from qwen_vl_utils import process_vision_info
 
# sample from amazon.com
sample = {
  "product_name": "Hasbro Marvel Avengers-Serie Marvel Assemble Titan-Held, Iron Man, 30,5 cm Actionfigur",
  "catergory": "Toys & Games | Toy Figures & Playsets | Action Figures",
  "image": "https://m.media-amazon.com/images/I/81+7Up7IWyL._AC_SY300_SX300_.jpg"
}
 
# prepare message
messages = [{
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": sample["image"],
            },
            {"type": "text", "text": prompt.format(product_name=sample["product_name"], category=sample["catergory"])},
        ],
    }
]
 
def generate_description(sample, model, processor):
    messages = [
        {"role": "system", "content": [{"type": "text", "text": system_message}]},
        {"role": "user", "content": [
            {"type": "image","image": sample["image"]},
            {"type": "text", "text": prompt.format(product_name=sample["product_name"], category=sample["catergory"])},
        ]},
    ]
    # Preparation for inference
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)
    inputs = processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to(model.device)
    # Inference: Generation of the output
    generated_ids = model.generate(**inputs, max_new_tokens=256, top_p=1.0, do_sample=True, temperature=0.8)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    output_text = processor.batch_decode(
        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
    )
    return output_text[0]
 
# let's generate the description
base_description = generate_description(sample, model, processor)
print(base_description)
# you can disable the active adapter if you want to rerun it with
# model.disable_adapters()