Update app.py

app.py

@@ -24,7 +24,7 @@ if 'feedback' not in st.session_state:
     st.session_state.feedback = {}
 
 # Define subset size
-SUBSET_SIZE = 1000  # Starting with 1000 items for quick testing
+SUBSET_SIZE = 500 # Starting with 500 items for quick testing
 
 class TextDataset(Dataset):
     def __init__(self, texts: List[str], tokenizer, max_length: int = 512):
@@ -176,8 +176,6 @@ st.info(f"Running with a subset of {SUBSET_SIZE} repositories for testing purpos
 data = precompute_embeddings(data, model, tokenizer)
 
 
-# [Previous imports and code remain the same until the UI section]
-
 # Main App Interface
 st.title("Repository Recommender System 🚀")
 st.caption("Testing Version - Running on subset of data")
@@ -199,7 +197,7 @@ with col2:
 if search_button and user_query.strip():
     with st.spinner("Finding relevant repositories..."):
         # Generate query embedding and get recommendations
-        query_embedding = generate_query_embedding(model, tokenizer, user_query)  # Fixed this line
+        query_embedding = generate_query_embedding(model, tokenizer, user_query)
         recommendations = find_similar_repos(query_embedding, data, top_n)
 
         # Save to history
@@ -212,34 +210,61 @@ if search_button and user_query.strip():
         # Display recommendations
         st.markdown("### 🎯 Top Recommendations")
         for idx, row in recommendations.iterrows():
-            with st.expander(f"Repository {idx + 1}: {row['repo']}", expanded=True):
-                # Repository details
-                col1, col2 = st.columns([2, 1])
-                with col1:
-                    st.markdown(f"**URL:** [View Repository]({row['url']})")
-                    st.markdown(f"**Path:** `{row['path']}`")
-                with col2:
-                    st.metric("Match Score", f"{row['similarity']:.2%}")
-
-                    # Feedback buttons
-                    feedback_col1, feedback_col2 = st.columns(2)
-                    with feedback_col1:
-                        if st.button("👍", key=f"like_{idx}"):
-                            save_feedback(row['repo'], 'likes')
-                            st.success("Thanks for your feedback!")
-                    with feedback_col2:
-                        if st.button("👎", key=f"dislike_{idx}"):
-                            save_feedback(row['repo'], 'dislikes')
-                            st.success("Thanks for your feedback!")
-
-                # Case Study Tab
-                with st.expander("📑 Case Study Brief"):
-                    st.markdown(generate_case_study(row))
-
-                # Documentation Tab
+            st.markdown(f"#### Repository {idx + 1}: {row['repo']}")
+            
+            # Repository details in columns
+            col1, col2 = st.columns([2, 1])
+            with col1:
+                st.markdown(f"**URL:** [View Repository]({row['url']})")
+                st.markdown(f"**Path:** `{row['path']}`")
+            with col2:
+                st.metric("Match Score", f"{row['similarity']:.2%}")
+
+            # Feedback buttons in columns
+            feedback_col1, feedback_col2 = st.columns([1, 4])
+            with feedback_col1:
+                if st.button("👍", key=f"like_{idx}"):
+                    save_feedback(row['repo'], 'likes')
+                    st.success("Thanks for your feedback!")
+                if st.button("👎", key=f"dislike_{idx}"):
+                    save_feedback(row['repo'], 'dislikes')
+                    st.success("Thanks for your feedback!")
+
+            # Case Study and Documentation in tabs instead of nested expanders
+            tab1, tab2 = st.tabs(["📑 Case Study Brief", "📚 Documentation"])
+            
+            with tab1:
+                st.markdown(generate_case_study(row))
+            
+            with tab2:
                 if row['docstring']:
-                    with st.expander("📚 Documentation"):
-                        st.markdown(row['docstring'])
+                    st.markdown(row['docstring'])
+                else:
+                    st.info("No documentation available")
+
+            st.markdown("---")  # Separator between repositories
+
+# Sidebar for History and Stats
+with st.sidebar:
+    st.header("📊 Search History")
+    if st.session_state.history:
+        for idx, item in enumerate(reversed(st.session_state.history[-5:])):
+            st.markdown(f"**Search {len(st.session_state.history)-idx}**")
+            st.markdown(f"Query: _{item['query'][:30]}..._")
+            st.caption(f"Time: {item['timestamp']}")
+            st.caption(f"Results: {len(item['results'])} repositories")
+            if st.button("Rerun this search", key=f"rerun_{idx}"):
+                st.session_state.rerun_query = item['query']
+            st.markdown("---")
+    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']])
 
 # Footer
 st.markdown("---")