Get the latest Apple AirPods Pro (2nd Generation) for 20% off the regular price. These wireless earbuds feature active noise cancellation, transparency mode, and spatial audio with dynamic head tracking.
Regular price: $249.99
Deal price: $199.99
You save: $50.00
" }, "excerpt": { "rendered": "Apple AirPods Pro (2nd Generation) with active noise cancellation and transparency mode. Now 20% off - only $199.99!
" } }, { "id": 2, "title": { "rendered": "Samsung 65\" QLED 4K Smart TV - $300 Off" }, "link": "https://www.example.com/deals/samsung-qled-tv", "date": "2025-02-26T09:30:00", "content": { "rendered": "Upgrade your home entertainment with this Samsung 65\" QLED 4K Smart TV. Features Quantum HDR, Motion Xcelerator Turbo+, and Object Tracking Sound for an immersive viewing experience.
Regular price: $1,299.99
Deal price: $999.99
You save: $300.00
" }, "excerpt": { "rendered": "Samsung 65\" QLED 4K Smart TV with Quantum HDR and Object Tracking Sound. Save $300 - now only $999.99!
" } }, { "id": 3, "title": { "rendered": "Sony WH-1000XM5 Wireless Headphones - 25% Off" }, "link": "https://www.example.com/deals/sony-wh1000xm5", "date": "2025-02-26T14:15:00", "content": { "rendered": "Experience industry-leading noise cancellation with the Sony WH-1000XM5 wireless headphones. Features 30-hour battery life, quick charging, and exceptional sound quality with the new Integrated Processor V1.
Regular price: $399.99
Deal price: $299.99
You save: $100.00
" }, "excerpt": { "rendered": "Sony WH-1000XM5 wireless headphones with industry-leading noise cancellation and 30-hour battery life. Now 25% off at $299.99!
" } }, { "id": 4, "title": { "rendered": "Bose QuietComfort Ultra Headphones - 20% Off" }, "link": "https://www.example.com/deals/bose-quietcomfort-ultra", "date": "2025-02-25T15:30:00", "content": { "rendered": "Experience the ultimate in noise cancellation with Bose QuietComfort Ultra headphones. Features spatial audio, custom EQ, and up to 24 hours of battery life.
Regular price: $429.99
Deal price: $343.99
You save: $86.00
" }, "excerpt": { "rendered": "Bose QuietComfort Ultra headphones with advanced noise cancellation and spatial audio. Now 20% off at $343.99!
" } }, { "id": 5, "title": { "rendered": "Beats Studio Pro Wireless Headphones - 40% Off" }, "link": "https://www.example.com/deals/beats-studio-pro", "date": "2025-02-26T16:30:00", "content": { "rendered": "The Beats Studio Pro wireless headphones deliver premium sound with active noise cancellation, transparency mode, and up to 40 hours of battery life.
Regular price: $349.99
Deal price: $209.99
You save: $140.00
" }, "excerpt": { "rendered": "Beats Studio Pro wireless headphones with active noise cancellation and 40-hour battery life. Now 40% off at $209.99!
" } }, { "id": 6, "title": { "rendered": "Dyson V12 Detect Slim Cordless Vacuum - $150 Off" }, "link": "https://www.example.com/deals/dyson-v12", "date": "2025-02-27T08:45:00", "content": { "rendered": "The Dyson V12 Detect Slim cordless vacuum features a laser that reveals microscopic dust, an LCD screen that displays particle counts, and powerful suction for deep cleaning.
Regular price: $649.99
Deal price: $499.99
You save: $150.00
" }, "excerpt": { "rendered": "Dyson V12 Detect Slim cordless vacuum with laser dust detection and powerful suction. Save $150 - now only $499.99!
" } }, { "id": 7, "title": { "rendered": "Nintendo Switch OLED Model - Bundle Deal" }, "link": "https://www.example.com/deals/nintendo-switch-oled", "date": "2025-02-27T11:20:00", "content": { "rendered": "Get the Nintendo Switch OLED Model with a vibrant 7-inch OLED screen, plus two games and a carrying case. The perfect gaming package for home or on-the-go play.
Regular price: $439.99
Deal price: $379.99
You save: $60.00
" }, "excerpt": { "rendered": "Nintendo Switch OLED Model bundle with two games and carrying case. Special bundle price of $379.99!
" } }, { "id": 8, "title": { "rendered": "MacBook Air M3 - $200 Off" }, "link": "https://www.example.com/deals/macbook-air-m3", "date": "2025-02-26T10:45:00", "content": { "rendered": "The latest MacBook Air with M3 chip offers incredible performance and battery life in an ultra-thin design. Features a 13.6-inch Liquid Retina display, 8GB RAM, and 256GB SSD storage.
Regular price: $1,099.99
Deal price: $899.99
You save: $200.00
" }, "excerpt": { "rendered": "MacBook Air with M3 chip, 13.6-inch Liquid Retina display, and all-day battery life. Save $200 - now only $899.99!
" } }, { "id": 9, "title": { "rendered": "Kindle Paperwhite Signature Edition - 30% Off" }, "link": "https://www.example.com/deals/kindle-paperwhite", "date": "2025-02-27T09:15:00", "content": { "rendered": "The Kindle Paperwhite Signature Edition features a 6.8-inch display, wireless charging, auto-adjusting front light, and 32GB storage. Perfect for reading anywhere, anytime.
Regular price: $189.99
Deal price: $132.99
You save: $57.00
" }, "excerpt": { "rendered": "Kindle Paperwhite Signature Edition with 6.8-inch display, wireless charging, and 32GB storage. Now 30% off at $132.99!
" } }, { "id": 10, "title": { "rendered": "LG C3 65\" OLED 4K Smart TV - $500 Off" }, "link": "https://www.example.com/deals/lg-c3-oled", "date": "2025-02-25T13:00:00", "content": { "rendered": "Experience stunning picture quality with the LG C3 65\" OLED 4K Smart TV. Features self-lit OLED pixels, Dolby Vision, Dolby Atmos, and NVIDIA G-SYNC for gaming.
Regular price: $1,799.99
Deal price: $1,299.99
You save: $500.00
" }, "excerpt": { "rendered": "LG C3 65\" OLED 4K Smart TV with self-lit pixels and Dolby Vision. Save $500 - now only $1,299.99!
" } } ] # Function to fetch deals from DealsFinders.com (from shopping_assistant.py) def fetch_deals_data(url="https://www.dealsfinders.com/wp-json/wp/v2/posts", num_pages=2, per_page=100, use_sample_data=False): """ Fetch deals data exclusively from the DealsFinders API or use sample data """ # If use_sample_data is True, return the sample deals if use_sample_data: print("Using sample deals data") return SAMPLE_DEALS all_deals = [] # Fetch from the DealsFinders API for page in range(1, num_pages + 1): try: # Add a user agent to avoid being blocked headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36' } response = requests.get(f"{url}?page={page}&per_page={per_page}", headers=headers) if response.status_code == 200: deals = response.json() all_deals.extend(deals) print(f"Fetched page {page} with {len(deals)} deals from DealsFinders API") # If we get fewer deals than requested, we've reached the end if len(deals) < per_page: print(f"Reached the end of available deals at page {page}") break else: print(f"Failed to fetch page {page} from DealsFinders API: {response.status_code}") print("Falling back to sample deals data") return SAMPLE_DEALS except Exception as e: print(f"Error fetching page {page} from DealsFinders API: {str(e)}") print("Falling back to sample deals data") return SAMPLE_DEALS # If no deals were fetched, use sample data if not all_deals: print("No deals fetched from API. Using sample deals data") return SAMPLE_DEALS return all_deals # Function to process deals data (from shopping_assistant.py) def process_deals_data(deals_data): """ Process the deals data into a structured format """ processed_deals = [] for deal in deals_data: try: # Extract relevant information using our HTML text extractor content_html = deal.get('content', {}).get('rendered', '') excerpt_html = deal.get('excerpt', {}).get('rendered', '') clean_content = extract_text_from_html(content_html) clean_excerpt = extract_text_from_html(excerpt_html) processed_deal = { 'id': deal.get('id'), 'title': deal.get('title', {}).get('rendered', ''), 'link': deal.get('link', ''), 'date': deal.get('date', ''), 'content': clean_content, 'excerpt': clean_excerpt } processed_deals.append(processed_deal) except Exception as e: print(f"Error processing deal: {str(e)}") return processed_deals # Define product categories category_descriptions = { "electronics": "Electronic devices like headphones, speakers, TVs, smartphones, and gadgets", "computers": "Laptops, desktops, computer parts, monitors, and computing accessories", "mobile": "Mobile phones, smartphones, phone cases, screen protectors, and chargers", "audio": "Headphones, earbuds, speakers, microphones, and audio equipment", "clothing": "Clothes, shirts, pants, dresses, and fashion items", "footwear": "Shoes, boots, sandals, slippers, and all types of footwear", "home": "Home decor, furniture, bedding, and household items", "kitchen": "Kitchen appliances, cookware, utensils, and kitchen gadgets", "toys": "Toys, games, and children's entertainment items", "sports": "Sports equipment, fitness gear, and outdoor recreation items", "beauty": "Beauty products, makeup, skincare, and personal care items", "books": "Books, e-books, audiobooks, and reading materials" } # List of categories categories = list(category_descriptions.keys()) # Try to load the recommended models try: # 1. Load BART model for zero-shot classification from transformers import pipeline # Initialize the zero-shot classification pipeline classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli") print("Using facebook/bart-large-mnli for classification") # 2. Load MPNet model for semantic search from sentence_transformers import SentenceTransformer, util # Load the sentence transformer model sentence_model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2') print("Using sentence-transformers/all-mpnet-base-v2 for semantic search") # Pre-compute embeddings for category descriptions category_texts = list(category_descriptions.values()) category_embeddings = sentence_model.encode(category_texts, convert_to_tensor=True) # Using recommended models using_recommended_models = True except Exception as e: # Fall back to local model if recommended models fail to load print(f"Error loading recommended models: {str(e)}") print("Falling back to local model") model_path = os.path.dirname(os.path.abspath(__file__)) tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForSequenceClassification.from_pretrained(model_path) # Load the local categories try: with open(os.path.join(model_path, "categories.json"), "r") as f: categories = json.load(f) except Exception as e: print(f"Error loading categories: {str(e)}") categories = ["electronics", "clothing", "home", "kitchen", "toys", "other"] # Not using recommended models using_recommended_models = False # File path for storing deals data locally DEALS_DATA_PATH = "deals_data.json" # Function to fetch and save a large number of deals def fetch_and_save_deals(max_deals=10000, per_page=100): """ Fetch a large number of deals and save them to a local file """ print(f"Fetching up to {max_deals} deals...") all_deals = [] num_pages = min(max_deals // per_page + (1 if max_deals % per_page > 0 else 0), 100) # Limit to 100 pages max # Fetch from the DealsFinders API for page in range(1, num_pages + 1): try: # Add a user agent to avoid being blocked headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36' } response = requests.get(f"https://www.dealsfinders.com/wp-json/wp/v2/posts?page={page}&per_page={per_page}", headers=headers) if response.status_code == 200: deals = response.json() all_deals.extend(deals) print(f"Fetched page {page} with {len(deals)} deals from DealsFinders API") # If we get fewer deals than requested, we've reached the end if len(deals) < per_page: print(f"Reached the end of available deals at page {page}") break # If we've reached the maximum number of deals, stop if len(all_deals) >= max_deals: all_deals = all_deals[:max_deals] # Trim to max_deals print(f"Reached the maximum number of deals ({max_deals})") break else: print(f"Failed to fetch page {page} from DealsFinders API: {response.status_code}") break except Exception as e: print(f"Error fetching page {page} from DealsFinders API: {str(e)}") break # Process the deals processed_deals = process_deals_data(all_deals) # Save the deals to a local file try: with open(DEALS_DATA_PATH, "w") as f: json.dump(processed_deals, f) print(f"Saved {len(processed_deals)} deals to {DEALS_DATA_PATH}") return processed_deals except Exception as e: print(f"Error saving deals to file: {str(e)}") return processed_deals # Function to load deals from the local file def load_deals_from_file(): """ Load deals from the local file """ try: if os.path.exists(DEALS_DATA_PATH): with open(DEALS_DATA_PATH, "r") as f: deals = json.load(f) print(f"Loaded {len(deals)} deals from {DEALS_DATA_PATH}") return deals else: print(f"Deals file {DEALS_DATA_PATH} does not exist") return None except Exception as e: print(f"Error loading deals from file: {str(e)}") return None # Global variable to store deals data deals_cache = None # Try to fetch and save deals on startup try: # First try to load from file deals_cache = load_deals_from_file() # If file doesn't exist or is empty, fetch and save if deals_cache is None or len(deals_cache) == 0: print("No deals found in local file. Fetching deals...") deals_cache = fetch_and_save_deals() print(f"Initialized with {len(deals_cache) if deals_cache else 0} deals") except Exception as e: print(f"Error initializing deals cache: {str(e)}") deals_cache = None def classify_text(text, fetch_deals=True): """ Classify the text using the model and fetch relevant deals """ global deals_cache # 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)) # Limit to top 3 categories if i >= 2: break 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) # Format the classification results if top_categories: result = f"Top categories for '{text}':\n\n" for category, score in top_categories: result += f"- {category}: {score:.4f}\n" result += f"\nBased on your query, I would recommend looking for deals in the **{top_categories[0][0]}** category.\n\n" else: result = f"No categories found for '{text}'. Please try a different query.\n\n" # Fetch and display deals if requested if fetch_deals: result += "## Relevant Deals from DealsFinders.com\n\n" try: # Fetch deals data if not already cached if deals_cache is None: # Use sample data by default in Hugging Face space environment deals_data = fetch_deals_data(num_pages=2, use_sample_data=True) # Use sample data for reliability deals_cache = process_deals_data(deals_data) # Using MPNet for semantic search if available if using_recommended_models: # Create deal texts for semantic search deal_texts = [] for deal in deals_cache: # Combine title and excerpt for better matching deal_text = f"{deal['title']} {deal['excerpt']}" deal_texts.append(deal_text) # Encode the query and deals query_embedding = sentence_model.encode(text, convert_to_tensor=True) deal_embeddings = sentence_model.encode(deal_texts, convert_to_tensor=True) # Calculate semantic similarity similarities = util.cos_sim(query_embedding, deal_embeddings)[0] # Get top 5 most similar deals top_indices = torch.topk(similarities, k=min(5, len(deals_cache))).indices # Extract the relevant deals relevant_deals = [deals_cache[idx] for idx in top_indices] else: # Improved keyword-based search with category awareness query_terms = text.lower().split() expanded_terms = list(query_terms) # Get the top category from the classification results top_category = top_categories[0][0] if top_categories else None # Add category-specific terms if top_category == "electronics": expanded_terms.extend(['electronic', 'device', 'gadget', 'tech', 'technology']) 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 top_category == "kitchen": expanded_terms.extend(['appliance', 'cookware', 'utensil', 'blender', 'mixer', 'toaster', 'microwave', 'oven']) elif top_category == "home": expanded_terms.extend(['furniture', 'decor', 'decoration', 'bedding', 'household']) elif top_category == "clothing": expanded_terms.extend(['clothes', 'shirt', 'pants', 'dress', 'fashion', 'wear', 'apparel']) elif top_category == "toys": expanded_terms.extend(['game', 'play', 'children', 'kid', 'kids', 'fun']) # 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() 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 # Boost score for deals matching the top category if top_category: if top_category.lower() in title.lower(): score += 15 if top_category.lower() in content.lower(): score += 5 if top_category.lower() in excerpt.lower(): score += 5 # 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) # 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): result += f"{i}. [{deal['title']}]({deal['link']})\n\n" else: result += "No specific deals found for your query. Try a different search term or browse the recommended category.\n\n" except Exception as e: result += f"Error fetching deals: {str(e)}\n\n" return result # Create the Gradio interface demo = gr.Interface( fn=classify_text, inputs=[ gr.Textbox( lines=2, placeholder="Enter your shopping query here...", label="Shopping Query" ), gr.Checkbox( label="Fetch Deals", value=True, info="Check to fetch and display deals from DealsFinders.com" ) ], outputs=gr.Markdown(label="Results"), title="Shopping Assistant", description=""" This demo shows how to use the Shopping Assistant model to classify shopping queries into categories and find relevant deals. Enter a shopping query below to see which categories it belongs to and find deals from DealsFinders.com. Examples: - "I'm looking for headphones" - "Do you have any kitchen appliance deals?" - "Show me the best laptop deals" - "I need a new smart TV" """, examples=[ ["I'm looking for headphones", True], ["Do you have any kitchen appliance deals?", True], ["Show me the best laptop deals", True], ["I need a new smart TV", True], ["headphone deals", True] ], theme=gr.themes.Soft() ) # Launch the app if __name__ == "__main__": demo.launch()