Update app.py

app.py

@@ -20,89 +20,66 @@ from streamlit.runtime.scriptrunner import get_script_run_ctx
 import asyncio
 import edge_tts
 
-# Available English voices
-ENGLISH_VOICES = [
-    "en-US-AriaNeural",      # Female, conversational
-    "en-US-JennyNeural",     # Female, customer service
-    "en-US-GuyNeural",       # Male, newscast
-    "en-US-RogerNeural",     # Male, calm
-    "en-GB-SoniaNeural",     # British female
-    "en-GB-RyanNeural",      # British male
-    "en-AU-NatashaNeural",   # Australian female
-    "en-AU-WilliamNeural",   # Australian male
-    "en-CA-ClaraNeural",     # Canadian female
-    "en-CA-LiamNeural",      # Canadian male
-    "en-IE-EmilyNeural",     # Irish female
-    "en-IE-ConnorNeural",    # Irish male
-    "en-IN-NeerjaNeural",    # Indian female
-    "en-IN-PrabhatNeural",   # Indian male
-]
-
-# Core Configuration & Setup
+# 🎯 1. Core Configuration & Setup
 st.set_page_config(
-    page_title="ARIA Research Assistant",
-    page_icon="🔬",
+    page_title="🚲BikeAI🏆 Claude/GPT Research",
+    page_icon="🚲🏆",
     layout="wide",
     initial_sidebar_state="auto",
     menu_items={
         'Get Help': 'https://huggingface.co/awacke1',
         'Report a bug': 'https://huggingface.co/spaces/awacke1',
-        'About': "ARIA: Academic Research Interactive Assistant"
+        'About': "🚲BikeAI🏆 Claude/GPT Research AI"
     }
 )
 load_dotenv()
 
-# API Setup
-openai_api_key = os.getenv('OPENAI_API_KEY', st.secrets.get('OPENAI_API_KEY', ''))
-anthropic_key = os.getenv('ANTHROPIC_API_KEY_3', st.secrets.get('ANTHROPIC_API_KEY', ''))
+# 🔑 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:
+    anthropic_key = st.secrets["ANTHROPIC_API_KEY"]
 
-openai_client = OpenAI(api_key=openai_api_key)
+openai.api_key = openai_api_key
 claude_client = anthropic.Anthropic(api_key=anthropic_key)
+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')
 
-# Session State Management
+# 📝 3. Session State Management
 if 'transcript_history' not in st.session_state:
     st.session_state['transcript_history'] = []
 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-vision-preview"
+    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 'current_audio' not in st.session_state:
-    st.session_state['current_audio'] = None
-if 'autoplay_audio' not in st.session_state:
-    st.session_state['autoplay_audio'] = True
+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:
     st.session_state['should_rerun'] = False
-if 'autorun' not in st.session_state:
-    st.session_state.autorun = True
-if 'run_option' not in st.session_state:
-    st.session_state.run_option = "Arxiv"
-if 'last_processed_text' not in st.session_state:
-    st.session_state.last_processed_text = ""
-
-# Custom CSS
+if 'old_val' not in st.session_state:
+    st.session_state['old_val'] = None
+
+# 🎨 4. Custom CSS
 st.markdown("""
 <style>
-    .main {
-        background: linear-gradient(135deg, #1a1a1a, #2d2d2d);
-        color: #ffffff;
-    }
-    .stMarkdown {
-        font-family: 'Helvetica Neue', sans-serif;
-    }
+    .main { background: linear-gradient(to right, #1a1a1a, #2d2d2d); color: #fff; }
+    .stMarkdown { font-family: 'Helvetica Neue', sans-serif; }
     .stButton>button {
-        background-color: #4CAF50;
-        color: white;
-        padding: 0.5rem 1rem;
-        border-radius: 5px;
-        border: none;
-        transition: background-color 0.3s;
-    }
-    .stButton>button:hover {
-        background-color: #45a049;
+        margin-right: 0.5rem;
     }
     .audio-player {
         margin: 1rem 0;
@@ -111,166 +88,267 @@ st.markdown("""
         background: #f5f5f5;
         box-shadow: 0 2px 4px rgba(0,0,0,0.1);
     }
-    .voice-container {
-        padding: 1rem;
-        background: white;
-        border-radius: 10px;
-        margin: 1rem 0;
+</style>
+""", unsafe_allow_html=True)
+
+FILE_EMOJIS = {
+    "md": "📝",
+    "mp3": "🎵",
+}
+
+def clean_for_speech(text: str) -> str:
+    """Clean text for speech synthesis"""
+    text = text.replace("\n", " ")
+    text = text.replace("</s>", " ")
+    text = text.replace("#", "")
+    text = re.sub(r"\(https?:\/\/[^\)]+\)", "", text)
+    text = re.sub(r"\s+", " ", text).strip()
+    return text
+
+@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):
+    """Wrapper for edge TTS generation"""
+    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch))
+
+def play_and_download_audio(file_path):
+    """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 save_full_transcript(query, text):
+    """Save full transcript of Arxiv results as a file."""
+    create_file(query, text, "md")
+
+def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True, full_audio=False):
+    """Perform Arxiv search and generate audio summaries"""
+    start = time.time()
+    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")
+
+    result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"
+
+    st.markdown(result)
+
+    # Generate full audio version 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)
+        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)
+        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)
+        st.write("### 📜 Long Refs")
+        play_and_download_audio(audio_file_refs)
+
+    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)
+            st.write("### 🔖 Titles")
+            play_and_download_audio(audio_file_titles)
+
+    elapsed = time.time()-start
+    st.write(f"**Total Elapsed:** {elapsed:.2f} s")
+
+    # Create file with result
+    create_file(q, result, "md")
+
+    return result
+
+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.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-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: return
+    with st.chat_message("user"):
+        st.markdown(text)
+    with st.chat_message("assistant"):
+        r = claude_client.messages.create(
+            model="claude-3-sonnet-20240229",
+            max_tokens=1000,
+            messages=[{"role":"user","content":text}]
+        )
+        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
+
+def generate_filename(prompt, response, file_type="md"):
+    """Generate filename with timestamp and cleaned text."""
+    timestamp = datetime.now().strftime("%y%m_%H%M")
+    safe_text = re.sub(r'[^\w\s-]', '', prompt[:50])
+    return f"{timestamp}_{safe_text}.{file_type}"
+
+def create_file(prompt, response, file_type="md"):
+    """Create file with content."""
+    filename = generate_filename(prompt.strip(), response.strip(), file_type)
+    with open(filename, 'w', encoding='utf-8') as f:
+        f.write(prompt + "\n\n" + response)
+    return filename
+
+def get_download_link(file):
+    """Generate download link for file"""
+    with open(file, "rb") as f:
+        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>'
+
+import streamlit as st
+import anthropic, openai, base64, cv2, glob, json, math, os, pytz, random, re, requests, 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 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
+st.set_page_config(
+    page_title="🚲BikeAI🏆 Claude/GPT Research",
+    page_icon="🚲🏆",
+    layout="wide",
+    initial_sidebar_state="auto",
+    menu_items={
+        'Get Help': 'https://huggingface.co/awacke1',
+        'Report a bug': 'https://huggingface.co/spaces/awacke1',
+        'About': "🚲BikeAI🏆 Claude/GPT Research AI"
     }
-    .text-display {
-        margin: 1rem 0;
-        padding: 1rem;
-        background: #f9f9f9;
-        border-radius: 5px;
-        font-size: 1.1em;
+)
+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:
+    anthropic_key = st.secrets["ANTHROPIC_API_KEY"]
+
+openai.api_key = openai_api_key
+claude_client = anthropic.Anthropic(api_key=anthropic_key)
+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:
+    st.session_state['transcript_history'] = []
+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-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:
+    st.session_state['should_rerun'] = False
+if 'old_val' not in st.session_state:
+    st.session_state['old_val'] = None
+
+# 🎨 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;
     }
-    .model-selector {
+    .audio-player {
         margin: 1rem 0;
-        padding: 0.5rem;
-        background: #ffffff;
-        border-radius: 5px;
-    }
-    .response-container {
-        margin-top: 2rem;
         padding: 1rem;
-        background: rgba(255, 255, 255, 0.05);
         border-radius: 10px;
+        background: #f5f5f5;
+        box-shadow: 0 2px 4px rgba(0,0,0,0.1);
     }
 </style>
 """, unsafe_allow_html=True)
 
-def create_voice_component():
-    """Create auto-searching voice recognition component"""
-    return components.html(
-        """
-        <div style="padding: 20px; border-radius: 10px; background: #f0f2f6;">
-            <div id="status" style="margin-bottom: 10px; color: #666;">Starting voice recognition...</div>
-            <div id="interim" style="color: #666; min-height: 24px;"></div>
-            <div id="output" style="margin-top: 10px; padding: 10px; min-height: 100px; 
-                                  background: white; border-radius: 5px; white-space: pre-wrap;"></div>
-            <script>
-                if ('webkitSpeechRecognition' in window) {
-                    const recognition = new webkitSpeechRecognition();
-                    recognition.continuous = true;
-                    recognition.interimResults = true;
-                    
-                    const status = document.getElementById('status');
-                    const interim = document.getElementById('interim');
-                    const output = document.getElementById('output');
-                    let fullTranscript = '';
-                    let lastPauseTime = Date.now();
-                    let pauseThreshold = 1500;
-                    
-                    window.addEventListener('load', () => {
-                        setTimeout(() => {
-                            try {
-                                recognition.start();
-                                status.textContent = 'Listening...';
-                            } catch (e) {
-                                console.error('Start error:', e);
-                                status.textContent = 'Error starting recognition';
-                            }
-                        }, 1000);
-                    });
-                    
-                    recognition.onresult = (event) => {
-                        let interimTranscript = '';
-                        let finalTranscript = '';
-                        
-                        for (let i = event.resultIndex; i < event.results.length; i++) {
-                            const transcript = event.results[i][0].transcript;
-                            if (event.results[i].isFinal) {
-                                finalTranscript += transcript + ' ';
-                                lastPauseTime = Date.now();
-                            } else {
-                                interimTranscript += transcript;
-                            }
-                        }
-                        
-                        if (finalTranscript) {
-                            fullTranscript += finalTranscript;
-                            interim.textContent = '';
-                            output.textContent = fullTranscript;
-                            
-                            window.parent.postMessage({
-                                type: 'streamlit:setComponentValue',
-                                value: {
-                                    text: fullTranscript,
-                                    trigger: 'speech'
-                                },
-                                dataType: 'json',
-                            }, '*');
-                        } else if (interimTranscript) {
-                            interim.textContent = '... ' + interimTranscript;
-                        }
-                        
-                        output.scrollTop = output.scrollHeight;
-                    };
-                    
-                    setInterval(() => {
-                        if (fullTranscript && Date.now() - lastPauseTime > pauseThreshold) {
-                            if (output.dataset.lastProcessed !== fullTranscript) {
-                                output.dataset.lastProcessed = fullTranscript;
-                                window.parent.postMessage({
-                                    type: 'streamlit:setComponentValue',
-                                    value: {
-                                        text: fullTranscript,
-                                        trigger: 'pause'
-                                    },
-                                    dataType: 'json',
-                                }, '*');
-                            }
-                        }
-                    }, 500);
-                    
-                    recognition.onend = () => {
-                        try {
-                            recognition.start();
-                            status.textContent = 'Listening...';
-                        } catch (e) {
-                            console.error('Restart error:', e);
-                            status.textContent = 'Recognition stopped. Refresh to restart.';
-                        }
-                    };
-                    
-                    recognition.onerror = (event) => {
-                        console.error('Recognition error:', event.error);
-                        status.textContent = 'Error: ' + event.error;
-                    };
-                } else {
-                    document.getElementById('status').textContent = 'Speech recognition not supported in this browser';
-                }
-            </script>
-        </div>
-        """,
-        height=200
-    )
-
-def get_audio_autoplay_html(audio_path):
-    """Create HTML for autoplaying audio with controls and download"""
-    try:
-        with open(audio_path, "rb") as audio_file:
-            audio_bytes = audio_file.read()
-            audio_b64 = base64.b64encode(audio_bytes).decode()
-            return f'''
-                <div class="audio-player">
-                    <audio controls autoplay style="width: 100%;">
-                        <source src="data:audio/mpeg;base64,{audio_b64}" type="audio/mpeg">
-                        Your browser does not support the audio element.
-                    </audio>
-                    <div style="margin-top: 5px;">
-                        <a href="data:audio/mpeg;base64,{audio_b64}" 
-                           download="{os.path.basename(audio_path)}"
-                           style="text-decoration: none; color: #4CAF50;">
-                           ⬇️ Download Audio
-                        </a>
-                    </div>
-                </div>
-            '''
-    except Exception as e:
-        return f"Error loading audio: {str(e)}"
-
-# Audio Processing Functions
+FILE_EMOJIS = {
+    "md": "📝",
+    "mp3": "🎵",
+}
+
 def clean_for_speech(text: str) -> str:
     """Clean text for speech synthesis"""
     text = text.replace("\n", " ")
@@ -280,151 +358,176 @@ def clean_for_speech(text: str) -> str:
     text = re.sub(r"\s+", " ", text).strip()
     return text
 
-async def generate_audio(text, voice="en-US-AriaNeural", rate="+0%", pitch="+0Hz"):
-    """Generate audio using Edge TTS with automatic playback"""
+@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
-    
-    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-    output_file = f"response_{timestamp}.mp3"
-    
-    communicate = edge_tts.Communicate(text, voice, rate=rate, pitch=pitch)
-    await communicate.save(output_file)
-    
-    return output_file
-
-def render_audio_result(audio_file, title="Generated Audio"):
-    """Render audio result with autoplay in Streamlit"""
-    if audio_file and os.path.exists(audio_file):
-        st.markdown(f"### {title}")
-        st.markdown(get_audio_autoplay_html(audio_file), unsafe_allow_html=True)
-
-async def process_voice_search(query, voice="en-US-AriaNeural"):
-    """Process voice search with automatic audio using selected voice"""
-    response, refs = perform_arxiv_search(query)
-    
-    audio_file = await generate_audio(response, voice=voice)
-    st.session_state.current_audio = audio_file
-    
-    return response, audio_file
-
-# Arxiv Search Functions
-def perform_arxiv_search(query):
-    """Enhanced Arxiv search with summary"""
-    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    
-    refs = client.predict(
-        query, 20, "Semantic Search",
-        "mistralai/Mixtral-8x7B-Instruct-v0.1",
-        api_name="/update_with_rag_md"
-    )[0]
-    
-    summary = client.predict(
-        query,
-        "mistralai/Mixtral-8x7B-Instruct-v0.1",
-        True,
-        api_name="/ask_llm"
-    )
-    
-    response = f"### Search Results for: {query}\n\n{summary}\n\n### References\n\n{refs}"
-    return response, refs
-
-def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True, 
-                     full_audio=False, voice="en-US-AriaNeural"):
-    """Full Arxiv search with audio summaries"""
+    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):
+    """Wrapper for edge TTS generation"""
+    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch))
+
+def play_and_download_audio(file_path):
+    """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 save_full_transcript(query, text):
+    """Save full transcript of Arxiv results as a file."""
+    create_file(query, text, "md")
+
+def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True, full_audio=False):
+    """Perform Arxiv search and generate audio summaries"""
     start = time.time()
-    response, refs = perform_arxiv_search(q)
-    
-    st.markdown(response)
-    
-    # Generate audio responses
+    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")
+
+    result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"
+
+    st.markdown(result)
+
+    # Generate full audio version if requested
     if full_audio:
-        audio_file = asyncio.run(generate_audio(response, voice=voice))
-        if audio_file:
-            render_audio_result(audio_file, "Complete Response")
-    
+        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)
+        st.write("### 📚 Full Audio")
+        play_and_download_audio(audio_file_full)
+
     if vocal_summary:
-        summary_audio = asyncio.run(generate_audio(
-            f"Summary of results for query: {q}",
-            voice=voice
-        ))
-        if summary_audio:
-            render_audio_result(summary_audio, "Summary")
-    
-    elapsed = time.time() - start
+        main_text = clean_for_speech(r2)
+        audio_file_main = speak_with_edge_tts(main_text)
+        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)
+        st.write("### 📜 Long Refs")
+        play_and_download_audio(audio_file_refs)
+
+    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)
+            st.write("### 🔖 Titles")
+            play_and_download_audio(audio_file_titles)
+
+    elapsed = time.time()-start
     st.write(f"**Total Elapsed:** {elapsed:.2f} s")
-    
-    return response
-def render_search_interface():
-    """Main search interface with voice recognition and model selection"""
-    st.header("🔍 Voice Search & Research")
 
-    # Get voice component value and set up model selection
+    # Create file with result
+    create_file(q, result, "md")
+
+    return result
+
+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.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-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: return
+    with st.chat_message("user"):
+        st.markdown(text)
+    with st.chat_message("assistant"):
+        r = claude_client.messages.create(
+            model="claude-3-sonnet-20240229",
+            max_tokens=1000,
+            messages=[{"role":"user","content":text}]
+        )
+        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
+
+def generate_filename(prompt, response, file_type="md"):
+    """Generate filename with timestamp and cleaned text."""
+    timestamp = datetime.now().strftime("%y%m_%H%M")
+    safe_text = re.sub(r'[^\w\s-]', '', prompt[:50])
+    return f"{timestamp}_{safe_text}.{file_type}"
+
+def create_file(prompt, response, file_type="md"):
+    """Create file with content."""
+    filename = generate_filename(prompt.strip(), response.strip(), file_type)
+    with open(filename, 'w', encoding='utf-8') as f:
+        f.write(prompt + "\n\n" + response)
+    return filename
+
+def get_download_link(file):
+    """Generate download link for file"""
+    with open(file, "rb") as f:
+        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>'
+
+def main():
+    st.sidebar.markdown("### 🚲BikeAI🏆 Multi-Agent Research")
+    tab_main = st.radio("Action:",["🎤 Voice","📸 Media","🔍 ArXiv","📝 Editor"],horizontal=True)
+
     mycomponent = components.declare_component("mycomponent", path="mycomponent")
     val = mycomponent(my_input_value="Hello")
 
-    # Show input in edit box if detected
+    # Show input in 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.get('old_val', None))
-
-        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)
-            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)
-                else:
-                    if run_option == "GPT-4o":
-                        process_with_gpt(edited_input)
-                    elif run_option == "Claude-3.5":
-                        process_with_claude(edited_input)
-
-                        
-def main():
-    st.sidebar.markdown("### 🚲BikeAI🏆 Multi-Agent Research")
-    tab_main = st.radio("Action:", ["🎤 Voice", "📸 Media", "🔍 ArXiv", "📝 Editor"], horizontal=True)
-
-    if tab_main == "🎤 Voice":
-        render_search_interface()
-
-    elif tab_main == "🔍 ArXiv":
-        st.subheader("🔍 Query ArXiv")
-        q = st.text_input("🔍 Query:")
-
-        st.markdown("### 🎛 Options")
-        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_audio = st.checkbox("📚FullAudio", value=False,
+                                 help="Full audio of results")
         full_transcript = st.checkbox("🧾FullTranscript", value=False,
-                                    help="Generate a full transcript file")
+                                  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)
+                                   titles_summary=titles_summary, full_audio=full_audio)
             if full_transcript:
                 save_full_transcript(q, result)
 
@@ -432,14 +535,30 @@ def main():
         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)
+                                   titles_summary=titles_summary, full_audio=full_audio)
             if full_transcript:
                 save_full_transcript(q_new, result)
 
+    elif tab_main == "🎤 Voice":
+        st.subheader("🎤 Voice Input")
+        user_text = st.text_area("💬 Message:", height=100)
+        user_text = user_text.strip().replace('\n', ' ')
+        if st.button("📨 Send"):
+            process_with_gpt(user_text)
+        st.subheader("📜 Chat 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"])
+                st.write("**Claude:**", c["claude"])
+        with t2:
+            for m in st.session_state.messages:
+                with st.chat_message(m["role"]):
+                    st.markdown(m["content"])
+
     elif tab_main == "📸 Media":
         st.header("📸 Images & 🎥 Videos")
         tabs = st.tabs(["🖼 Images", "🎥 Video"])
-        
         with tabs[0]:
             imgs = glob.glob("*.png")+glob.glob("*.jpg")
             if imgs:
@@ -453,7 +572,6 @@ def main():
                             st.markdown(a)
             else:
                 st.write("No images found.")
-                
         with tabs[1]:
             vids = glob.glob("*.mp4")
             if vids:
@@ -501,4 +619,6 @@ def main():
     if st.session_state.should_rerun:
         st.session_state.should_rerun = False
         st.rerun()
-    
+
+if __name__ == "__main__":
+    main()