updated the code ✅✅

app.py

@@ -1,60 +1,136 @@
 import gradio as gr
-from transformers import T5ForConditionalGeneration, AutoTokenizer
-
-# Load the T5 model and tokenizer
-model = T5ForConditionalGeneration.from_pretrained("t5-small")
-tokenizer = AutoTokenizer.from_pretrained("t5-small")
-
-def generate_response(image, text, specialization):
-    """
-    Generate a response based on the uploaded image and/or user query.
-    """
-    if not text.strip():
-        return "Please enter a valid query."
-
-    # Prepare the input text
-    input_text = f"Specialization: {specialization}\n{text}"
-    inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True)
-
-    # Generate the response
-    outputs = model.generate(**inputs, max_new_tokens=128)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    return response
+from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
+import torch
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Load model and processor with cache
+@gr.Cache()
+def load_model():
+    try:
+        model = Qwen2VLForConditionalGeneration.from_pretrained(
+            "prithivMLmods/Radiology-Infer-Mini",
+            torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+            device_map="auto"
+        )
+        processor = AutoProcessor.from_pretrained("prithivMLmods/Radiology-Infer-Mini")
+        return model, processor
+    except Exception as e:
+        logger.error(f"Error loading model: {e}")
+        raise
+
+model, processor = load_model()
+
+def generate_response(image, text, specialization, history=None):
+    """Generate response combining image and text inputs with proper error handling."""
+    try:
+        # Validate inputs
+        if not image and not text.strip():
+            return "⚠️ Please provide either an image or a text query.", history
+        
+        # Prepare messages with specialization context
+        messages = [{
+            "role": "system",
+            "content": f"You are a {specialization} medical assistant. Provide professional, accurate analysis in clear language."
+        }]
+        
+        content = []
+        if image:
+            content.append({"type": "image", "image": image})
+        if text.strip():
+            content.append({"type": "text", "text": text})
+        
+        messages.append({"role": "user", "content": content})
+
+        # Process inputs
+        inputs = processor(
+            text=processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True),
+            images=[image] if image else None,
+            return_tensors="pt"
+        ).to(model.device)
+
+        # Generate response
+        generated_ids = model.generate(
+            **inputs,
+            max_new_tokens=256,
+            temperature=0.7,
+            repetition_penalty=1.1,
+            eos_token_id=processor.tokenizer.eos_token_id
+        )
+        
+        response = processor.batch_decode(
+            generated_ids[:, inputs.input_ids.shape[1]:],
+            skip_special_tokens=True,
+            clean_up_tokenization_spaces=False
+        )[0]
+
+        # Format history
+        formatted_history = (history or []) + [(text, response)]
+        return response, formatted_history
+
+    except Exception as e:
+        logger.error(f"Generation error: {e}")
+        return f"❌ Error processing request: {str(e)}", history
 
 # Gradio Interface
-with gr.Blocks() as app:
-    gr.Markdown("# 🩺 AI Doctor Assistant")
-    gr.Markdown(
-        "Upload a medical image (e.g., X-ray, MRI) and/or ask a health-related question. "
-        "Select a specialization for more accurate responses."
-    )
+with gr.Blocks(theme=gr.themes.Soft()) as app:
+    gr.Markdown("""
+    # 🩺 AI Medical Assistant
+    **Upload medical images and ask questions** for analysis in various specialties.
+    """)
 
     with gr.Row():
-        image_input = gr.Image(type="pil", label="Upload Medical Image (Optional)")
-        specialization = gr.Dropdown(
-            choices=["general", "radiology", "cardiology", "neurology", "pediatrics"],
-            value="general",
-            label="Specialization"
-        )
+        with gr.Column(scale=1):
+            specialization = gr.Dropdown(
+                label="Medical Specialty",
+                choices=["General Practice", "Radiology", "Cardiology", "Neurology", "Pediatrics"],
+                value="General Practice"
+            )
+            image_input = gr.Image(type="pil", label="Upload Medical Image", sources=["upload", "clipboard"])
+        
+        with gr.Column(scale=2):
+            chatbot = gr.Chatbot(height=400, label="Consultation History")
+            text_input = gr.Textbox(
+                label="Patient Query",
+                placeholder="Describe symptoms or ask about the image...",
+                lines=3
+            )
+            submit_btn = gr.Button("Submit", variant="primary")
 
-    text_input = gr.Textbox(
-        label="Enter Your Query",
-        placeholder="Type your health-related question here..."
-    )
+    # Examples
+    gr.Examples(
+        examples=[
+            ["Radiology", "Explain this chest X-ray finding.", "![image/png](https://cdn-uploads.huggingface.co/production/uploads/669d65ab8580d17cb6beabc0/eg2_EACmEhtkFqp3alrbm.png)
 
-    response_output = gr.Textbox(
-        label="AI Doctor's Response",
-        interactive=False
-    )
+"],
+            ["Cardiology", "Interpret these ECG results.", "![image/png](https://cdn-uploads.huggingface.co/production/uploads/669d65ab8580d17cb6beabc0/jOmU2DXOnnU0jivCA6xWI.png)
 
-    submit_button = gr.Button("Get Response")
+"]
+        ],
+        inputs=[specialization, text_input, image_input]
+    )
 
-    submit_button.click(
+    # Event handling
+    submit_event = text_input.submit(
         fn=generate_response,
-        inputs=[image_input, text_input, specialization],
-        outputs=[response_output]
+        inputs=[image_input, text_input, specialization, chatbot],
+        outputs=[text_input, chatbot]
+    )
+    
+    submit_btn.click(
+        fn=generate_response,
+        inputs=[image_input, text_input, specialization, chatbot],
+        outputs=[text_input, chatbot]
+    )
+
+    # Clear inputs after submission
+    submit_event.then(
+        lambda: ("", None),
+        outputs=[text_input, image_input]
     )
 
-# Launch the app
-app.launch()
+if __name__ == "__main__":
+    app.launch(server_name="0.0.0.0" if torch.cuda.is_available() else "127.0.0.0")