Update app.py

app.py

@@ -1,11 +1,8 @@
 import streamlit as st
 import pandas as pd
-import numpy as np
-import json
 import os
 import glob
 import random
-from pathlib import Path
 from datetime import datetime
 import edge_tts
 import asyncio
@@ -52,8 +49,7 @@ SESSION_VARS = {
     'voice_text': None,
     'user_name': random.choice(USER_NAMES),
     'max_items': 100,
-    'global_voice': "en-US-AriaNeural",
-    'last_arxiv_input': None
+    'global_voice': "en-US-AriaNeural"
 }
 
 for var, default in SESSION_VARS.items():
@@ -188,8 +184,6 @@ def simple_dataset_search(query, df):
         return pd.DataFrame(matches)
     return pd.DataFrame()
 
-from datasets import load_dataset
-
 @st.cache_data
 def load_dataset_page(dataset_id, token, page, rows_per_page):
     try:
@@ -213,7 +207,6 @@ class SimpleDatasetSearcher:
         return load_dataset_page(self.dataset_id, self.token, page, ROWS_PER_PAGE)
 
 def concatenate_mp3(files, output_file):
-    # Naive binary concatenation of MP3 files
     with open(output_file, 'wb') as outfile:
         for f in files:
             with open(f, 'rb') as infile:
@@ -222,11 +215,8 @@ def concatenate_mp3(files, output_file):
 def main():
     st.title("🎙️ Voice Chat & Search")
 
-    # Sidebar
     with st.sidebar:
-        # Editable user name
         st.session_state['user_name'] = st.selectbox("Current User:", USER_NAMES, index=0)
-        
         st.session_state['max_items'] = st.number_input("Max Items per search iteration:", min_value=1, max_value=1000, value=st.session_state['max_items'])
         
         st.subheader("📝 Saved Inputs & Responses")
@@ -236,14 +226,11 @@ def main():
             fname = os.path.basename(fpath)
             st.write(f"- {fname} (User: {user})")
 
-    # Create voice component for input
     voice_component = create_voice_component()
     voice_val = voice_component(my_input_value="Start speaking...")
 
-    # Tabs
     tab1, tab2, tab3, tab4 = st.tabs(["🗣️ Voice Chat History", "📚 ArXiv Search", "📊 Dataset Search", "⚙️ Settings"])
 
-    # ------------------ Voice Chat History -------------------------
     with tab1:
         st.subheader("Voice Chat History")
         files = list_saved_inputs()
@@ -252,20 +239,16 @@ def main():
             user, ts, content = parse_md_file(fpath)
             conversation.append((user, ts, content, fpath))
 
-        # Enumerate to ensure unique keys
         for i, (user, ts, content, fpath) in enumerate(reversed(conversation), start=1):
             with st.expander(f"{ts} - {user}", expanded=False):
                 st.write(content)
-                # Make button key unique by including i
                 if st.button(f"🔊 Read Aloud {ts}-{user}", key=f"read_{i}_{fpath}"):
                     voice = USER_VOICES.get(user, "en-US-AriaNeural")
                     audio_file = speak_with_edge_tts(content, voice=voice)
                     if audio_file:
                         play_and_download_audio(audio_file)
 
-        # Read entire conversation
         if st.button("📜 Read Conversation", key="read_conversation_all"):
-            # conversation is currently reversed, re-reverse to get chronological
             conversation_chrono = list(reversed(conversation))
             mp3_files = []
             for user, ts, content, fpath in conversation_chrono:
@@ -282,7 +265,6 @@ def main():
                 st.write("**Full Conversation Audio:**")
                 play_and_download_audio(combined_file)
 
-    # ------------------ ArXiv Search -------------------------
     with tab2:
         st.subheader("ArXiv Search")
         edited_input = st.text_area("Enter or Edit Search Query:", value=(voice_val.strip() if voice_val else ""), height=100)
@@ -296,9 +278,8 @@ def main():
         if run_arxiv and edited_input.strip():
             should_run_arxiv = True
 
-        if should_run_arxiv and st.session_state['last_arxiv_input'] != edited_input:
+        if should_run_arxiv:
             st.session_state['old_val'] = edited_input
-            st.session_state['last_arxiv_input'] = edited_input
             save_input_as_md(st.session_state['user_name'], edited_input, prefix="input")
             with st.spinner("Searching ArXiv..."):
                 results = arxiv_search(edited_input)
@@ -306,7 +287,6 @@ def main():
                     summary = summarize_arxiv_results(results)
                     save_response_as_md(st.session_state['user_name'], summary, prefix="response")
                     st.write(summary)
-                    # Play summary aloud
                     voice = USER_VOICES.get(st.session_state['user_name'], "en-US-AriaNeural")
                     audio_file = speak_with_edge_tts(summary, voice=voice)
                     if audio_file:
@@ -314,7 +294,6 @@ def main():
                 else:
                     st.warning("No results found on ArXiv.")
 
-    # ------------------ Dataset Search -------------------------
     with tab3:
         st.subheader("Dataset Search")
         ds_searcher = SimpleDatasetSearcher()
@@ -339,11 +318,9 @@ def main():
                 else:
                     st.warning("No matching results found.")
 
-    # ------------------ Settings Tab -------------------------
     with tab4:
         st.subheader("Settings")
         if st.button("🗑️ Clear Search History", key="clear_history"):
-            # Delete all files
             for fpath in list_saved_inputs():
                 os.remove(fpath)
             st.session_state['search_history'] = []