Update app.py

app.py

@@ -7,60 +7,54 @@ from PIL import Image
 import io
 
 # --- CONFIGURATION ---
-# Using the lightweight OpenAI CLIP model
-MODEL_ID = "openai/clip-vit-base-patch32" 
+MODEL_ID = "openai/clip-vit-base-patch32"
 DATA_FILE = "food_embeddings_clip.parquet"
 
+# 🎥 PASTE YOUR YOUTUBE VIDEO ID HERE
+# (e.g. if link is https://www.youtube.com/watch?v=dQw4w9WgXcQ, the ID is dQw4w9WgXcQ)
+YOUTUBE_ID = "IXeIxYHi0Es" 
+
 print(f"⏳ Loading {MODEL_ID} and Data...")
 
-# 1. Load Model (CLIP class is specific and lighter)
+# 1. Load Model
 model = CLIPModel.from_pretrained(MODEL_ID)
 processor = CLIPProcessor.from_pretrained(MODEL_ID)
 
-# 2. Load the "Memory"
+# 2. Load Data
 try:
     df = pd.read_parquet(DATA_FILE)
+    # Prepare Vectors
+    all_vectors = np.stack(df['embedding'].to_numpy())
+    db_features = torch.tensor(all_vectors)
 except FileNotFoundError:
-    raise RuntimeError(f"❌ ERROR: Could not find {DATA_FILE}. Did you upload it to Files?")
-
-# 3. Prepare Database
-all_vectors = np.stack(df['embedding'].to_numpy())
-db_features = torch.tensor(all_vectors)
+    raise RuntimeError(f"❌ ERROR: Could not find {DATA_FILE}. Did you upload it?")
 
 print("✅ System Ready!")
 
+# --- SEARCH LOGIC ---
 def search(text_query, image_query):
-    # A. Decide Input Type
+    if not text_query and not image_query:
+        return []
+
+    # A. Determine Input
     if image_query:
         inputs = processor(images=image_query, return_tensors="pt", padding=True)
-        get_feat_func = model.get_image_features
-    elif text_query:
-        inputs = processor(text=[text_query], return_tensors="pt", padding=True)
-        get_feat_func = model.get_text_features
+        get_feat = model.get_image_features
     else:
-        return None
+        inputs = processor(text=[text_query], return_tensors="pt", padding=True)
+        get_feat = model.get_text_features
 
-    # B. Run Inference
+    # B. Inference & Search
     with torch.no_grad():
-        query_vec = get_feat_func(**inputs)
+        query_vec = get_feat(**inputs)
+        top_scores, top_indices = torch.topk(scores, k=5)
 
-    # C. Search Logic
-    # 1. Normalize Query
-    query_vec = query_vec / query_vec.norm(p=2, dim=-1, keepdim=True)
-    
-    # 2. Dot Product
-    scores = torch.mm(query_vec, db_features.T)
-    
-    # 3. Top 5 Results
-    top_scores, top_indices = torch.topk(scores, k=5)
-    
-    # D. Fetch Results
+    # C. Format Results
     results = []
     for idx, score in zip(top_indices[0], top_scores[0]):
-        idx = idx.item()
-        row = df.iloc[idx]
+        row = df.iloc[idx.item()]
         
-        # Load Image from Parquet bytes
+        # Load Image
         img_data = row['image']
         if isinstance(img_data, dict) and 'bytes' in img_data:
             img = Image.open(io.BytesIO(img_data['bytes']))
@@ -68,23 +62,73 @@ def search(text_query, image_query):
             img = img_data
 
         results.append((img, f"{row['label_name']} ({score.item():.2f})"))
-        
     return results
 
-# --- INTERFACE ---
-with gr.Blocks(title="Food Search (CLIP)") as demo:
-    gr.Markdown("# 🍕 Lightweight Food Search (CLIP)")
+# --- APP INTERFACE (The Original Design) ---
+# We use a 'Soft' theme for a professional look
+with gr.Blocks(theme=gr.themes.Soft(), title="AI Food Search") as demo:
     
+    # 1. Header Section
+    gr.Markdown(
+        """
+        # 🍔 AI Food Search Engine
+        ### Powered by OpenAI CLIP & Hugging Face
+        Search through 5,000 food images using natural language or reference images.
+        """
+    )
+    
+    # 2. YouTube Demo Section (Embedded Player)
+    if YOUTUBE_ID and YOUTUBE_ID != "YOUR_YOUTUBE_ID_HERE":
+        gr.HTML(
+            f"""
+            <div style="display: flex; justify-content: center; margin-bottom: 20px;">
+                <iframe width="560" height="315" 
+                src="https://www.youtube.com/embed/{YOUTUBE_ID}" 
+                title="YouTube video player" frameborder="0" 
+                allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" 
+                allowfullscreen></iframe>
+            </div>
+            """
+        )
+    else:
+        gr.Info("ℹ️ Add your YouTube ID in the code to display the video here.")
+
+    # 3. Main Search Interface
     with gr.Row():
-        with gr.Column():
-            txt_input = gr.Textbox(label="Search by Text", placeholder="e.g. 'sushi on a boat'")
-            img_input = gr.Image(type="pil", label="Or Search by Image")
-            btn = gr.Button("Search", variant="primary")
+        # Left Column: Inputs
+        with gr.Column(scale=1):
+            gr.Markdown("### 🔍 Your Query")
+            txt_input = gr.Textbox(
+                label="Search by Text", 
+                placeholder="e.g. 'spicy tacos with lime'",
+                show_label=True
+            )
+            gr.Markdown("**OR**")
+            img_input = gr.Image(
+                type="pil", 
+                label="Search by Image",
+                height=300
+            )
             
-        with gr.Column():
-            gallery = gr.Gallery(label="Top Matches")
+            search_btn = gr.Button("🚀 Find Food", variant="primary", size="lg")
+
+        # Right Column: Results
+        with gr.Column(scale=2):
+            gr.Markdown("### 🍕 Top Matches")
+            gallery = gr.Gallery(
+                label="Results", 
+                columns=3, 
+                height="auto",
+                object_fit="cover"
+            )
+
+    # 4. Footer / Credits
+    gr.Markdown("---")
+    gr.Markdown(f"*Model: {MODEL_ID} | Dataset: Food-101 (Subset)*")
 
-    btn.click(fn=search, inputs=[txt_input, img_input], outputs=gallery)
+    # Event Listeners (Enter Key + Button Click)
+    txt_input.submit(search, inputs=[txt_input, img_input], outputs=gallery)
+    search_btn.click(search, inputs=[txt_input, img_input], outputs=gallery)
 
-# Bind to 0.0.0.0 for Spaces
+# Launch
 demo.launch(server_name="0.0.0.0", server_port=7860)