Update app.py

app.py

@@ -1,289 +1,4 @@
-import streamlit as st
-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, Counter
-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
-from streamlit_marquee import streamlit_marquee
-
-# 🎯 1. Core Configuration & Setup
-st.set_page_config(
-    page_title="🚲TalkingAIResearcher🏆",
-    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': "🚲TalkingAIResearcher🏆"
-    }
-)
-load_dotenv()
-
-# Add available English voices for Edge TTS
-EDGE_TTS_VOICES = [
-    "en-US-AriaNeural",
-    "en-US-GuyNeural",
-    "en-US-JennyNeural",
-    "en-GB-SoniaNeural",
-    "en-GB-RyanNeural",
-    "en-AU-NatashaNeural",
-    "en-AU-WilliamNeural",
-    "en-CA-ClaraNeural",
-    "en-CA-LiamNeural"
-]
-
-def get_central_time():
-    """Get current time in US Central timezone"""
-    central = pytz.timezone('US/Central')
-    return datetime.now(central)
-
-def format_timestamp_prefix():
-    """Generate timestamp prefix in format MM_dd_yy_hh_mm_AM/PM"""
-    ct = get_central_time()
-    return ct.strftime("%m_%d_%y_%I_%M_%p")
-
-# Initialize session state variables
-if 'tts_voice' not in st.session_state:
-    st.session_state['tts_voice'] = EDGE_TTS_VOICES[0]
-if 'audio_format' not in st.session_state:
-    st.session_state['audio_format'] = 'mp3'
-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
-if 'last_query' not in st.session_state:
-    st.session_state['last_query'] = ""
-if 'marquee_content' not in st.session_state:
-    st.session_state['marquee_content'] = "🚀 Welcome to TalkingAIResearcher | 🤖 Your Research Assistant"
-
-# 🔑 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')
-
-# Constants
-FILE_EMOJIS = {
-    "md": "📝",
-    "mp3": "🎵",
-    "wav": "🔊"
-}
-
-# Functions
-def get_high_info_terms(text: str, top_n=10) -> list:
-    stop_words = set(['the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for', 'of', 'with'])
-    words = re.findall(r'\b\w+(?:-\w+)*\b', text.lower())
-    bi_grams = [' '.join(pair) for pair in zip(words, words[1:])]
-    combined = words + bi_grams
-    filtered = [term for term in combined if term not in stop_words and len(term.split()) <= 2]
-    counter = Counter(filtered)
-    return [term for term, freq in counter.most_common(top_n)]
-
-def clean_text_for_filename(text: str) -> str:
-    text = text.lower()
-    text = re.sub(r'[^\w\s-]', '', text)
-    words = text.split()
-    stop_short = set(['the', 'and', 'for', 'with', 'this', 'that'])
-    filtered = [w for w in words if len(w) > 3 and w not in stop_short]
-    return '_'.join(filtered)[:200]
-
-def generate_filename(prompt, response, file_type="md"):
-    prefix = format_timestamp_prefix() + "_"
-    combined = (prompt + " " + response).strip()
-    info_terms = get_high_info_terms(combined, top_n=10)
-    snippet = (prompt[:100] + " " + response[:100]).strip()
-    snippet_cleaned = clean_text_for_filename(snippet)
-    name_parts = info_terms + [snippet_cleaned]
-    full_name = '_'.join(name_parts)
-    if len(full_name) > 150:
-        full_name = full_name[:150]
-    return f"{prefix}{full_name}.{file_type}"
-
-def create_file(prompt, response, file_type="md"):
-    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, file_type="zip"):
-    with open(file, "rb") as f:
-        b64 = base64.b64encode(f.read()).decode()
-    if file_type == "zip":
-        return f'<a href="data:application/zip;base64,{b64}" download="{os.path.basename(file)}">📂 Download {os.path.basename(file)}</a>'
-    elif file_type == "mp3":
-        return f'<a href="data:audio/mpeg;base64,{b64}" download="{os.path.basename(file)}">🎵 Download {os.path.basename(file)}</a>'
-    elif file_type == "wav":
-        return f'<a href="data:audio/wav;base64,{b64}" download="{os.path.basename(file)}">🔊 Download {os.path.basename(file)}</a>'
-    elif file_type == "md":
-        return f'<a href="data:text/markdown;base64,{b64}" download="{os.path.basename(file)}">📝 Download {os.path.basename(file)}</a>'
-    else:
-        return f'<a href="data:application/octet-stream;base64,{b64}" download="{os.path.basename(file)}">Download {os.path.basename(file)}</a>'
-
-def clean_for_speech(text: str) -> str:
-    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
-
-async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=0, file_format="mp3"):
-    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, file_type=file_format)
-    await communicate.save(out_fn)
-    return out_fn
-
-def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0, file_format="mp3"):
-    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch, file_format))
-
-def play_and_download_audio(file_path, file_type="mp3"):
-    if file_path and os.path.exists(file_path):
-        st.audio(file_path)
-        dl_link = get_download_link(file_path, file_type=file_type)
-        st.markdown(dl_link, unsafe_allow_html=True)
-
-def save_qa_with_audio(question, answer, voice=None):
-    """Save Q&A to markdown and generate audio"""
-    if not voice:
-        voice = st.session_state['tts_voice']
-    
-    combined_text = f"# Question\n{question}\n\n# Answer\n{answer}"
-    md_file = create_file(question, answer, "md")
-    
-    audio_text = f"Question: {question}\n\nAnswer: {answer}"
-    audio_file = speak_with_edge_tts(
-        audio_text,
-        voice=voice,
-        file_format=st.session_state['audio_format']
-    )
-    
-    return md_file, audio_file
-
-def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, 
-                     titles_summary=True, full_audio=False, marquee_settings=None):
-    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)
-
-    md_file, audio_file = save_qa_with_audio(q, result)
-    
-    st.subheader("📝 Main Response Audio")
-    play_and_download_audio(audio_file, st.session_state['audio_format'])
-
-    papers = parse_arxiv_refs(refs)
-    if papers:
-        create_paper_audio_files(papers, input_question=q)
-        if marquee_settings:
-            display_papers(papers, marquee_settings)
-        else:
-            display_papers(papers, get_marquee_settings())
-    else:
-        st.warning("No papers found in the response.")
-
-    elapsed = time.time()-start
-    st.write(f"**Total Elapsed:** {elapsed:.2f} s")
-    
-    return result
-
-def process_voice_input(text):
-    if not text:
-        return
-        
-    st.subheader("🔍 Search Results")
-    result = perform_ai_lookup(
-        text, 
-        vocal_summary=True,
-        extended_refs=False,
-        titles_summary=True,
-        full_audio=True,
-        marquee_settings=marquee_settings)
-    
-    md_file, audio_file = save_qa_with_audio(text, result)
-    
-    st.subheader("📝 Generated Files")
-    st.write(f"Markdown: {md_file}")
-    st.write(f"Audio: {audio_file}")
-    play_and_download_audio(audio_file, st.session_state['audio_format'])
-
-def load_files_for_sidebar():
-    md_files = glob.glob("*.md")
-    mp3_files = glob.glob("*.mp3")
-    wav_files = glob.glob("*.wav")
-    
-    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
-    all_files = md_files + mp3_files + wav_files
-
-    groups = defaultdict(list)
-    prefix_length = len("MM_dd_yy_hh_mm_AP")
-    
-    for f in all_files:
-        basename = os.path.basename(f)
-        if len(basename) >= prefix_length and '_' in basename:
-            group_name = basename[:prefix_length]
-            groups[group_name].append(f)
-        else:
-            groups['Other'].append(f)
-            
-    sorted_groups = sorted(groups.items(), 
-                         key=lambda x: x[0] if x[0] != 'Other' else '', 
-                         reverse=True)
-    return sorted_groups
+return sorted_groups
 
 def display_file_manager_sidebar(groups_sorted):
     st.sidebar.title("🎵 Audio & Docs Manager")
@@ -508,6 +223,7 @@ def display_papers(papers, marquee_settings):
                     if file_ext in ['mp3', 'wav']:
                         st.audio(paper['full_audio'])
 
+                        
 def main():
     marquee_settings = get_marquee_settings()
     
@@ -602,10 +318,9 @@ def main():
         user_text = user_text.strip().replace('\n', ' ')
 
         if st.button("📨 Send"):
-            process_voice_input(user_text)
+            process_voice_input(user_text, marquee_settings=marquee_settings)
             
-        st.subheader("📜 Chat History")
-        for c in st.session_state.chat_history:
+        st.subheader("📜 Chat History")for c in st.session_state.chat_history:
             st.write("**You:**", c["user"])
             st.write("**Response:**", c["claude"])