Update app.py

app.py

@@ -4,7 +4,7 @@ from transformers import pipeline
 from sklearn.metrics.pairwise import cosine_similarity
 from sentence_transformers import SentenceTransformer
 import numpy as np
-##
+
 # Set modern page configuration
 st.set_page_config(page_title="News Analyzer", layout="wide")
 
@@ -156,23 +156,24 @@ with col2:
     # Button & Answer Display
     if st.button("🔮 Get Answer"):
         if user_question.strip() and uploaded_file is not None:
-            # Extract the 3rd column from the dataframe
-            context = df.iloc[:, 0].dropna().tolist()   # Get the 3rd column as context (0-based index)
-            
-            # Generate embeddings for the context (3rd column rows) and the question
-            context_embeddings = sentence_model.encode(context)
-            question_embedding = sentence_model.encode([user_question])
-            
-            # Calculate cosine similarity
-            similarities = cosine_similarity(question_embedding, context_embeddings)
-            top_indices = similarities[0].argsort()[-5:][::-1]  # Get top 5 similar rows
-            
-            # Prepare the top 5 similar context rows
-            top_context = "\n".join([context[i] for i in top_indices])
-            
-            # Get answer from Hugging Face model using top context
-            result = pipe(question=user_question, context=top_context)
-            answer = result['answer']
+            with st.spinner("⏳ Wait, our agent will look into that..."):
+                # Extract the 1st column as context (0-indexed)
+                context = df.iloc[:, 0].dropna().tolist()
+                
+                # Generate embeddings for the context rows and the question
+                context_embeddings = sentence_model.encode(context)
+                question_embedding = sentence_model.encode([user_question])
+                
+                # Calculate cosine similarity
+                similarities = cosine_similarity(question_embedding, context_embeddings)
+                top_indices = similarities[0].argsort()[-5:][::-1]  # Get top 5 similar rows
+                
+                # Prepare the top 5 similar context rows
+                top_context = "\n".join([context[i] for i in top_indices])
+                
+                # Get answer from Hugging Face model using top context
+                result = pipe(question=user_question, context=top_context)
+                answer = result['answer']
         else:
             answer = "⚠️ Please upload a valid file first!"