Create app.py

app.py

@@ -0,0 +1,106 @@
+import gradio as gr
+import torch
+import pandas as pd
+import numpy as np
+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):
+        super().__init__()
+        self.conv1 = GATConv(in_channels, hidden_channels, heads=2)
+        self.dropout1 = torch.nn.Dropout(0.45)
+        self.conv2 = GATConv(hidden_channels * 2, out_channels, heads=1)
+
+    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)
+        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)
+
+# Load the BERT-based sentence transformer model
+model_bert = SentenceTransformer("all-mpnet-base-v2")
+
+# Ensure the DataFrame is loaded properly
+df = pd.read_feather("EmbeddedCombined.feather")
+
+# Generate GNN-based embeddings
+with torch.no_grad():
+    all_video_embeddings = 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)
+
+    most_similar_video = {
+        "title": df["title"].iloc[most_similar_index],
+        "description": df["description"].iloc[most_similar_index],
+        "similarity_score": similarities[most_similar_index],
+    }
+
+    # 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].cpu(), all_video_embeddings[i].cpu())
+            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]
+        recommendations = [df["title"].iloc[idx] for idx in top_10_indices]
+        return recommendations
+
+    top_10_recommendations = recommend_next_10_videos(
+        most_similar_index, all_video_embeddings
+    )
+
+    return (
+        most_similar_video["title"],
+        most_similar_video["description"],
+        most_similar_video["similarity_score"],
+        top_10_recommendations,
+    )
+
+# Update the Gradio interface to fix the output type
+interface = gr.Interface(
+    fn=get_similar_and_recommend,
+    inputs=gr.components.Textbox(label="Enter Text to Find Most Similar Video"),
+    outputs=[
+        gr.components.Textbox(label="Video Title"),
+        gr.components.Textbox(label="Video Description"),
+        gr.components.Textbox(label="Similarity Score"),
+        gr.components.Textbox(label="Top 10 Recommended Videos", lines=10),  # Handle a list
+    ],
+    title="Video Recommendation System with GNN-based Recommendations",
+    description="Enter text to find the most similar video and get the top 10 recommended videos based on dot product and GNN embeddings.",
+)
+
+# Launch the Gradio interface
+interface.launch()