Upload app.py with huggingface_hub

app.py

@@ -142,76 +142,57 @@ def classify_text(text, fetch_deals=True):
                 deals_data = fetch_deals_data(num_pages=2)  # Limit to 2 pages for faster response
                 deals_cache = process_deals_data(deals_data)
             
-            # Direct approach to find relevant deals
-            headphone_terms = ['headphone', 'headphones', 'earbuds', 'earphones', 'earpods', 'airpods', 'audio', 'bluetooth', 'wireless']
-            laptop_terms = ['laptop', 'notebook', 'computer', 'macbook', 'chromebook', 'pc']
-            tv_terms = ['tv', 'television', 'smart tv', 'roku', 'streaming']
-            kitchen_terms = ['kitchen', 'appliance', 'mixer', 'blender', 'toaster', 'microwave', 'oven']
+            # Extract query terms and expand with related terms
+            query_terms = text.lower().split()
+            expanded_terms = list(query_terms)
             
-            # Determine which category to search for
-            search_terms = []
-            if 'headphone' in text.lower() or any(term in text.lower() for term in headphone_terms):
-                search_terms = headphone_terms
-                print("Searching for headphone deals")
-            elif 'laptop' in text.lower() or any(term in text.lower() for term in laptop_terms):
-                search_terms = laptop_terms
-                print("Searching for laptop deals")
-            elif 'tv' in text.lower() or any(term in text.lower() for term in tv_terms):
-                search_terms = tv_terms
-                print("Searching for TV deals")
-            elif 'kitchen' in text.lower() or any(term in text.lower() for term in kitchen_terms):
-                search_terms = kitchen_terms
-                print("Searching for kitchen deals")
+            # Add related terms based on the query
+            if any(term in text.lower() for term in ['headphone', 'headphones']):
+                expanded_terms.extend(['earbuds', 'earphones', 'earpods', 'airpods', 'audio', 'bluetooth', 'wireless'])
+            elif any(term in text.lower() for term in ['laptop', 'computer']):
+                expanded_terms.extend(['notebook', 'macbook', 'chromebook', 'pc'])
+            elif any(term in text.lower() for term in ['tv', 'television']):
+                expanded_terms.extend(['smart tv', 'roku', 'streaming'])
+            elif any(term in text.lower() for term in ['kitchen', 'appliance']):
+                expanded_terms.extend(['mixer', 'blender', 'toaster', 'microwave', 'oven'])
             
-            # Find deals matching the search terms
-            matched_deals = []
+            # Score deals based on relevance to the query
+            scored_deals = []
             for deal in deals_cache:
                 title = deal['title'].lower()
                 content = deal['content'].lower()
+                excerpt = deal['excerpt'].lower()
                 
-                # Check if any search term is in the title (highest priority)
-                if any(term in title for term in search_terms):
-                    matched_deals.append((deal, 100))  # High score for title matches
-                # Check if any search term is in the content
-                elif any(term in content for term in search_terms):
-                    matched_deals.append((deal, 50))   # Lower score for content matches
+                score = 0
+                
+                # Check original query terms (higher weight)
+                for term in query_terms:
+                    if term in title:
+                        score += 10
+                    if term in content:
+                        score += 3
+                    if term in excerpt:
+                        score += 3
+                
+                # Check expanded terms (lower weight)
+                for term in expanded_terms:
+                    if term not in query_terms:  # Skip original terms
+                        if term in title:
+                            score += 5
+                        if term in content:
+                            score += 1
+                        if term in excerpt:
+                            score += 1
+                
+                # Add to scored deals if it has any relevance
+                if score > 0:
+                    scored_deals.append((deal, score))
             
             # Sort by score (descending)
-            matched_deals.sort(key=lambda x: x[1], reverse=True)
+            scored_deals.sort(key=lambda x: x[1], reverse=True)
             
-            # Extract the deals from the matched list
-            relevant_deals = [deal for deal, _ in matched_deals[:5]]
-            
-            # If no deals found with the specific search, try a more general approach
-            if not relevant_deals:
-                print("No specific deals found, trying general search")
-                # Hardcoded headphone deals we know exist
-                headphone_deals = [
-                    {
-                        'title': 'BlitzRock Bluetooth 5.4 Open Ear Headphones',
-                        'link': 'https://dealsfinders.com/blitzrock-bluetooth-5-4-open-ear-headphones/',
-                        'excerpt': 'Bluetooth headphones with open ear design'
-                    },
-                    {
-                        'title': 'Sony ZX Series Wired On-Ear Headphones White MDR-ZX110',
-                        'link': 'https://dealsfinders.com/sony-zx-series-wired-on-ear-headphones-white-mdr-zx110/',
-                        'excerpt': 'Sony wired headphones'
-                    },
-                    {
-                        'title': '50% Off BlitzMax Open Ear Headphones Call Noise Cancellation',
-                        'link': 'https://dealsfinders.com/50-off-blitzmax-open-ear-headphones-call-noise-cancellation/',
-                        'excerpt': 'Discount on noise cancelling headphones'
-                    },
-                    {
-                        'title': 'Bluetooth Headphones with RGB Lights',
-                        'link': 'https://dealsfinders.com/bluetooth-headphones-with-rgb-lights-4/',
-                        'excerpt': 'Bluetooth headphones with RGB lighting'
-                    }
-                ]
-                
-                # If looking for headphones, use our hardcoded list
-                if 'headphone' in text.lower() or any(term in text.lower() for term in headphone_terms):
-                    relevant_deals = headphone_deals
+            # Extract the deals from the scored list
+            relevant_deals = [deal for deal, _ in scored_deals[:5]]
             
             if relevant_deals:
                 for i, deal in enumerate(relevant_deals, 1):