Upload app.py with huggingface_hub

app.py

@@ -144,21 +144,62 @@ 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)
             
-            # Search for relevant deals
+            # Search for relevant deals with improved matching
             query_terms = text.lower().split()
-            relevant_deals = []
             
+            # Add related terms for specific queries
+            expanded_terms = list(query_terms)  # Start with original terms
+            
+            # Special case for headphones
+            if 'headphone' in query_terms or 'headphones' in query_terms:
+                expanded_terms.extend(['earbuds', 'earphones', 'earpods', 'airpods', 'audio', 'bluetooth', 'wireless'])
+            
+            # Score and rank deals
+            scored_deals = []
             for deal in deals_cache:
                 title = deal['title'].lower()
                 content = deal['content'].lower()
                 excerpt = deal['excerpt'].lower()
                 
-                # Check if any query term is in the deal information
-                if any(term in title or term in content or term in excerpt for term in query_terms):
-                    relevant_deals.append(deal)
+                # Calculate relevance score
+                score = 0
+                
+                # Check original query terms (higher weight)
+                for term in query_terms:
+                    # Title matches are most important
+                    if term in title:
+                        score += 10
+                    # Content and excerpt matches
+                    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
+                
+                # Special case for headphones - look for exact product matches
+                if 'headphone' in query_terms or 'headphones' in query_terms:
+                    headphone_terms = ['headphone', 'headphones', 'earbuds', 'earphones', 'earpods', 'airpods']
+                    if any(term in title for term in headphone_terms):
+                        score += 20  # Significant boost for headphone products
+                
+                # Add to scored deals if it has any relevance
+                if score > 0:
+                    scored_deals.append((deal, score))
+            
+            # Sort by score (descending)
+            scored_deals.sort(key=lambda x: x[1], reverse=True)
             
-            # Limit to top 5 most relevant deals
-            relevant_deals = relevant_deals[:5]
+            # Extract the deals from the scored list
+            relevant_deals = [deal for deal, score in scored_deals[:5]]
             
             if relevant_deals:
                 for i, deal in enumerate(relevant_deals, 1):