Update app.py

app.py

@@ -175,34 +175,12 @@ st.info(f"Running with a subset of {SUBSET_SIZE} repositories for testing purpos
 # Precompute embeddings for the subset
 data = precompute_embeddings(data, model, tokenizer)
 
-# Main App Interface
-st.title("Repository Recommender System 🚀")
-st.caption("Testing Version - Running on subset of data")
 
-# Rest of your UI code remains the same...
+# [Previous imports and code remain the same until the UI section]
 
 # Main App Interface
-st.title("Enhanced Repository Recommender System 🚀")
-
-# Sidebar for History and Stats
-with st.sidebar:
-    st.header("📊 Search History")
-    if st.session_state.history:
-        for idx, item in enumerate(st.session_state.history[-5:]):  # Show last 5 searches
-            with st.expander(f"Search {len(st.session_state.history)-idx}: {item['query'][:30]}..."):
-                st.write(f"Time: {item['timestamp']}")
-                st.write(f"Results: {len(item['results'])} repositories")
-                if st.button("Rerun this search", key=f"rerun_{idx}"):
-                    st.session_state.rerun_query = item['query']
-    else:
-        st.write("No search history yet")
-
-    st.header("📈 Usage Statistics")
-    st.write(f"Total Searches: {len(st.session_state.history)}")
-    if st.session_state.feedback:
-        feedback_df = pd.DataFrame(st.session_state.feedback).T
-        feedback_df['Total'] = feedback_df['likes'] + feedback_df['dislikes']
-        st.bar_chart(feedback_df[['likes', 'dislikes']])
+st.title("Repository Recommender System 🚀")
+st.caption("Testing Version - Running on subset of data")
 
 # Main interface
 user_query = st.text_area(
@@ -221,11 +199,8 @@ with col2:
 if search_button and user_query.strip():
     with st.spinner("Finding relevant repositories..."):
         # Generate query embedding and get recommendations
-        query_embedding = generate_embedding(model, tokenizer, user_query)
-        data['similarity'] = data['embedding'].apply(
-            lambda x: cosine_similarity([query_embedding], [x])[0][0]
-        )
-        recommendations = data.nlargest(top_n, 'similarity')
+        query_embedding = generate_query_embedding(model, tokenizer, user_query)  # Fixed this line
+        recommendations = find_similar_repos(query_embedding, data, top_n)
 
         # Save to history
         st.session_state.history.append({