from PIL import Image

agent = laya.load_vlm("thaitea/laya-vision-smolvlm-256m")   # downloads from the Hub
result = agent.predict(
    {"image": Image.open("photo.jpg"), "note": "customer says it arrived broken"},
    {
        "damaged":  {"type": "noul",   "instructions": "Does the item in the photo look damaged?"},
        "category": {"type": "choice", "instructions": "What kind of item is this?",
                     "criteria": ["electronics", "clothing", "furniture", "food", "other"]},
    },
)
print(result["answers"]["damaged"]["noul"], result["answers"]["category"]["choice"])