Update app.py

app.py

@@ -1,13 +1,23 @@
 import streamlit as st
-import anthropic
-import openai
-import base64
-import os
-import re
-import asyncio
+import anthropic, openai, base64, cv2, glob, json, math, os, pytz, random, re, requests, textract, time, zipfile
+import plotly.graph_objects as go
+import streamlit.components.v1 as components
 from datetime import datetime
+from audio_recorder_streamlit import audio_recorder
+from bs4 import BeautifulSoup
+from collections import defaultdict, deque
+from dotenv import load_dotenv
 from gradio_client import Client
-from collections import defaultdict
+from huggingface_hub import InferenceClient
+from io import BytesIO
+from PIL import Image
+from PyPDF2 import PdfReader
+from urllib.parse import quote
+from xml.etree import ElementTree as ET
+from openai import OpenAI
+import extra_streamlit_components as stx
+from streamlit.runtime.scriptrunner import get_script_run_ctx
+import asyncio
 import edge_tts
 
 # 🎯 1. Core Configuration & Setup
@@ -22,22 +32,12 @@ st.set_page_config(
         'About': "🚲BikeAI🏆 Claude/GPT Research AI"
     }
 )
-st.markdown("""
-    <style>
-        .main { background: linear-gradient(to right, #1a1a1a, #2d2d2d); color: #fff; }
-        .stMarkdown { font-family: 'Helvetica Neue', sans-serif; }
-        .stButton>button {
-            margin-right: 0.5rem;
-        }
-    </style>
-    """, unsafe_allow_html=True)
-
-# 🔑 2. API Setup & Clients
-from dotenv import load_dotenv
 load_dotenv()
 
+# 🔑 2. API Setup & Clients
 openai_api_key = os.getenv('OPENAI_API_KEY', "")
 anthropic_key = os.getenv('ANTHROPIC_API_KEY_3', "")
+xai_key = os.getenv('xai',"")
 if 'OPENAI_API_KEY' in st.secrets:
     openai_api_key = st.secrets['OPENAI_API_KEY']
 if 'ANTHROPIC_API_KEY' in st.secrets:
@@ -45,7 +45,9 @@ if 'ANTHROPIC_API_KEY' in st.secrets:
 
 openai.api_key = openai_api_key
 claude_client = anthropic.Anthropic(api_key=anthropic_key)
-openai_client = openai  # Using OpenAI directly
+openai_client = OpenAI(api_key=openai.api_key, organization=os.getenv('OPENAI_ORG_ID'))
+HF_KEY = os.getenv('HF_KEY')
+API_URL = os.getenv('API_URL')
 
 # 📝 3. Session State Management
 if 'transcript_history' not in st.session_state:
@@ -53,9 +55,17 @@ if 'transcript_history' not in st.session_state:
 if 'chat_history' not in st.session_state:
     st.session_state['chat_history'] = []
 if 'openai_model' not in st.session_state:
-    st.session_state['openai_model'] = "gpt-4"  # Update as needed
+    st.session_state['openai_model'] = "gpt-4o-2024-05-13"
 if 'messages' not in st.session_state:
     st.session_state['messages'] = []
+if 'last_voice_input' not in st.session_state:
+    st.session_state['last_voice_input'] = ""
+if 'editing_file' not in st.session_state:
+    st.session_state['editing_file'] = None
+if 'edit_new_name' not in st.session_state:
+    st.session_state['edit_new_name'] = ""
+if 'edit_new_content' not in st.session_state:
+    st.session_state['edit_new_content'] = ""
 if 'viewing_prefix' not in st.session_state:
     st.session_state['viewing_prefix'] = None
 if 'should_rerun' not in st.session_state:
@@ -63,7 +73,23 @@ if 'should_rerun' not in st.session_state:
 if 'old_val' not in st.session_state:
     st.session_state['old_val'] = None
 
-# 🧠 4. High-Information Content Extraction
+# 🎨 4. Custom CSS
+st.markdown("""
+<style>
+    .main { background: linear-gradient(to right, #1a1a1a, #2d2d2d); color: #fff; }
+    .stMarkdown { font-family: 'Helvetica Neue', sans-serif; }
+    .stButton>button {
+        margin-right: 0.5rem;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+FILE_EMOJIS = {
+    "md": "📝",
+    "mp3": "🎵",
+}
+
+# 🧠 5. High-Information Content Extraction
 def get_high_info_terms(text: str) -> list:
     """Extract high-information terms from text, including key phrases."""
     stop_words = set([
@@ -124,7 +150,7 @@ def clean_text_for_filename(text: str) -> str:
     filtered = [w for w in words if len(w)>3 and w not in stop_short]
     return '_'.join(filtered)[:200]
 
-# 📁 5. File Operations
+# 📁 6. File Operations
 def generate_filename(prompt, response, file_type="md"):
     """
     Generate filename with meaningful terms and short dense clips from prompt & response.
@@ -150,7 +176,7 @@ def generate_filename(prompt, response, file_type="md"):
     return filename
 
 def create_file(prompt, response, file_type="md"):
-    """Create file with an intelligent naming scheme."""
+    """Create file with intelligent naming"""
     filename = generate_filename(prompt.strip(), response.strip(), file_type)
     with open(filename, 'w', encoding='utf-8') as f:
         f.write(prompt + "\n\n" + response)
@@ -162,7 +188,7 @@ def get_download_link(file):
         b64 = base64.b64encode(f.read()).decode()
     return f'<a href="data:file/zip;base64,{b64}" download="{os.path.basename(file)}">📂 Download {os.path.basename(file)}</a>'
 
-# 🔊 6. Audio Processing
+# 🔊 7. Audio Processing
 def clean_for_speech(text: str) -> str:
     """Clean text for speech synthesis"""
     text = text.replace("\n", " ")
@@ -172,64 +198,53 @@ def clean_for_speech(text: str) -> str:
     text = re.sub(r"\s+", " ", text).strip()
     return text
 
-async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=0, out_fn="temp.mp3"):
-    """Generate audio using Edge TTS (async)"""
+@st.cache_resource
+def speech_synthesis_html(result):
+    """Create HTML for speech synthesis"""
+    html_code = f"""
+    <html><body>
+    <script>
+    var msg = new SpeechSynthesisUtterance("{result.replace('"', '')}");
+    window.speechSynthesis.speak(msg);
+    </script>
+    </body></html>
+    """
+    components.html(html_code, height=0)
+
+async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=0):
+    """Generate audio using Edge TTS"""
     text = clean_for_speech(text)
     if not text.strip():
         return None
     rate_str = f"{rate:+d}%"
     pitch_str = f"{pitch:+d}Hz"
     communicate = edge_tts.Communicate(text, voice, rate=rate_str, pitch=pitch_str)
+    out_fn = generate_filename(text, text, "mp3")
     await communicate.save(out_fn)
     return out_fn
 
-def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0, out_fn="temp.mp3"):
-    """Wrapper for Edge TTS generation (sync)"""
-    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch, out_fn))
+def speak_with_edge_tts(text, voice, rate=0, pitch=0):
+    """Wrapper for edge TTS generation"""
+    try:
+        return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch))
+    except Exception as e:
+        st.error(f"Error generating audio: {e}")
+        return None
 
 def play_and_download_audio(file_path):
-    """Play and provide a download link for audio"""
+    """Play and provide download link for audio"""
     if file_path and os.path.exists(file_path):
         st.audio(file_path)
         dl_link = f'<a href="data:audio/mpeg;base64,{base64.b64encode(open(file_path,"rb").read()).decode()}" download="{os.path.basename(file_path)}">Download {os.path.basename(file_path)}</a>'
         st.markdown(dl_link, unsafe_allow_html=True)
 
-def auto_play_audio(file_path):
-    """Embeds an <audio> tag with autoplay + controls + a download link."""
-    if not file_path or not os.path.exists(file_path):
-        return
-    with open(file_path, "rb") as f:
-        b64_data = base64.b64encode(f.read()).decode("utf-8")
-    filename = os.path.basename(file_path)
-    st.markdown(f"""
-    <audio controls autoplay>
-        <source src="data:audio/mpeg;base64,{b64_data}" type="audio/mpeg">
-        Your browser does not support the audio element.
-    </audio>
-    <br/>
-    <a href="data:audio/mpeg;base64,{b64_data}" download="{filename}">
-        Download {filename}
-    </a>
-    """, unsafe_allow_html=True)
-
-def generate_audio_filename(query, title, summary):
-    """
-    Generate a specialized MP3 filename using query + title + summary.
-    Example: "2310_1205_query_title_summary.mp3"
-    """
-    combined = (query + " " + title + " " + summary).strip().lower()
-    combined = re.sub(r'[^\w\s-]', '', combined)  # Remove special characters
-    combined = "_".join(combined.split())[:80]    # Limit length
-    prefix = datetime.now().strftime("%y%m_%H%M")
-    return f"{prefix}_{combined}.mp3"
-
-# 🎬 7. Media Processing
+# 🎬 8. Media Processing
 def process_image(image_path, user_prompt):
     """Process image with GPT-4V"""
     with open(image_path, "rb") as imgf:
         image_data = imgf.read()
     b64img = base64.b64encode(image_data).decode("utf-8")
-    resp = openai_client.ChatCompletion.create(
+    resp = openai_client.chat.completions.create(
         model=st.session_state["openai_model"],
         messages=[
             {"role": "system", "content": "You are a helpful assistant."},
@@ -242,25 +257,24 @@ def process_image(image_path, user_prompt):
     )
     return resp.choices[0].message.content
 
-def process_audio_with_whisper(audio_path):
+def process_audio(audio_path):
     """Process audio with Whisper"""
     with open(audio_path, "rb") as f:
-        transcription = openai_client.Audio.transcriptions.create(model="whisper-1", file=f)
+        transcription = openai_client.audio.transcriptions.create(model="whisper-1", file=f)
     st.session_state.messages.append({"role": "user", "content": transcription.text})
     return transcription.text
 
 def process_video(video_path, seconds_per_frame=1):
     """Extract frames from video"""
-    import cv2
     vid = cv2.VideoCapture(video_path)
     total = int(vid.get(cv2.CAP_PROP_FRAME_COUNT))
     fps = vid.get(cv2.CAP_PROP_FPS)
-    skip = int(fps * seconds_per_frame)
+    skip = int(fps*seconds_per_frame)
     frames_b64 = []
     for i in range(0, total, skip):
         vid.set(cv2.CAP_PROP_POS_FRAMES, i)
         ret, frame = vid.read()
-        if not ret:
+        if not ret: 
             break
         _, buf = cv2.imencode(".jpg", frame)
         frames_b64.append(base64.b64encode(buf).decode("utf-8"))
@@ -270,61 +284,196 @@ def process_video(video_path, seconds_per_frame=1):
 def process_video_with_gpt(video_path, prompt):
     """Analyze video frames with GPT-4V"""
     frames = process_video(video_path)
-    resp = openai_client.ChatCompletion.create(
+    resp = openai_client.chat.completions.create(
         model=st.session_state["openai_model"],
         messages=[
-            {"role": "system", "content": "Analyze video frames."},
-            {"role": "user", "content": [
-                {"type": "text", "text": prompt},
+            {"role":"system","content":"Analyze video frames."},
+            {"role":"user","content":[
+                {"type":"text","text":prompt},
                 *[{"type":"image_url","image_url":{"url":f"data:image/jpeg;base64,{fr}"}} for fr in frames]
             ]}
         ]
     )
     return resp.choices[0].message.content
 
-# 🤖 8. AI Model Integration
+# 🤖 9. AI Model Integration
+
 def save_full_transcript(query, text):
     """Save full transcript of Arxiv results as a file."""
     create_file(query, text, "md")
 
+def parse_arxiv_refs(ref_text: str):
+    """
+    Parse the multi-line references returned by the RAG pipeline.
+    Typical format lines like:
+       1) [Paper Title 2023] This is the summary ...
+       2) [Another Title (2024)] Another summary text ...
+    We'll attempt to find a year with a small regex or fallback.
+    Return list of dicts: { 'title': str, 'summary': str, 'year': int or None }
+    """
+    lines = ref_text.split('\n')
+    results = []
+    for line in lines:
+        line = line.strip()
+        if not line:
+            continue
+        # Attempt to find [Title ...]
+        title_match = re.search(r"\[([^\]]+)\]", line)
+        if title_match:
+            raw_title = title_match.group(1).strip()
+        else:
+            # If no bracket found, skip or treat entire line as summary
+            raw_title = "No Title"
+
+        # Attempt to find trailing summary after bracket
+        # Example line: " [Paper Title 2024] Paper summary blah blah"
+        # So remove the bracketed portion from the line
+        remainder = line.replace(title_match.group(0), "").strip() if title_match else line
+        summary = remainder
+
+        # Attempt to guess year from the raw title
+        # We look for 4-digit patterns in raw_title or summary
+        year_match = re.search(r'(20\d{2})', raw_title)
+        if not year_match:
+            # fallback: try summary
+            year_match = re.search(r'(20\d{2})', summary)
+        if year_match:
+            year = int(year_match.group(1))
+        else:
+            year = None
+
+        results.append({
+            'title': raw_title,
+            'summary': summary,
+            'year': year
+        })
+    return results
+
+
+def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, 
+                      titles_summary=True, full_audio=False, selected_voice="en-US-AriaNeural"):
+    """Perform Arxiv search and generate audio summaries."""
+    start = time.time()
+
+    # 🎯 1) Query the HF RAG pipeline
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    refs = client.predict(q,20,"Semantic Search","mistralai/Mixtral-8x7B-Instruct-v0.1",api_name="/update_with_rag_md")[0]
+    r2 = client.predict(q,"mistralai/Mixtral-8x7B-Instruct-v0.1",True,api_name="/ask_llm")
+
+    # 🎯 2) Combine for final text output
+    result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"
+    st.markdown(result)
+
+    # 🎯 3) Generate "all at once" audio if requested
+    if full_audio:
+        complete_text = f"Complete response for query: {q}. {clean_for_speech(r2)} {clean_for_speech(refs)}"
+        audio_file_full = speak_with_edge_tts(complete_text, selected_voice)
+        st.write("### 📚 Full Audio")
+        play_and_download_audio(audio_file_full)
+
+    if vocal_summary:
+        main_text = clean_for_speech(r2)
+        audio_file_main = speak_with_edge_tts(main_text, selected_voice)
+        st.write("### 🎙 Short Audio")
+        play_and_download_audio(audio_file_main)
+
+    if extended_refs:
+        summaries_text = "Extended references: " + refs.replace('"','')
+        summaries_text = clean_for_speech(summaries_text)
+        audio_file_refs = speak_with_edge_tts(summaries_text, selected_voice)
+        st.write("### 📜 Long Refs")
+        play_and_download_audio(audio_file_refs)
+
+    # --------------------------------------
+    # NEW: Parse references, show sorted list
+    # --------------------------------------
+    parsed_refs = parse_arxiv_refs(refs)
+
+    # Sort by year descending (put None at bottom)
+    parsed_refs.sort(key=lambda x: x["year"] if x["year"] else 0, reverse=True)
+
+    st.write("## Individual Papers (Most Recent First)")
+    for idx, paper in enumerate(parsed_refs):
+        year_str = paper["year"] if paper["year"] else "Unknown Year"
+        st.markdown(f"**{idx+1}. {paper['title']}**  \n*Year:* {year_str}")
+        st.markdown(f"*Summary:* {paper['summary']}")
+
+        # Two new TTS buttons: Title only or Title+Summary
+        colA, colB = st.columns(2)
+        with colA:
+            if st.button(f"🔊 Title", key=f"title_{idx}"):
+                text_tts = clean_for_speech(paper['title'])
+                audio_file_title = speak_with_edge_tts(text_tts, selected_voice)
+                play_and_download_audio(audio_file_title)
+
+        with colB:
+            if st.button(f"🔊 Title+Summary", key=f"summary_{idx}"):
+                text_tts = clean_for_speech(paper['title'] + ". " + paper['summary'])
+                audio_file_title_summary = speak_with_edge_tts(text_tts, selected_voice)
+                play_and_download_audio(audio_file_title_summary)
+
+        st.write("---")
+
+    # Keep your original block for "Titles Only" if you want:
+    if titles_summary:
+        titles = []
+        for line in refs.split('\n'):
+            m = re.search(r"\[([^\]]+)\]", line)
+            if m:
+                titles.append(m.group(1))
+        if titles:
+            titles_text = "Titles: " + ", ".join(titles)
+            titles_text = clean_for_speech(titles_text)
+            audio_file_titles = speak_with_edge_tts(titles_text, selected_voice)
+            st.write("### 🔖 Titles (All-In-One)")
+            play_and_download_audio(audio_file_titles)
+
+    elapsed = time.time()-start
+    st.write(f"**Total Elapsed:** {elapsed:.2f} s")
+
+    # Always create a file with the result
+    create_file(q, result, "md")
+
+    return result
+
 def process_with_gpt(text):
     """Process text with GPT-4"""
-    if not text:
+    if not text: 
         return
     st.session_state.messages.append({"role":"user","content":text})
     with st.chat_message("user"):
         st.markdown(text)
     with st.chat_message("assistant"):
-        c = openai_client.ChatCompletion.create(
+        c = openai_client.chat.completions.create(
             model=st.session_state["openai_model"],
             messages=st.session_state.messages,
             stream=False
         )
         ans = c.choices[0].message.content
-        st.write("GPT-4: " + ans)
+        st.write("GPT-4o: " + ans)
         create_file(text, ans, "md")
         st.session_state.messages.append({"role":"assistant","content":ans})
     return ans
 
 def process_with_claude(text):
     """Process text with Claude"""
-    if not text:
+    if not text: 
         return
     with st.chat_message("user"):
         st.markdown(text)
     with st.chat_message("assistant"):
-        r = claude_client.completions.create(
-            prompt=text,
-            model="claude-3",
-            max_tokens=1000
+        r = claude_client.messages.create(
+            model="claude-3-sonnet-20240229",
+            max_tokens=1000,
+            messages=[{"role":"user","content":text}]
         )
-        ans = r['completion']
+        ans = r.content[0].text
         st.write("Claude-3.5: " + ans)
         create_file(text, ans, "md")
         st.session_state.chat_history.append({"user":text,"claude":ans})
     return ans
 
-# 📂 9. File Management
+# 📂 10. File Management
 def create_zip_of_files(md_files, mp3_files):
     """Create zip with intelligent naming"""
     md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
@@ -358,21 +507,22 @@ def load_files_for_sidebar():
     """Load and group files for sidebar display"""
     md_files = glob.glob("*.md")
     mp3_files = glob.glob("*.mp3")
-    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
 
+    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
     all_files = md_files + mp3_files
+
     groups = defaultdict(list)
     for f in all_files:
         fname = os.path.basename(f)
-        prefix = fname[:10]  # e.g., "2310_1205_"
+        prefix = fname[:10]
         groups[prefix].append(f)
 
     for prefix in groups:
         groups[prefix].sort(key=lambda x: os.path.getmtime(x), reverse=True)
 
     sorted_prefixes = sorted(groups.keys(), 
-                             key=lambda pre: max(os.path.getmtime(x) for x in groups[pre]), 
-                             reverse=True)
+                           key=lambda pre: max(os.path.getmtime(x) for x in groups[pre]), 
+                           reverse=True)
     return groups, sorted_prefixes
 
 def extract_keywords_from_md(files):
@@ -412,7 +562,7 @@ def display_file_manager_sidebar(groups, sorted_prefixes):
         if st.button("⬇️ ZipAll"):
             z = create_zip_of_files(all_md, all_mp3)
             if z:
-                st.sidebar.markdown(get_download_link(z), unsafe_allow_html=True)
+                st.sidebar.markdown(get_download_link(z),unsafe_allow_html=True)
 
     for prefix in sorted_prefixes:
         files = groups[prefix]
@@ -435,32 +585,106 @@ def display_file_manager_sidebar(groups, sorted_prefixes):
                 ctime = datetime.fromtimestamp(os.path.getmtime(f)).strftime("%Y-%m-%d %H:%M:%S")
                 st.write(f"**{fname}** - {ctime}")
 
-# 🎯 10. Main Application
+# 🎯 11. Main Application
+async def get_available_voices():
+    voices = await edge_tts.list_voices()
+    return [voice["shortName"] for voice in voices]
+
+@st.cache_resource
+def fetch_voices():
+    return asyncio.run(get_available_voices())
+
 def main():
     st.sidebar.markdown("### 🚲BikeAI🏆 Multi-Agent Research")
-    tab_main = st.radio("Action:", ["🎤 Voice","📸 Media","🔍 ArXiv","📝 Editor"], horizontal=True)
+    tab_main = st.radio("Action:",["🎤 Voice","📸 Media","🔍 ArXiv","📝 Editor"],horizontal=True)
 
-    # Placeholder for custom component if needed
-    # mycomponent = components.declare_component("mycomponent", path="mycomponent")
-    # val = mycomponent(my_input_value="Hello")
+    mycomponent = components.declare_component("mycomponent", path="mycomponent")
+    val = mycomponent(my_input_value="Hello")
 
-    # Example input handling
-    # if val:
-    #     # Handle custom component input
-    #     pass
+    if 'voices' not in st.session_state:
+        st.session_state['voices'] = fetch_voices()
+
+    st.sidebar.markdown("### 🎤 Select Voice for Audio Generation")
+    selected_voice = st.sidebar.selectbox(
+        "Choose a voice:",
+        options=st.session_state['voices'],
+        index=st.session_state['voices'].index("en-US-AriaNeural") if "en-US-AriaNeural" in st.session_state['voices'] else 0
+    )
+
+    # Show input in a text box for editing if detected
+    if val:
+        val_stripped = val.replace('\n', ' ')
+        edited_input = st.text_area("✏️ Edit Input:", value=val_stripped, height=100)
+        run_option = st.selectbox("Model:", ["Arxiv", "GPT-4o", "Claude-3.5"])
+        col1, col2 = st.columns(2)
+        with col1:
+            autorun = st.checkbox("⚙ AutoRun", value=True)
+        with col2:
+            full_audio = st.checkbox("📚FullAudio", value=False, 
+                                     help="Generate full audio response")
+
+        input_changed = (val != st.session_state.old_val)
+
+        if autorun and input_changed:
+            st.session_state.old_val = val
+            if run_option == "Arxiv":
+                perform_ai_lookup(
+                    edited_input, 
+                    vocal_summary=True, 
+                    extended_refs=False, 
+                    titles_summary=True, 
+                    full_audio=full_audio,
+                    selected_voice=selected_voice
+                )
+            else:
+                if run_option == "GPT-4o":
+                    process_with_gpt(edited_input)
+                elif run_option == "Claude-3.5":
+                    process_with_claude(edited_input)
+        else:
+            if st.button("▶ Run"):
+                st.session_state.old_val = val
+                if run_option == "Arxiv":
+                    perform_ai_lookup(
+                        edited_input, 
+                        vocal_summary=True, 
+                        extended_refs=False, 
+                        titles_summary=True, 
+                        full_audio=full_audio,
+                        selected_voice=selected_voice
+                    )
+                else:
+                    if run_option == "GPT-4o":
+                        process_with_gpt(edited_input)
+                    elif run_option == "Claude-3.5":
+                        process_with_claude(edited_input)
 
     if tab_main == "🔍 ArXiv":
         st.subheader("🔍 Query ArXiv")
         q = st.text_input("🔍 Query:")
 
         st.markdown("### 🎛 Options")
-        full_audio = st.checkbox("📚 Full Audio", value=False, help="Generate full audio response")
-        full_transcript = st.checkbox("🧾 Full Transcript", value=False, help="Generate a full transcript file")
+        vocal_summary = st.checkbox("🎙ShortAudio", value=True)
+        extended_refs = st.checkbox("📜LongRefs", value=False)
+        titles_summary = st.checkbox("🔖TitlesOnly", value=True)
+        full_audio = st.checkbox("📚FullAudio", value=False,
+                                 help="Full audio of results")
+        full_transcript = st.checkbox("🧾FullTranscript", value=False,
+                                      help="Generate a full transcript file")
+
+        if q and st.button("🔍Run"):
+            result = perform_ai_lookup(q, vocal_summary=vocal_summary, extended_refs=extended_refs, 
+                                       titles_summary=titles_summary, full_audio=full_audio, selected_voice=selected_voice)
+            if full_transcript:
+                save_full_transcript(q, result)
 
-        if q and st.button("🔍 Run Query"):
-            perform_ai_lookup(q)
+        st.markdown("### Change Prompt & Re-Run")
+        q_new = st.text_input("🔄 Modify Query:")
+        if q_new and st.button("🔄 Re-Run with Modified Query"):
+            result = perform_ai_lookup(q_new, vocal_summary=vocal_summary, extended_refs=extended_refs, 
+                                       titles_summary=titles_summary, full_audio=full_audio, selected_voice=selected_voice)
             if full_transcript:
-                create_file(q, "Full transcript generated.", "md")  # Customize as needed
+                save_full_transcript(q_new, result)
 
     elif tab_main == "🎤 Voice":
         st.subheader("🎤 Voice Input")
@@ -469,7 +693,7 @@ def main():
         if st.button("📨 Send"):
             process_with_gpt(user_text)
         st.subheader("📜 Chat History")
-        t1, t2 = st.tabs(["Claude History","GPT-4 History"])
+        t1,t2=st.tabs(["Claude History","GPT-4o History"])
         with t1:
             for c in st.session_state.chat_history:
                 st.write("**You:**", c["user"])
@@ -483,51 +707,45 @@ def main():
         st.header("📸 Images & 🎥 Videos")
         tabs = st.tabs(["🖼 Images", "🎥 Video"])
         with tabs[0]:
-            imgs = glob.glob("*.png") + glob.glob("*.jpg") + glob.glob("*.jpeg")
+            imgs = glob.glob("*.png")+glob.glob("*.jpg")
             if imgs:
-                cols = st.columns(st.slider("Cols", 1, 5, 3))
-                for i, f in enumerate(imgs):
-                    with cols[i % len(cols)]:
-                        st.image(Image.open(f), use_container_width=True)
+                c = st.slider("Cols",1,5,3)
+                cols = st.columns(c)
+                for i,f in enumerate(imgs):
+                    with cols[i%c]:
+                        st.image(Image.open(f),use_container_width=True)
                         if st.button(f"👀 Analyze {os.path.basename(f)}", key=f"analyze_{f}"):
-                            a = process_image(f, "Describe this image.")
+                            a = process_image(f,"Describe this image.")
                             st.markdown(a)
             else:
                 st.write("No images found.")
         with tabs[1]:
-            vids = glob.glob("*.mp4") + glob.glob("*.avi") + glob.glob("*.mov")
+            vids = glob.glob("*.mp4")
             if vids:
                 for v in vids:
                     with st.expander(f"🎥 {os.path.basename(v)}"):
                         st.video(v)
                         if st.button(f"Analyze {os.path.basename(v)}", key=f"analyze_{v}"):
-                            a = process_video_with_gpt(v, "Describe this video.")
+                            a = process_video_with_gpt(v,"Describe video.")
                             st.markdown(a)
             else:
                 st.write("No videos found.")
 
     elif tab_main == "📝 Editor":
-        st.subheader("📝 File Editor")
-        # Example editor logic: list markdown files and allow editing
-        md_files = glob.glob("*.md")
-        if md_files:
-            selected_file = st.selectbox("Select a file to edit:", md_files)
-            with st.form("edit_form"):
-                new_content = st.text_area("✏️ Content:", open(selected_file, 'r', encoding='utf-8').read(), height=300)
-                submitted = st.form_submit_button("💾 Save")
-                if submitted:
-                    with open(selected_file, 'w', encoding='utf-8') as f:
-                        f.write(new_content)
-                    st.success(f"Updated {selected_file}!")
-                    st.session_state.should_rerun = True
+        if getattr(st.session_state,'current_file',None):
+            st.subheader(f"Editing: {st.session_state.current_file}")
+            new_text = st.text_area("✏️ Content:", st.session_state.file_content, height=300)
+            if st.button("💾 Save"):
+                with open(st.session_state.current_file,'w',encoding='utf-8') as f:
+                    f.write(new_text)
+                st.success("Updated!")
+                st.session_state.should_rerun = True
         else:
-            st.write("No markdown files available to edit.")
+            st.write("Select a file from the sidebar to edit.")
 
-    # File manager in sidebar
     groups, sorted_prefixes = load_files_for_sidebar()
     display_file_manager_sidebar(groups, sorted_prefixes)
 
-    # If user clicked "view group"
     if st.session_state.viewing_prefix and st.session_state.viewing_prefix in groups:
         st.write("---")
         st.write(f"**Viewing Group:** {st.session_state.viewing_prefix}")
@@ -536,7 +754,7 @@ def main():
             ext = os.path.splitext(fname)[1].lower().strip('.')
             st.write(f"### {fname}")
             if ext == "md":
-                content = open(f, 'r', encoding='utf-8').read()
+                content = open(f,'r',encoding='utf-8').read()
                 st.markdown(content)
             elif ext == "mp3":
                 st.audio(f)
@@ -547,120 +765,7 @@ def main():
 
     if st.session_state.should_rerun:
         st.session_state.should_rerun = False
-        st.experimental_rerun()
-
-def parse_arxiv_papers(ref_text: str):
-    """
-    Splits the references into paper-level chunks.
-    Each paper starts with a number followed by a parenthesis, e.g., "1) [Title (Year)] Summary..."
-    Returns a list of dictionaries with 'title', 'summary', and 'year'.
-    Limits to 20 papers.
-    """
-    # Split based on patterns like "1) ", "2) ", etc.
-    chunks = re.split(r'\n?\d+\)\s+', ref_text)
-    # Remove any empty strings resulting from split
-    chunks = [chunk.strip() for chunk in chunks if chunk.strip()]
-    papers = []
-    for chunk in chunks[:20]:
-        # Extract title within brackets if present
-        title_match = re.search(r'\[([^\]]+)\]', chunk)
-        title = title_match.group(1).strip() if title_match else "No Title"
-        
-        # Extract year (assuming it's a 4-digit number within the title or summary)
-        year_match = re.search(r'\b(20\d{2})\b', chunk)
-        year = int(year_match.group(1)) if year_match else None
-        
-        # The entire chunk is considered the summary
-        summary = chunk
-        
-        papers.append({
-            'title': title,
-            'summary': summary,
-            'year': year
-        })
-    return papers
-
-def perform_ai_lookup(q):
-    """
-    Performs the Arxiv search and handles the processing of results.
-    Generates audio files for each paper (if year is 2023 or 2024).
-    """
-    st.write(f"## Query: {q}")
-
-    # 1) Query the HF RAG pipeline
-    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    refs = client.predict(q, 20, "Semantic Search", "mistralai/Mixtral-8x7B-Instruct-v0.1", api_name="/update_with_rag_md")[0]
-    r2 = client.predict(q, "mistralai/Mixtral-8x7B-Instruct-v0.1", True, api_name="/ask_llm")
-
-    # 2) Combine for final text output
-    result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"
-    st.markdown(result)
-
-    # 3) Parse references into papers
-    papers = parse_arxiv_papers(refs)
-
-    # 4) Display each paper and generate audio if applicable
-    st.write("## Individual Papers (Up to 20)")
-    for idx, paper in enumerate(papers):
-        year_str = paper["year"] if paper["year"] else "Unknown Year"
-        st.markdown(f"**Paper #{idx+1}: {paper['title']}**  \n*Year:* {year_str}")
-        st.markdown(f"*Summary:* {paper['summary']}")
-        st.write("---")
-
-        # Generate TTS if year is 2023 or 2024
-        if paper["year"] in [2023, 2024]:
-            # Combine title and summary for TTS
-            tts_text = f"Title: {paper['title']}. Summary: {paper['summary']}"
-            # Generate a specialized filename
-            mp3_filename = generate_audio_filename(q, paper['title'], paper['summary'])
-            # Generate audio using Edge TTS
-            temp_mp3 = speak_with_edge_tts(tts_text, out_fn=mp3_filename)
-            if temp_mp3 and os.path.exists(mp3_filename):
-                # Embed the audio player with auto-play and download link
-                auto_play_audio(mp3_filename)
-
-    # Optionally save the full transcript
-    st.write("### Transcript")
-    st.markdown(result)
-    create_file(q, result, "md")
-
-def process_with_gpt(text):
-    """Process text with GPT-4"""
-    if not text:
-        return
-    st.session_state.messages.append({"role":"user","content":text})
-    with st.chat_message("user"):
-        st.markdown(text)
-    with st.chat_message("assistant"):
-        c = openai_client.ChatCompletion.create(
-            model=st.session_state["openai_model"],
-            messages=st.session_state.messages,
-            stream=False
-        )
-        ans = c.choices[0].message.content
-        st.write("GPT-4: " + ans)
-        create_file(text, ans, "md")
-        st.session_state.messages.append({"role":"assistant","content":ans})
-    return ans
-
-def process_with_claude(text):
-    """Process text with Claude"""
-    if not text:
-        return
-    with st.chat_message("user"):
-        st.markdown(text)
-    with st.chat_message("assistant"):
-        r = claude_client.completions.create(
-            prompt=text,
-            model="claude-3",
-            max_tokens=1000
-        )
-        ans = r['completion']
-        st.write("Claude-3.5: " + ans)
-        create_file(text, ans, "md")
-        st.session_state.chat_history.append({"user":text,"claude":ans})
-    return ans
+        st.rerun()
 
-# Run the app
-if __name__ == "__main__":
+if __name__=="__main__":
     main()