import gradio as gr
from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Radiology-Infer-Mini", torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("prithivMLmods/Radiology-Infer-Mini")

def generate_report(image, text):
    # Prepare the message
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": image},
                {"type": "text", "text": text},
            ],
        }
    ]
    
    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("cpu")
    
    generated_ids = model.generate(**inputs, max_new_tokens=128)
    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]

interface = gr.Interface(
    fn=generate_report,
    inputs=[
        gr.Image(type="pil", label="Upload Image"),
        gr.Textbox(label="Enter Description/Query", placeholder="Enter your query here..."),
    ],
    outputs=gr.Textbox(label="Generated Report"),
    title="Pter.AI Report Generator",
    description="Upload a medical image and provide a description/query to generate a radiology report.",
)

interface.launch()