Update app.py

app.py

@@ -6,6 +6,7 @@ from torch_geometric.data import Data
 from torch_geometric.nn import GATConv
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
+
 # Define the GATConv model architecture
 class ModeratelySimplifiedGATConvModel(torch.nn.Module):
     def __init__(self, in_channels, hidden_channels, out_channels):
@@ -60,33 +61,42 @@ def get_similar_and_recommend(input_text):
     input_embedding = model_bert.encode([input_text])[0]
     similarities = cosine_similarity([input_embedding], embeddings_matrix)[0]
 
-    # Modify the similarity scores based on user input
-    user_keywords = input_text.split()  # Create a list of keywords from user input
-    weight = 1.0  # Initial weight factor
+    most_similar_index = np.argmax(similarities)  # Use unweighted scores for the most similar video
 
-    for keyword in user_keywords:
-        if keyword.lower() in df["title"].str.lower().tolist():  # Check if the keyword is in any title
-            weight += 0.1  # Increase weight for matching keyword
+    # Get all features of the most similar video
+    most_similar_video_features = df.iloc[most_similar_index].to_dict()
+    # Get all features of the most similar video
+    most_similar_video_features = df.iloc[most_similar_index].to_dict()
+    
+    # Remove the "embeddings" key from most_similar_video_features
+    if "embeddings" in most_similar_video_features:
+        del most_similar_video_features["embeddings"]
+    if "text_for_embedding" in most_similar_video_features:
+        del most_similar_video_features["text_for_embedding"]
 
-    weighted_similarities = similarities * weight  # Apply the weight to the similarity score
 
-    most_similar_index = np.argmax(weighted_similarities)  # Use weighted scores to find most similar
+    # Apply search context weight for GNN recommendations
+    user_keywords = input_text.split()  # Create a list of keywords from user input
+    weight = 1.0  # Initial weight factor
 
-    # Get all features of the most similar video
-    most_similar_video_features = df.iloc[most_similar_index].to_dict()
+    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
 
-    # Recommend the top 10 videos based on GNN embeddings and dot product
-    def recommend_next_10_videos(given_video_index, all_video_embeddings):
+    # Recommend the top 10 videos based on GNN embeddings and weighted dot product
+    def recommend_next_10_videos(given_video_index, all_video_embeddings, weight):
         dot_products = [
-            torch.dot(all_video_embeddings[given_video_index], all_video_embeddings[i])
+            torch.dot(all_video_embeddings[given_video_index], all_video_embeddings[i]) * weight
             for i in range(all_video_embeddings.shape[0])
         ]
         dot_products[given_video_index] = -float("inf")
 
-        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_next_10_videos(most_similar_index, all_video_embeddings)
+    top_10_recommended_videos_features = recommend_next_10_videos(
+        most_similar_index, all_video_embeddings, weight
+    )
 
     # Exclude unwanted features for recommended videos
     for recommended_video in top_10_recommended_videos_features:
@@ -95,11 +105,11 @@ def get_similar_and_recommend(input_text):
         if "embeddings" in recommended_video:
             del recommended_video["embeddings"]
 
-    # Create the output JSON with all features and the search context
+    # Create the output JSON with the search context
     output = {
         "search_context": {
             "input_text": input_text,
-            "weight": weight,  # The applied weight based on user input
+            "weight": weight,  # Weight applied to the GNN recommendations
         },
         "most_similar_video": most_similar_video_features,
         "top_10_recommended_videos": top_10_recommended_videos_features,
@@ -107,13 +117,13 @@ def get_similar_and_recommend(input_text):
 
     return output
 
-# Update the Gradio interface to output JSON with weighted recommendations
+# Update the Gradio interface to output JSON with search context for GNN recommendations
 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 and user-influenced weight factor.",
+    description="Enter text to find the most similar video and get top 10 recommended videos with search context applied to GNN results.",
 )
 
 interface.launch()