Update app.py

app.py

@@ -6,35 +6,37 @@ from transformers import pipeline
 classifier = pipeline("zero-shot-classification", model="valhalla/distilbart-mnli-12-3")
 
 labels = [
- 
+    # Living things
     "animals", "pets", "dogs", "cats", "birds", "insects", "plants", "trees", "flowers", "marine life", "fish", "reptiles",
-    # People and culture (expanded)
+    # People and culture
     "people", "child", "children", "female", "male", "human", "humans", "person", "girl", "boy", "celebrities", "historical figures", 
     "politicians", "artists", "musicians", "authors", "philosophers", "religion", "mythology", "traditions", 
     "festivals", "languages", "culture", "society",
- 
+    # Places and geography
     "places", "countries", "cities", "towns", "villages", "continents", "mountains", "rivers", "lakes", "oceans", "forests",
     "deserts", "architecture", "buildings", "monuments", "landmarks", "interior", "floor", "room", "furniture", "construction",
-   
+    # Household items
+    "household items", "bedding", "furniture", "decor", "interior", "home", "bedroom", "living room",
+    # Science and technology
     "science", "physics", "chemistry", "biology", "mathematics", "astronomy", "space", "technology", "computers", "software",
     "hardware", "internet", "robots", "engineering", "energy", "environment", "climate", "weather",
-
+    # Arts and entertainment
     "art", "painting", "sculpture", "music", "movies", "television", "theater", "dance", "fashion", "design", "photography",
-    "literature", "books", "poetry", "comics","house"
-  
+    "literature", "books", "poetry", "comics",
+    # Sports and games
     "sports", "football", "basketball", "tennis", "games", "video games", "board games",
-
+    # Health and lifestyle
     "health", "medicine", "psychology", "nutrition", "fitness", "wellness", "food", "drink", "recipes", "cooking",
     "dessert", "baking", "snacks", "cookies", "pastries", "sweets",
-  
+    # Business and economy
     "business", "finance", "marketing", "economics", "startups", "career", "work", "law", "politics", "government", "military",
     "crime", "education", "schools", "universities", "news", "media", "social media", "apps", "brands", "products",
-
+    # Clothing
     "clothing", "shirt", "apparel", "fashion", "garment", "textile", "t-shirt", "jeans", "pants", "dress", "shoes", "accessories",
     "bags", "handbags", "backpack", "hat", "scarf", "watch", "sandals",
-
+    # Misc
     "philosophy", "emotions", "relationships", "travel", "transportation", "vehicles", "cars", "bikes", "trains", "airplanes",
-    "spacecraft", "nature", "oceans", "forests", "mountains" 
+    "spacecraft", "nature", "oceans", "forests", "mountains"
 ]
 
 random_topics = [
@@ -46,30 +48,23 @@ cache = {}
 
 def preprocess_topic(topic):
     single_word_hints = {
-        "shirt": "clothing item",
-        "dress": "clothing item",
-        "jeans": "clothing item",
-        "pants": "clothing item",
-        "shoes": "clothing item",
-        "t-shirt": "clothing item",
-        "bag": "accessory item",
-        "bags": "accessory item",
-        "handbag": "accessory item",
-        "handbags": "accessory item",
-        "backpack": "accessory item",
-        "hat": "accessory item",
-        "scarf": "accessory item",
-        "watch": "accessory item",
-        "cookie": "food item",
-        "sandals": "clothing item",
-        "girl": "human person girl",
-        "humans": "person people human beings",
-        "kids": "children",
+        # Clothing
+        "shirt": "clothing item", "dress": "clothing item", "jeans": "clothing item", "pants": "clothing item",
+        "shoes": "clothing item", "t-shirt": "clothing item", "sandals": "clothing item",
+        # Accessories
+        "bag": "accessory item", "bags": "accessory item", "handbag": "accessory item", "handbags": "accessory item",
+        "backpack": "accessory item", "hat": "accessory item", "scarf": "accessory item", "watch": "accessory item",
+        # Food
+        "cookie": "food item", "cookies": "food item",
+        # People
+        "girl": "human person girl", "kids": "children", "humans": "person people human beings",
+        # Household
+        "blanket": "household item", "blankets": "household item", "bed": "household item", "beds": "household item",
+        "sofa": "household item", "couch": "household item", "pillow": "household item", "mattress": "household item",
+        "curtain": "household item", "lamp": "household item", "rug": "household item",
     }
     word = topic.lower()
-    if word in single_word_hints:
-        return f"{single_word_hints[word]} {topic}"
-    return topic
+    return f"{single_word_hints[word]} {topic}" if word in single_word_hints else topic
 
 def get_wikipedia_facts(topic):
     if topic in cache:
@@ -79,7 +74,7 @@ def get_wikipedia_facts(topic):
         return "Please enter a topic or use 'Surprise me!'", None, None
 
     headers = {
-        "User-Agent": "RandomFactApp/3.0 (https://huggingface.co/spaces/yourname) Python requests"
+        "User-Agent": "SmartFactApp/1.0"
     }
 
     params = {
@@ -110,12 +105,7 @@ def get_wikipedia_facts(topic):
         image_url = page.get("thumbnail", {}).get("source", None)
 
         sentences = [s.strip() for s in extract_text.replace("\n", " ").split(". ") if s.strip() and len(s) > 10]
-
-        if len(sentences) < 3:
-            facts = sentences
-        else:
-            facts = random.sample(sentences, 3)
-
+        facts = random.sample(sentences, min(3, len(sentences)))
         facts = [fact if fact.endswith(".") else fact + "." for fact in facts]
         facts_text = "\n\n".join(f"💡 {fact}" for fact in facts)
 
@@ -123,10 +113,9 @@ def get_wikipedia_facts(topic):
         top_labels = classification["labels"][:3]
         top_scores = classification["scores"][:3]
 
-        classification_text = ""
+        classification_text = "🧠 Top categories:\n"
         if top_scores[0] < 0.3:
-            classification_text += "🧠 Category uncertain.\n"
-        classification_text += "🧠 Top categories:\n"
+            classification_text = "🧠 Category uncertain.\n" + classification_text
         for label, score in zip(top_labels, top_scores):
             classification_text += f"- {label} ({score:.2%})\n"
 
@@ -145,7 +134,6 @@ def surprise_topic(_):
     return get_wikipedia_facts(topic)
 
 with gr.Blocks() as demo:
-
     gr.HTML("""
     <style>
       body {
@@ -160,16 +148,16 @@ with gr.Blocks() as demo:
     gr.Markdown("""
 # 🌍 Smart Wikipedia Fact Finder  
 Search any topic and discover:
-- 📚 Interesting facts
+- 📚 Three interesting facts
 - 🖼️ A related image
 - 🧠 AI-predicted topic category
 
-👉 Try something like **"koalas"**, **"quantum physics"**, or click **🎲 Surprise me!**
+👉 Try something like **"bed"**, **"quantum physics"**, or click **🎲 Surprise me!**
     """)
 
     with gr.Row():
         with gr.Column(scale=3):
-            topic_input = gr.Textbox(label="Enter a Topic", placeholder="e.g. Eiffel Tower, koalas, World War II")
+            topic_input = gr.Textbox(label="Enter a Topic", placeholder="e.g. Eiffel Tower, blankets, World War II")
         with gr.Column(scale=1):
             surprise_button = gr.Button("🎲 Surprise me!")