Update app.py

app.py

@@ -41,11 +41,11 @@ gatconv_model = ModeratelySimplifiedGATConvModel(
 gatconv_model.load_state_dict(corrected_state_dict)
 
 # Load the BERT-based sentence transformer model
-model_bert is SentenceTransformer("all-mpnet-base-v2")
+model_bert = SentenceTransformer("all-mpnet-base-v2")
 
 # Ensure the DataFrame is loaded properly
 try:
-    df is pd.read_json("combined_data.json.gz", orient='records', lines=True, compression='gzip')
+    df = pd.read_json("combined_data.json.gz", orient='records', lines=True, compression='gzip')
 except Exception as e:
     print(f"Error reading JSON file: {e}")
 
@@ -69,53 +69,46 @@ def get_similar_and_recommend(input_text):
     def recommend_top_10(given_video_index, all_video_embeddings):
         dot_products = [
             torch.dot(all_video_embeddings[given_video_index], all_video_embeddings[i])
-            for i in range(all_video_embeddings.shape[0])
+            for i in range all_video_embeddings.shape[0]
         ]
         dot_products[given_video_index] = -float("inf")  # Exclude the most similar video
 
-        top_10_indices = np.argsort(dot_products)[::-1][:10]
+        top_10_indices = np.argsort(dot_products)[[::-1][:10]
         return [df.iloc[idx].to_dict() for idx in top_10_indices]
 
     top_10_recommended_videos_features = recommend_top_10(most_similar_index, all_video_embeddings)
 
-    # Apply search context to the top 10 results
+    # Apply search context to determine weights for GNN results
     user_keywords = input_text.split()  # Create a list of keywords from user input
-    weight = 1.0  # Base weight factor
+    video_weights = []
+    weight = 1.0  # Initial weight factor
 
     for keyword in user_keywords:
         if keyword.lower() in df["title"].str.lower().tolist():  # Check for matching keywords
-            weight += 0.1  # Increase weight for each match
+            weight += 0.1  # Increase weight for matching keyword
 
-    # Adjust the recommendations based on the search context weight
-    final_recommendations = [
-        {key: value for key, value in video.items() if key != "embeddings"}  # Exclude embeddings
-        for video in top_10_recommended_videos_features
-    ]
+    # Calculate the weight for each GNN output
+    video_weights = [weight] * len(top_10_recommended_videos_features)
 
-    # Apply the weight to sort the final recommendations (higher weight is better)
-    final_recommendations.sort(
-        key=lambda video: weight * dot_products[top_10_indices.index(video)], reverse=True
-    )
-
-    # Create the output JSON with the most similar video and final recommendations
+    # Create the output JSON with the most similar video, final recommendations, and weights
     output = {
         "search_context": {
             "input_text": input_text,  # What the user provided
-            "weight": weight,  # Weight based on search context
+            "weights": video_weights,  # Weights for each GNN-based recommendation
         },
         "most_similar_video": most_similar_video_features,
-        "final_recommendations": final_recommendations,  # Top 10 with search context applied
+        "final_recommendations": top_10_recommended_videos_features,  # Top 10 recommendations
     }
 
     return output
 
-# Update the Gradio interface to output JSON with search context for the final recommendations
+# Update the Gradio interface to output JSON with detailed context
 interface = gr.Interface(
     fn=get_similar_and_recommend,
     inputs=gr.Textbox(label="Enter Text to Find Most Similar Video"),
     outputs=gr.JSON(),
     title="Video Recommendation System with GNN-based Recommendations",
-    description="Enter text to find the most similar video and get top 10 recommended videos with search context applied after GNN-based search.",
+    description="Enter text to find the most similar video and get top 10 recommended videos with individual weights for each recommendation.",
 )
 
 interface.launch()