added the model code ✅✅

app.py

@@ -5,45 +5,56 @@ from PIL import Image
 import logging
 
 # Configure logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
 logger = logging.getLogger(__name__)
 
-class MedicalAnalyzer:
-    def __init__(self):
-        self.device = "cuda" if torch.cuda.is_available() else "cpu"
-        self.model = None
-        self.processor = None
-        
-    def load_model(self):
-        try:
-            logger.info(f"Loading model on {self.device}...")
-            self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-            self.model = BlipForConditionalGeneration.from_pretrained(
-                "Salesforce/blip-image-captioning-base",
-                torch_dtype=torch.float32
-            ).to(self.device)
-            logger.info("Model loaded successfully")
-        except Exception as e:
-            logger.error(f"Model loading failed: {e}")
-            raise RuntimeError(f"Model loading failed. Please check:\n1. Internet connection\n2. Disk space (1GB+ needed)\n3. Try: pip install -r requirements.txt")
+# Initialize model components
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+MODEL_LOADED = False
 
-analyzer = MedicalAnalyzer()
+try:
+    logger.info(f"Loading model on {DEVICE}...")
+    processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+    model = BlipForConditionalGeneration.from_pretrained(
+        "Salesforce/blip-image-captioning-base",
+        torch_dtype=torch.float32
+    ).to(DEVICE)
+    MODEL_LOADED = True
+    logger.info("Model loaded successfully")
+except Exception as e:
+    logger.error(f"Model loading failed: {e}")
+    raise RuntimeError(
+        "Model failed to load. Please:\n"
+        "1. Check internet connection\n"
+        "2. Verify at least 1GB disk space\n"
+        "3. Try: pip install -r requirements.txt\n"
+        "4. Restart your runtime"
+    )
 
-def analyze_medical_image(image, question):
+def analyze_medical_image(image: Image.Image, question: str) -> str:
+    """Analyze medical image with optional question"""
+    if not MODEL_LOADED:
+        return "❌ Model not available. Please check server logs."
+    
     try:
         if not image:
             return "⚠️ Please upload a medical image"
         
-        if analyzer.model is None:
-            analyzer.load_model()
+        # Medical-focused prompt
+        prompt = (
+            f"Question: As a doctor, {question if question else 'describe any abnormalities in this medical image'} "
+            "Answer professionally:"
+        )
         
-        prompt = f"Question: As a doctor, {question if question else 'describe any abnormalities in this medical image'} Answer:"
-        inputs = analyzer.processor(image, prompt, return_tensors="pt").to(analyzer.device)
+        inputs = processor(image, prompt, return_tensors="pt").to(DEVICE)
         
         with torch.no_grad():
-            outputs = analyzer.model.generate(**inputs, max_new_tokens=100)
+            outputs = model.generate(**inputs, max_new_tokens=100)
         
-        result = analyzer.processor.decode(outputs[0], skip_special_tokens=True)
+        result = processor.decode(outputs[0], skip_special_tokens=True)
         return result.replace(prompt, "").strip()
     
     except Exception as e:
@@ -51,17 +62,31 @@ def analyze_medical_image(image, question):
         return f"❌ Analysis failed: {str(e)}"
 
 # Simplified Gradio Interface
-with gr.Blocks(title="Medical Image Analyzer") as app:
+with gr.Blocks(
+    title="Medical Image Analyzer",
+    css=".gradio-container {max-width: 800px !important}"
+) as app:
     gr.Markdown("# 🩺 Medical Image Analyzer")
     
     with gr.Row():
         with gr.Column():
-            image_input = gr.Image(type="pil", label="Upload Scan/X-ray")
-            question_input = gr.Textbox(label="Clinical Question (optional)")
-            submit_btn = gr.Button("Analyze")
+            image_input = gr.Image(
+                type="pil",
+                label="Upload Scan/X-ray",
+                sources=["upload", "clipboard"]
+            )
+            question_input = gr.Textbox(
+                label="Clinical Question (optional)",
+                placeholder="Describe symptoms or ask about findings..."
+            )
+            submit_btn = gr.Button("Analyze", variant="primary")
         
         with gr.Column():
-            output = gr.Textbox(label="Analysis Result", interactive=False)
+            output = gr.Textbox(
+                label="Analysis Result",
+                interactive=False,
+                lines=10
+            )
     
     submit_btn.click(
         analyze_medical_image,
@@ -71,7 +96,6 @@ with gr.Blocks(title="Medical Image Analyzer") as app:
 
 if __name__ == "__main__":
     try:
-        analyzer.load_model()
         app.launch(
             server_name="0.0.0.0",
             server_port=7860,