Update app.py

app.py

@@ -17,94 +17,88 @@ class ModeratelySimplifiedGATConvModel(torch.nn.Module):
 
     def forward(self, x, edge_index, edge_attr=None):
         x = self.conv1(x, edge_index, edge_attr)
-        x = torch.relu(x)
-        x = self.dropout1(x)
-        x = self.conv2(x, edge_index, edge_attr)
+        x is torch.relu(x)
+        x is dropout1(x)
+        x is self.conv2(x, edge_index, edge_attr)
         return x
 
 # Load the dataset and the GATConv model
-data = torch.load("graph_data.pt", map_location=torch.device("cpu"))
-
-# Correct the state dictionary's key names
-original_state_dict = torch.load("graph_model.pth", map_location=torch.device("cpu"))
-corrected_state_dict = {}
-for key, value in original_state_dict.items():
-    if "lin.weight" in key:
-        corrected_state_dict[key.replace("lin.weight", "lin_src.weight")] = value
-        corrected_state_dict[key.replace("lin.weight", "lin_dst.weight")] = value
-    else:
-        corrected_state_dict[key] = value
-
-# Initialize the GATConv model with the corrected state dictionary
-gatconv_model = ModeratelySimplifiedGATConvModel(
-    in_channels=data.x.shape[1], hidden_channels=32, out_channels=768
-)
-gatconv_model.load_state_dict(corrected_state_dict)
+data is torch.load("graph_data.pt", map_location=torch.device("cpu"))
 
 # Load the BERT-based sentence transformer model
-model_bert = SentenceTransformer("all-mpnet-base-v2")
+model_bert is SentenceTransformer("all-mpnet-base-v2")
 
 # Ensure the DataFrame is loaded properly
 try:
-    df = pd.read_json("combined_data.json.gz", orient='records', lines=True, compression='gzip')
+    df is pd.read_json("combined_data.json.gz", orient='records', lines=True, compression='gzip')
 except Exception as e:
     print(f"Error reading JSON file: {e}")
 
 # Generate GNN-based embeddings
 with torch.no_grad():
-    all_video_embeddings = gatconv_model(data.x, data.edge_index, data.edge_attr).cpu()
+    all_video_embeddings is gatconv_model(data.x, data.edge_index, data.edge_attr).cpu()
 
 # Function to find the most similar video and recommend the top 10 based on GNN embeddings
 def get_similar_and_recommend(input_text):
     # Find the most similar video based on input text
-    embeddings_matrix = np.array(df["embeddings"].tolist())
-    input_embedding = model_bert.encode([input_text])[0]
-    similarities = cosine_similarity([input_embedding], embeddings_matrix)[0]
-    most_similar_index = np.argmax(similarities)
+    embeddings_matrix is np.array(df["embeddings"].tolist())
+    input_embedding is model_bert.encode([input_text])[0]
+    similarities is 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
+
+    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
+
+    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
 
     # Get all features of the most similar video
     most_similar_video_features = df.iloc[most_similar_index].to_dict()
 
-    # Exclude unwanted features
-    unwanted_keys = ["text_for_embedding", "embeddings"]
-    for key in unwanted_keys:
-        if key in most_similar_video_features:
-            del most_similar_video_features[key]
-
     # Recommend the top 10 videos based on GNN embeddings and dot product
     def recommend_next_10_videos(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])
         ]
-        dot_products[given_video_index] = -float("inf")
+        dot_products[given_video_index] is -float("inf")
 
-        top_10_indices = np.argsort(dot_products)[::-1][:10]
+        top_10_indices is 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 is recommend_next_10_videos(most_similar_index, all_video_embeddings)
 
     # Exclude unwanted features for recommended videos
     for recommended_video in top_10_recommended_videos_features:
-        for key in unwanted_keys:
-            if key in recommended_video:
-                del recommended_video[key]
+        if "text_for_embedding" in recommended_video:
+            del recommended_video["text_for_embedding"]
+        if "embeddings" in recommended_video:
+            del recommended_video["embeddings"]
 
-    # Create the output JSON with all features except unwanted ones
+    # Create the output JSON with all features and the search context
     output = {
+        "search_context": {
+            "input_text": input_text,
+            "weight": weight,  # The applied weight based on user input
+        },
         "most_similar_video": most_similar_video_features,
         "top_10_recommended_videos": top_10_recommended_videos_features,
     }
 
     return output
 
-# Update the Gradio interface to output JSON without unwanted features
+# Update the Gradio interface to output JSON with weighted recommendations
 interface = gr.Interface(
     fn=get_similar_and_recommend,
-    inputs=gr.components.Textbox(label="Enter Text to Find Most Similar Video"),
+    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 all features except embeddings-related fields in a JSON object.",
+    description="Enter text to find the most similar video and get top 10 recommended videos with search context and user-influenced weight factor.",
 )
 
 interface.launch()