Upload app.py with huggingface_hub

app.py

@@ -482,43 +482,111 @@ except Exception as e:
     deals_cache = process_deals_data(SAMPLE_DEALS)
     print(f"Initialized with {len(deals_cache)} sample deals")
 
+# Global variables for models
+classifier = None
+sentence_model = None
+tokenizer = None
+model = None
+simple_classify = None
+
 def classify_text(text, fetch_deals=True):
     """
     Classify the text using the model and fetch relevant deals
     """
-    global deals_cache
+    global deals_cache, classifier, sentence_model, tokenizer, model, simple_classify
     
     # Get the top categories based on the model type
     if using_recommended_models:
         # Using BART for zero-shot classification
-        result = classifier(text, categories, multi_label=True)
-        
-        # Extract categories and scores
-        top_categories = []
-        for i, (category, score) in enumerate(zip(result['labels'], result['scores'])):
-            if score > 0.1:  # Lower threshold for zero-shot classification
-                top_categories.append((category, score))
+        try:
+            result = classifier(text, categories, multi_label=True)
             
-            # Limit to top 3 categories
-            if i >= 2:
-                break
+            # Extract categories and scores
+            top_categories = []
+            for i, (category, score) in enumerate(zip(result['labels'], result['scores'])):
+                if score > 0.1:  # Lower threshold for zero-shot classification
+                    top_categories.append((category, score))
+                
+                # Limit to top 3 categories
+                if i >= 2:
+                    break
+        except Exception as e:
+            print(f"Error using zero-shot classification: {str(e)}")
+            # Fallback to simple keyword-based classification
+            top_categories = []
+            for category, terms in {
+                "electronics": ["electronics", "gadget", "device", "tech", "electronic"],
+                "computers": ["computer", "laptop", "desktop", "pc", "monitor"],
+                "mobile": ["phone", "mobile", "smartphone", "cell", "iphone", "android"],
+                "audio": ["audio", "headphone", "speaker", "earbud", "sound"],
+                "clothing": ["clothing", "clothes", "shirt", "pants", "dress", "wear"],
+                "footwear": ["shoe", "boot", "sneaker", "footwear", "sandal"],
+                "home": ["home", "furniture", "decor", "house", "living"],
+                "kitchen": ["kitchen", "cook", "appliance", "food", "dining"],
+                "toys": ["toy", "game", "play", "kid", "child"],
+                "sports": ["sport", "fitness", "exercise", "workout", "athletic"],
+                "beauty": ["beauty", "makeup", "cosmetic", "skin", "hair"],
+                "books": ["book", "read", "novel", "textbook", "ebook"]
+            }.items():
+                score = 0
+                for term in terms:
+                    if term in text.lower():
+                        score += 1
+                if score > 0:
+                    top_categories.append((category, score/5))
+            
+            # Sort by score
+            top_categories.sort(key=lambda x: x[1], reverse=True)
+            top_categories = top_categories[:3]  # Limit to top 3
+    elif simple_classify is not None:
+        # Using simple keyword-based classification
+        top_categories = simple_classify(text)
     else:
-        # Using the original classification model
-        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
-        
-        # Get the model prediction
-        with torch.no_grad():
-            outputs = model(**inputs)
-            predictions = torch.sigmoid(outputs.logits)
-        
-        # Get the top categories
-        top_categories = []
-        for i, score in enumerate(predictions[0]):
-            if score > 0.5:  # Threshold for multi-label classification
-                top_categories.append((categories[i], score.item()))
-        
-        # Sort by score
-        top_categories.sort(key=lambda x: x[1], reverse=True)
+        try:
+            # Using the original classification model
+            inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+            
+            # Get the model prediction
+            with torch.no_grad():
+                outputs = model(**inputs)
+                predictions = torch.sigmoid(outputs.logits)
+            
+            # Get the top categories
+            top_categories = []
+            for i, score in enumerate(predictions[0]):
+                if score > 0.5:  # Threshold for multi-label classification
+                    top_categories.append((categories[i], score.item()))
+            
+            # Sort by score
+            top_categories.sort(key=lambda x: x[1], reverse=True)
+        except Exception as e:
+            print(f"Error using local model: {str(e)}")
+            # Fallback to simple keyword-based classification
+            top_categories = []
+            for category, terms in {
+                "electronics": ["electronics", "gadget", "device", "tech", "electronic"],
+                "computers": ["computer", "laptop", "desktop", "pc", "monitor"],
+                "mobile": ["phone", "mobile", "smartphone", "cell", "iphone", "android"],
+                "audio": ["audio", "headphone", "speaker", "earbud", "sound"],
+                "clothing": ["clothing", "clothes", "shirt", "pants", "dress", "wear"],
+                "footwear": ["shoe", "boot", "sneaker", "footwear", "sandal"],
+                "home": ["home", "furniture", "decor", "house", "living"],
+                "kitchen": ["kitchen", "cook", "appliance", "food", "dining"],
+                "toys": ["toy", "game", "play", "kid", "child"],
+                "sports": ["sport", "fitness", "exercise", "workout", "athletic"],
+                "beauty": ["beauty", "makeup", "cosmetic", "skin", "hair"],
+                "books": ["book", "read", "novel", "textbook", "ebook"]
+            }.items():
+                score = 0
+                for term in terms:
+                    if term in text.lower():
+                        score += 1
+                if score > 0:
+                    top_categories.append((category, score/5))
+            
+            # Sort by score
+            top_categories.sort(key=lambda x: x[1], reverse=True)
+            top_categories = top_categories[:3]  # Limit to top 3
     
     # Format the classification results
     if top_categories: