Update app.py

app.py

@@ -1,34 +1,43 @@
 import gradio as gr
 import pandas as pd
-import pickle
 import numpy as np
 import os
 import random
 import base64
 from huggingface_hub import InferenceClient
 from sklearn.metrics.pairwise import cosine_similarity
+from datasets import load_dataset  # Added for HF Dataset loading
 from IO_pipeline import RecipeDigitalizerPipeline
 
 # ==========================================
-# 1. SETUP & DATA LOADING 
+# 1. SETUP & DATA LOADING (UPDATED)
 # ==========================================
 hf_token = os.getenv("HF_TOKEN")
 API_MODEL = "BAAI/bge-small-en-v1.5"
 client = InferenceClient(token=hf_token) if hf_token else None
 
-print("⏳ Loading Data...")
+print("⏳ Loading Data from Hugging Face...")
 try:
-    df_recipes = pd.read_csv('RecipeData_10K.csv')
-    with open('recipe_embeddings.pkl', 'rb') as f:
-        data = pickle.load(f)
-        if isinstance(data, dict):
-            stored_embeddings = np.array(data['embeddings'])
-        elif isinstance(data, pd.DataFrame):
-            target_col = next((c for c in ['embedding', 'embeddings', 'vectors'] if c in data.columns), None)
-            stored_embeddings = np.vstack(data[target_col].values) if target_col else data
-        else:
-            stored_embeddings = data
-    print("✅ Data Loaded!")
+    # Load dataset from Hugging Face
+    # We load the 'train' split by default. 
+    dataset = load_dataset("Liori25/10k_recipes", split="train")
+    
+    # Convert to Pandas DataFrame
+    df_recipes = dataset.to_pandas()
+
+    # Extract Embeddings
+    # We look for common names for the embedding column
+    target_col = next((c for c in ['embedding', 'embeddings', 'vectors'] if c in df_recipes.columns), None)
+    
+    if target_col:
+        # Convert the column of lists into a 2D numpy array
+        # This handles the conversion from the HF list format to the numpy matrix required for cosine_similarity
+        stored_embeddings = np.vstack(df_recipes[target_col].values)
+        print(f"✅ Data Loaded from HF! Shape: {stored_embeddings.shape}")
+    else:
+        print("⚠️ No embedding column found in dataset.")
+        stored_embeddings = None
+
 except Exception as e:
     print(f"❌ Error loading data: {e}")
     df_recipes = pd.DataFrame({'Title': [], 'Raw_Output': []})
@@ -99,7 +108,7 @@ def find_similar_recipes_list(query_text):
     for idx in top_indices:
         score = scores[idx]
         row = df_recipes.iloc[idx]
-        title = row['Title']
+        title = row.get('Title', 'Unknown Recipe')
         score_display = f"{score:.3%}"
         
         # Build the content block
@@ -344,7 +353,7 @@ button.gallery-item img {
 
 button.gallery-item:hover {
     transform: scale(2.5) !important; 
-    z-index: 1000 !important;          
+    z-index: 1000 !important;           
     box-shadow: 0 10px 25px rgba(0,0,0,0.3) !important;
     border: 2px solid white !important;
     border-radius: 8px !important;
@@ -446,6 +455,10 @@ with gr.Blocks(title="CookBook AI") as demo:
                         time_options = ["2h", "3h", "4h", "6h", "9h", "12h", "a day ago", "2 days ago"]
                         post_time = random.choice(time_options)
                         
+                        # Fallback for feed display
+                        raw_desc = str(row.get('Raw_Output', 'Delicious recipe...'))[:250]
+                        title_feed = row.get('Title', 'Recipe')
+
                         with gr.Group(elem_classes=["content-card"]):
                             gr.HTML(f"""
                             <div style="display:flex; gap:10px; align-items:center; margin-bottom:12px;">
@@ -453,8 +466,8 @@ with gr.Blocks(title="CookBook AI") as demo:
                                 <div><b>{user_name}</b><br><span style="color:gray; font-size:12px;">{post_time} · 🌍 Public</span></div>
                             </div>
                             """)
-                            gr.Markdown(f"### {row['Title']}")
-                            gr.Markdown(f"{str(row['Raw_Output'])[:250]}...")
+                            gr.Markdown(f"### {title_feed}")
+                            gr.Markdown(f"{raw_desc}...")
                             with gr.Row():
                                 gr.Button("👍 Like", size="sm", variant="secondary")
                                 gr.Button("💬 Comment", size="sm", variant="secondary")