Create backup13.app.py

backup13.app.py

@@ -0,0 +1,463 @@
+import streamlit as st
+import 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
+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
+import extra_streamlit_components as stx
+from streamlit.runtime.scriptrunner import get_script_run_ctx
+import asyncio
+import edge_tts
+
+# -------------------- Configuration --------------------
+st.set_page_config(
+    page_title="🚲CCCG🏆 Code Competition Claude vs GPT",
+    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': "🚲CCCG🏆 Code Competition Claude vs GPT"
+    }
+)
+load_dotenv()
+
+USER_NAMES = [
+    "Aria", "Guy", "Sonia", "Tony", "Jenny", "Davis", "Libby", "Clara", "Liam", "Natasha", "William"
+]
+
+ENGLISH_VOICES = [
+    "en-US-AriaNeural", "en-US-GuyNeural", "en-GB-SoniaNeural", "en-GB-TonyNeural",
+    "en-US-JennyNeural", "en-US-DavisNeural", "en-GB-LibbyNeural", "en-CA-ClaraNeural",
+    "en-CA-LiamNeural", "en-AU-NatashaNeural", "en-AU-WilliamNeural"
+]
+
+USER_VOICES = dict(zip(USER_NAMES, ENGLISH_VOICES))
+
+if 'user_name' not in st.session_state:
+    st.session_state['user_name'] = USER_NAMES[0]
+if 'old_val' not in st.session_state:
+    st.session_state['old_val'] = None
+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
+
+FILE_EMOJIS = {
+    "md": "📝",
+    "mp3": "🎵",
+}
+
+def get_high_info_terms(text: str) -> list:
+    # Expanded stop words
+    stop_words = set([
+        'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for', 'of', 'with',
+        'by', 'from', 'up', 'about', 'into', 'over', 'after', 'is', 'are', 'was', 'were',
+        'be', 'been', 'being', 'have', 'has', 'had', 'do', 'does', 'did', 'will', 'would',
+        'should', 'could', 'might', 'must', 'shall', 'can', 'may', 'this', 'that', 'these',
+        'those', 'i', 'you', 'he', 'she', 'it', 'we', 'they', 'what', 'which', 'who',
+        'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most',
+        'other', 'some', 'such', 'than', 'too', 'very', 'just', 'there', 'as', 'if', 'while'
+    ])
+
+    # Key phrases tailored to your interests
+    key_phrases = [
+        'artificial intelligence', 'machine learning', 'deep learning', 'neural networks',
+        'natural language processing', 'healthcare systems', 'clinical medicine',
+        'genomics', 'biological systems', 'cognitive science', 'data visualization',
+        'wellness technology', 'robotics', 'medical imaging', 'semantic understanding',
+        'transformers', 'large language models', 'empirical studies', 'scientific research',
+        'quantum mechanics', 'biomedical engineering', 'computational biology'
+    ]
+
+    # Preserve key phrases and remove them from the text
+    preserved_phrases = []
+    lower_text = text.lower()
+    for phrase in key_phrases:
+        if phrase in lower_text:
+            preserved_phrases.append(phrase)
+            text = text.replace(phrase, '')
+            break  # Stop after the first matching key phrase
+
+    # Extract words and filter high-info terms
+    words = re.findall(r'\b\w+(?:-\w+)*\b', text)
+    high_info_words = [
+        word.lower() for word in words
+        if len(word) > 3
+        and word.lower() not in stop_words
+        and not word.isdigit()
+        and any(c.isalpha() for c in word)
+    ]
+
+    # Combine preserved phrases and filtered words, ensuring uniqueness
+    unique_terms = []
+    seen = set()
+    for term in preserved_phrases + high_info_words:
+        if term not in seen:
+            seen.add(term)
+            unique_terms.append(term)
+
+    # Return only the top 5 terms
+    return unique_terms[:5]
+
+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','from','just','very','then','been','only','also','about'])
+    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"):
+    # Adjust timezone to Central Time
+    central_tz = pytz.timezone('America/Chicago')
+    central_time = datetime.now(central_tz)
+    
+    # Format the prefix to include the required format
+    prefix = central_time.strftime("%m-%d-%y_%I-%M-%p_")  # e.g., 12-20-24_11-34-AM_
+
+    combined = (prompt + " " + response).strip()
+    info_terms = get_high_info_terms(combined)
+
+    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]
+
+    filename = f"{prefix}{full_name}.{file_type}"
+    return filename
+
+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):
+    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 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):
+    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")
+    try:
+        await communicate.save(out_fn)
+    except edge_tts.exceptions.NoAudioReceived:
+        st.error("No audio was received from TTS service.")
+        return None
+    return out_fn
+
+def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0):
+    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch))
+
+def play_and_download_audio(file_path):
+    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 load_files_for_sidebar():
+    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']
+    all_files = md_files + mp3_files
+
+    groups = defaultdict(list)
+    for f in all_files:
+        fname = os.path.basename(f)
+        prefix = fname[:17]
+        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)
+    return groups, sorted_prefixes
+
+def extract_keywords_from_md(files):
+    text = ""
+    for f in files:
+        if f.endswith(".md"):
+            c = open(f,'r',encoding='utf-8').read()
+            text += " " + c
+    return get_high_info_terms(text)
+
+def display_file_manager_sidebar(groups, sorted_prefixes):
+    st.sidebar.title("🎵 Audio & Docs Manager")
+
+    all_md = []
+    all_mp3 = []
+    for prefix in groups:
+        for f in groups[prefix]:
+            if f.endswith(".md"):
+                all_md.append(f)
+            elif f.endswith(".mp3"):
+                all_mp3.append(f)
+
+    top_bar = st.sidebar.columns(3)
+    with top_bar[0]:
+        if st.button("🗑 DelAllMD"):
+            for f in all_md:
+                os.remove(f)
+            st.session_state.should_rerun = True
+    with top_bar[1]:
+        if st.button("🗑 DelAllMP3"):
+            for f in all_mp3:
+                os.remove(f)
+            st.session_state.should_rerun = True
+    with top_bar[2]:
+        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)
+
+    for prefix in sorted_prefixes:
+        files = groups[prefix]
+        kw = extract_keywords_from_md(files)
+        keywords_str = " ".join(kw) if kw else "No Keywords"
+        with st.sidebar.expander(f"{prefix} Files ({len(files)}) - KW: {keywords_str}", expanded=True):
+            c1,c2 = st.columns(2)
+            with c1:
+                if st.button("👀ViewGrp", key="view_group_"+prefix):
+                    st.session_state.viewing_prefix = prefix
+            with c2:
+                if st.button("🗑DelGrp", key="del_group_"+prefix):
+                    for f in files:
+                        os.remove(f)
+                    st.success(f"Deleted group {prefix}!")
+                    st.session_state.should_rerun = True
+
+            for f in files:
+                fname = os.path.basename(f)
+                ctime = datetime.fromtimestamp(os.path.getmtime(f)).strftime("%Y-%m-%d %H:%M:%S")
+                st.write(f"**{fname}** - {ctime}")
+
+def create_zip_of_files(md_files, mp3_files):
+    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
+    all_files = md_files + mp3_files
+    if not all_files:
+        return None
+
+    all_content = []
+    for f in all_files:
+        if f.endswith('.md'):
+            with open(f,'r',encoding='utf-8') as file:
+                all_content.append(file.read())
+        elif f.endswith('.mp3'):
+            all_content.append(os.path.basename(f))
+
+    combined_content = " ".join(all_content)
+    info_terms = get_high_info_terms(combined_content)
+
+    timestamp = datetime.now().strftime("%y%m_%H%M")
+    name_text = '_'.join(term.replace(' ', '-') for term in info_terms[:3])
+    zip_name = f"{timestamp}_{name_text}.zip"
+
+    with zipfile.ZipFile(zip_name,'w') as z:
+        for f in all_files:
+            z.write(f)
+
+    return zip_name
+
+def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True, full_audio=False):
+    """Perform Arxiv search (via your RAG pattern) and generate audio summaries."""
+    start = time.time()
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    # The next lines call your RAG pipeline
+    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}"
+
+    # Audio outputs
+    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)
+        if audio_file_full:
+            st.write("### 📚 Full Audio")
+            play_and_download_audio(audio_file_full)
+
+    if vocal_summary:
+        main_text = clean_for_speech(r2)
+        if main_text.strip():
+            audio_file_main = speak_with_edge_tts(main_text)
+            if audio_file_main:
+                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)
+        if summaries_text.strip():
+            audio_file_refs = speak_with_edge_tts(summaries_text)
+            if audio_file_refs:
+                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)
+            if titles_text.strip():
+                audio_file_titles = speak_with_edge_tts(titles_text)
+                if audio_file_titles:
+                    st.write("### 🔖 Titles")
+                    play_and_download_audio(audio_file_titles)
+
+    # show text last after playback interfaces.   For the big one lets add a feature later that breaks into their own.
+    st.markdown(result)
+            
+    elapsed = time.time()-start
+    st.write(f"**Total Elapsed:** {elapsed:.2f} s")
+
+    create_file(q, result, "md")
+
+    return result
+
+def main():
+    st.session_state['user_name'] = st.selectbox("Current User:", USER_NAMES, index=0)
+
+    # Display saved files in sidebar
+    groups, sorted_prefixes = load_files_for_sidebar()
+    display_file_manager_sidebar(groups, sorted_prefixes)
+    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}")
+        for f in groups[st.session_state.viewing_prefix]:
+            fname = os.path.basename(f)
+            ext = os.path.splitext(fname)[1].lower().strip('.')
+            st.write(f"### {fname}")
+            if ext == "md":
+                content = open(f,'r',encoding='utf-8').read()
+                st.markdown(content)
+            elif ext == "mp3":
+                st.audio(f)
+            else:
+                st.markdown(get_download_link(f), unsafe_allow_html=True)
+        if st.button("❌ Close"):
+            st.session_state.viewing_prefix = None
+
+    if st.button("🗑️ Clear All History in Sidebar"):
+        md_files = glob.glob("*.md")
+        mp3_files = glob.glob("*.mp3")
+        for f in md_files+mp3_files:
+            os.remove(f)
+        st.success("All history cleared!")
+        st.rerun()
+
+    st.title("🎙️ ArXiv Voice Search")
+
+    # Voice component
+    mycomponent = components.declare_component("mycomponent", path="mycomponent")
+    voice_val = mycomponent(my_input_value="Start speaking...")
+
+    tabs = st.tabs(["🎤 Voice Chat", "💾 History", "⚙️ Settings"])
+
+    with tabs[0]:
+        st.subheader("🎤 Voice Chat")
+        if voice_val:
+            voice_text = voice_val.strip()
+            input_changed = (voice_text != st.session_state.get('old_val'))
+            if input_changed and voice_text:
+                # Save user input
+                create_file(st.session_state['user_name'], voice_text, "md")
+
+                # Perform ArXiv search automatically
+                with st.spinner("Searching ArXiv..."):
+                    # Always do vocal_summary = True, extended_refs=False, titles_summary=True, full_audio=False
+                    result = perform_ai_lookup(voice_text, vocal_summary=True, extended_refs=False, titles_summary=True, full_audio=False)
+
+                # Update old_val
+                st.session_state['old_val'] = voice_text
+                # Clear the text by rerunning
+                #st.rerun()
+
+        st.write("Speak a query to run an ArXiv search and hear the results.")
+
+    with tabs[1]:
+        st.subheader("💾 History")
+        # Show all MD files and allow reading them aloud
+        md_files = sorted(glob.glob("*.md"), key=os.path.getmtime, reverse=True)
+        for i, fpath in enumerate(md_files, start=1):
+            fname = os.path.basename(fpath)
+            with open(fpath,'r',encoding='utf-8') as ff:
+                content = ff.read()
+            with st.expander(fname, expanded=False):
+                st.write(content)
+                if st.button(f"🔊 Read Aloud {fname}", key=f"read_{i}_{fname}"):
+                    voice = USER_VOICES.get(st.session_state['user_name'], "en-US-AriaNeural")
+                    audio_file = speak_with_edge_tts(content, voice=voice)
+                    if audio_file:
+                        play_and_download_audio(audio_file)
+
+        if st.button("📜 Read Entire History"):
+            all_content = []
+            for fpath in sorted(md_files, key=os.path.getmtime):
+                with open(fpath,'r',encoding='utf-8') as ff:
+                    c = ff.read().strip()
+                    if c:
+                        all_content.append((fpath, c))
+            mp3_files = []
+            for (fpath, text) in all_content:
+                voice = USER_VOICES.get(st.session_state['user_name'], "en-US-AriaNeural")
+                audio_file = speak_with_edge_tts(text, voice=voice)
+                if audio_file:
+                    mp3_files.append(audio_file)
+                    st.write(f"**{os.path.basename(fpath)}:**")
+                    play_and_download_audio(audio_file)
+
+            if mp3_files:
+                combined_file = f"full_conversation_{datetime.now().strftime('%Y%m%d_%H%M%S')}.mp3"
+                with open(combined_file, 'wb') as outfile:
+                    for f in mp3_files:
+                        with open(f, 'rb') as infile:
+                            outfile.write(infile.read())
+                st.write("**Full Conversation Audio:**")
+                play_and_download_audio(combined_file)
+
+    with tabs[2]:
+        st.subheader("⚙️ Settings")
+        st.write("Currently no additional settings.")
+
+    if st.session_state.should_rerun:
+        st.session_state.should_rerun = False
+        st.rerun()
+
+if __name__=="__main__":
+    main()