added the code ✅✅

app.py

@@ -5,54 +5,52 @@ from PIL import Image
 import logging
 
 # Configure logging
-logging.basicConfig(level=logging.INFO)
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 logger = logging.getLogger(__name__)
 
-# Load smaller BLIP model (more reliable)
-def load_model():
-    try:
-        device = "cuda" if torch.cuda.is_available() else "cpu"
-        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  # More stable than float16
-        ).to(device)
+class MedicalAnalyzer:
+    def __init__(self):
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+        self.model = None
+        self.processor = None
         
-        logger.info("Model loaded successfully")
-        return model, processor, device
-    except Exception as e:
-        logger.error(f"Model loading failed: {e}")
-        raise
+    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")
 
-try:
-    model, processor, device = load_model()
-except Exception as e:
-    raise gr.Error(f"Failed to load model. Please check:\n1. Internet connection\n2. Disk space (5GB+ needed)\n3. Try again later")
+analyzer = MedicalAnalyzer()
 
-def analyze_medical_image(image, question, history=[]):
+def analyze_medical_image(image, question):
     try:
         if not image:
-            return "⚠️ Please upload a medical image", history
+            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:"
+        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 = model.generate(**inputs, max_new_tokens=100)
+            outputs = analyzer.model.generate(**inputs, max_new_tokens=100)
         
-        result = processor.decode(outputs[0], skip_special_tokens=True)
-        result = result.replace(prompt, "").strip()
-        
-        return result, history + [(question, result)]
+        result = analyzer.processor.decode(outputs[0], skip_special_tokens=True)
+        return result.replace(prompt, "").strip()
     
     except Exception as e:
-        logger.error(f"Error: {e}")
-        return f"❌ Analysis failed: {str(e)}", history
+        logger.error(f"Analysis error: {e}")
+        return f"❌ Analysis failed: {str(e)}"
 
-# Simple Gradio Interface
+# Simplified Gradio Interface
 with gr.Blocks(title="Medical Image Analyzer") as app:
     gr.Markdown("# 🩺 Medical Image Analyzer")
     
@@ -63,13 +61,22 @@ with gr.Blocks(title="Medical Image Analyzer") as app:
             submit_btn = gr.Button("Analyze")
         
         with gr.Column():
-            chatbot = gr.Chatbot(label="Analysis Report")
+            output = gr.Textbox(label="Analysis Result", interactive=False)
     
     submit_btn.click(
         analyze_medical_image,
-        [image_input, question_input, chatbot],
-        [chatbot, chatbot]
+        inputs=[image_input, question_input],
+        outputs=output
     )
 
 if __name__ == "__main__":
-    app.launch(server_name="0.0.0.0", share=False)
+    try:
+        analyzer.load_model()
+        app.launch(
+            server_name="0.0.0.0",
+            server_port=7860,
+            show_error=True
+        )
+    except Exception as e:
+        logger.error(f"Application failed: {e}")
+        raise gr.Error("Application failed to start. Please check the logs.")