Update app.py

app.py

@@ -1,3 +1,24 @@
+import gradio as gr
+import torch
+import pickle
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from sklearn.preprocessing import normalize
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load the pre-trained embedding model (SentenceTransformer)
+model = SentenceTransformer('nomic-ai/nomic-embed-text-v1')
+
+# Load BART summarization model and tokenizer
+model_bart = torch.hub.load('pytorch/fairseq', 'bart.large.cnn')
+tokenizer = torch.hub.load('huggingface/pytorch-transformers', 'tokenizer', 'facebook/bart-large-cnn')
+
+# Load normalized embeddings from the pkl file
+with open('normalized_embeddings.pkl', 'rb') as f:
+    normalized_embeddings = pickle.load(f)
+
+# Load the hotel dataset (processed)
+df_copy_first_1000 = pd.read_csv('hotel_dataset_processed.csv')
 
 # Function to summarize text using BART
 def summarize_text(text):
@@ -6,14 +27,15 @@ def summarize_text(text):
     summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
     return summary
 
+# Function to search hotels
 def search_hotels(query_text, k=1):
     try:
-        # Encode the query text
+        # Encode the query text using SentenceTransformer
         query_embedding = model.encode(query_text, convert_to_tensor=True)
         query_embedding = query_embedding.cpu().numpy().reshape(1, -1)
         query_embedding = normalize(query_embedding, norm='l2')
 
-        # Compute cosine similarity between query and stored embeddings
+        # Compute cosine similarity between query embedding and stored embeddings
         similarities = cosine_similarity(query_embedding, normalized_embeddings)
 
         # Get indices of the top k similar hotels
@@ -25,8 +47,13 @@ def search_hotels(query_text, k=1):
         # Prepare results
         results = []
         for _, row in top_hotels.iterrows():
-            # Create a summary for the description, review title, review text, and review count
-            summary_text = f"Description: {row['hotel_description']}\nReview Title: {row['review_title']}\nReview Text: {row['review_text']}\nReview Count: {row['review_count']}"
+            # Create a summary for the hotel details
+            summary_text = (
+                f"Description: {row['hotel_description']}\n"
+                f"Review Title: {row['review_title']}\n"
+                f"Review Text: {row['review_text']}\n"
+                f"Review Count: {row['review_count']}"
+            )
             summary = summarize_text(summary_text)
 
             result = (
@@ -34,7 +61,7 @@ def search_hotels(query_text, k=1):
                 f"Locality: {row['locality']}\n"
                 f"Price Range: {row['price_range']}\n"
                 f"Rate: {row['rate']}\n"
-                f"\n {summary}\n"
+                f"\nSummary:\n{summary}\n"
             )
             results.append(result)
 
@@ -53,5 +80,4 @@ iface = gr.Interface(
 )
 
 # Launch Gradio Interface
-if __name__ == "__main__":
-    iface.launch()
+iface.launch()