Update backup19-processInputButton-app.py

backup19-processInputButton-app.py

@@ -20,7 +20,7 @@ from streamlit.runtime.scriptrunner import get_script_run_ctx
 import asyncio
 import edge_tts
 
-# 🔧 Config & Setup
+# 🎯 1. Core Configuration & Setup
 st.set_page_config(
     page_title="🚲BikeAI🏆 Claude/GPT Research",
     page_icon="🚲🏆",
@@ -34,6 +34,7 @@ st.set_page_config(
 )
 load_dotenv()
 
+# 🔑 2. API Setup & Clients
 openai_api_key = os.getenv('OPENAI_API_KEY', "")
 anthropic_key = os.getenv('ANTHROPIC_API_KEY_3', "")
 if 'OPENAI_API_KEY' in st.secrets:
@@ -47,6 +48,7 @@ openai_client = OpenAI(api_key=openai.api_key, organization=os.getenv('OPENAI_OR
 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:
@@ -70,7 +72,7 @@ if 'should_rerun' not in st.session_state:
 if 'old_val' not in st.session_state:
     st.session_state['old_val'] = None
 
-# 🎨 Minimal Custom CSS
+# 🎨 4. Custom CSS
 st.markdown("""
 <style>
     .main { background: linear-gradient(to right, #1a1a1a, #2d2d2d); color: #fff; }
@@ -86,35 +88,99 @@ FILE_EMOJIS = {
     "mp3": "🎵",
 }
 
-def clean_for_speech(text: str) -> str:
-    text = text.replace("\n", " ")
-    text = text.replace("</s>", " ")
-    text = text.replace("#", "")
-    # Remove links
-    text = re.sub(r"\(https?:\/\/[^\)]+\)", "", text)
-    text = re.sub(r"\s+", " ", text).strip()
-    return text
-
+# 🧠 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([
+        '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'
+    ])
+
+    key_phrases = [
+        'artificial intelligence', 'machine learning', 'deep learning', 'neural network',
+        'personal assistant', 'natural language', 'computer vision', 'data science',
+        'reinforcement learning', 'knowledge graph', 'semantic search', 'time series',
+        'large language model', 'transformer model', 'attention mechanism',
+        'autonomous system', 'edge computing', 'quantum computing', 'blockchain technology',
+        'cognitive science', 'human computer', 'decision making', 'arxiv search',
+        'research paper', 'scientific study', 'empirical analysis'
+    ]
+
+    # First identify key phrases
+    preserved_phrases = []
+    lower_text = text.lower()
+    for phrase in key_phrases:
+        if phrase in lower_text:
+            preserved_phrases.append(phrase)
+            text = text.replace(phrase, '')
+
+    # Then extract individual high-info words
+    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 and deduplicate while preserving order
+    all_terms = preserved_phrases + high_info_words
+    seen = set()
+    unique_terms = []
+    for term in all_terms:
+        if term not in seen:
+            seen.add(term)
+            unique_terms.append(term)
+
+    max_terms = 5
+    return unique_terms[:max_terms]
+
+# 📁 6. File Operations
 def generate_filename(content, file_type="md"):
+    """Generate filename with meaningful terms"""
     prefix = datetime.now().strftime("%y%m_%H%M") + "_"
-    words = re.findall(r"\w+", content)
-    name_text = '_'.join(words[:3]) if words else 'file'
+    info_terms = get_high_info_terms(content)
+    name_text = '_'.join(term.replace(' ', '-') for term in info_terms) if info_terms else 'file'
+    
+    max_length = 100
+    if len(name_text) > max_length:
+        name_text = name_text[:max_length]
+    
     filename = f"{prefix}{name_text}.{file_type}"
     return filename
 
 def create_file(prompt, response, file_type="md"):
+    """Create file with intelligent naming"""
     filename = generate_filename(response.strip() if response.strip() else prompt.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>'
 
+# 🔊 7. Audio Processing
+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>
@@ -126,74 +192,31 @@ def speech_synthesis_html(result):
     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,"mp3")
+    out_fn = generate_filename(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 perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True, full_audio=False):
-    start = time.time()
-    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
-    r = client.predict(q,20,"Semantic Search","mistralai/Mixtral-8x7B-Instruct-v0.1",api_name="/update_with_rag_md")
-    refs = r[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("### 📚 Complete Audio Response")
-        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("### 🎙️ Vocal Summary (Short Answer)")
-        play_and_download_audio(audio_file_main)
-
-    if extended_refs:
-        summaries_text = "Here are the summaries from the references: " + refs.replace('"','')
-        summaries_text = clean_for_speech(summaries_text)
-        audio_file_refs = speak_with_edge_tts(summaries_text)
-        st.write("### 📜 Extended References & Summaries")
-        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 = "Here are the titles of the papers: " + ", ".join(titles)
-            titles_text = clean_for_speech(titles_text)
-            audio_file_titles = speak_with_edge_tts(titles_text)
-            st.write("### 🔖 Paper Titles")
-            play_and_download_audio(audio_file_titles)
-
-    elapsed = time.time()-start
-    st.write(f"**Total Elapsed:** {elapsed:.2f} s")
-    create_file(q, result, "md")
-    return result
-
+# 🎬 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")
@@ -211,12 +234,14 @@ def process_image(image_path, user_prompt):
     return resp.choices[0].message.content
 
 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)
     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"""
     vid = cv2.VideoCapture(video_path)
     total = int(vid.get(cv2.CAP_PROP_FRAME_COUNT))
     fps = vid.get(cv2.CAP_PROP_FPS)
@@ -232,6 +257,7 @@ def process_video(video_path, seconds_per_frame=1):
     return frames_b64
 
 def process_video_with_gpt(video_path, prompt):
+    """Analyze video frames with GPT-4V"""
     frames = process_video(video_path)
     resp = openai_client.chat.completions.create(
         model=st.session_state["openai_model"],
@@ -245,7 +271,58 @@ def process_video_with_gpt(video_path, prompt):
     )
     return resp.choices[0].message.content
 
+# 🤖 9. AI Model Integration
+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")
+    r = client.predict(q,20,"Semantic Search","mistralai/Mixtral-8x7B-Instruct-v0.1",api_name="/update_with_rag_md")
+    refs = r[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("### 📚 Complete Audio Response")
+        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("### 🎙️ Vocal Summary (Short Answer)")
+        play_and_download_audio(audio_file_main)
+
+    if extended_refs:
+        summaries_text = "Here are the summaries from the references: " + refs.replace('"','')
+        summaries_text = clean_for_speech(summaries_text)
+        audio_file_refs = speak_with_edge_tts(summaries_text)
+        st.write("### 📜 Extended References & Summaries")
+        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 = "Here are the titles of the papers: " + ", ".join(titles)
+            titles_text = clean_for_speech(titles_text)
+            audio_file_titles = speak_with_edge_tts(titles_text)
+            st.write("### 🔖 Paper Titles")
+            play_and_download_audio(audio_file_titles)
+
+    elapsed = time.time()-start
+    st.write(f"**Total Elapsed:** {elapsed:.2f} s")
+    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"):
@@ -263,6 +340,7 @@ def process_with_gpt(text):
     return ans
 
 def process_with_claude(text):
+    """Process text with Claude"""
     if not text: return
     with st.chat_message("user"):
         st.markdown(text)
@@ -278,27 +356,42 @@ def process_with_claude(text):
         st.session_state.chat_history.append({"user":text,"claude":ans})
     return ans
 
+# 📂 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']
     all_files = md_files + mp3_files
     if not all_files:
         return None
-    stems = [os.path.splitext(os.path.basename(f))[0] for f in all_files]
-    joined = "_".join(stems)
-    if len(joined) > 50:
-        joined = joined[:50] + "_etc"
-    zip_name = f"{joined}.zip"
+
+    # Collect content for high-info term extraction
+    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 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']
-
     all_files = md_files + mp3_files
 
     groups = defaultdict(list)
@@ -310,25 +403,22 @@ def load_files_for_sidebar():
     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)
+    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):
+    """Extract keywords from markdown files"""
     text = ""
     for f in files:
         if f.endswith(".md"):
             c = open(f,'r',encoding='utf-8').read()
             text += " " + c
-    words = re.findall(r"\w+", text.lower())
-    unique_words = []
-    for w in words:
-        if w not in unique_words:
-            unique_words.append(w)
-        if len(unique_words) == 5:
-            break
-    return unique_words
+    return get_high_info_terms(text)
 
 def display_file_manager_sidebar(groups, sorted_prefixes):
+    """Display file manager in sidebar"""
     st.sidebar.title("🎵 Audio & Document Manager")
 
     all_md = []
@@ -378,16 +468,7 @@ 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}")
 
-def run_selected_model(option, user_input):
-    user_input = user_input.strip()
-    if option == "Arxiv":
-        st.subheader("Arxiv Only Results:")
-        perform_ai_lookup(user_input, vocal_summary=True, extended_refs=False, titles_summary=True)
-    elif option == "GPT-4o":
-        process_with_gpt(user_input)
-    elif option == "Claude-3.5":
-        process_with_claude(user_input)
-
+# 🎯 11. Main Application
 def main():
     st.sidebar.markdown("### 🚲BikeAI🏆 Multi-Agent Research AI")
     tab_main = st.radio("Action:",["🎤 Voice Input","📸 Media Gallery","🔍 Search ArXiv","📝 File Editor"],horizontal=True)
@@ -415,7 +496,10 @@ def main():
                 perform_ai_lookup(edited_input, vocal_summary=True, extended_refs=False, 
                                 titles_summary=True, full_audio=full_audio)
             else:
-                run_selected_model(run_option, edited_input)
+                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("Process Input"):
                 st.session_state.old_val = val
@@ -423,7 +507,10 @@ def main():
                     perform_ai_lookup(edited_input, vocal_summary=True, extended_refs=False, 
                                     titles_summary=True, full_audio=full_audio)
                 else:
-                    run_selected_model(run_option, edited_input)
+                    if run_option == "GPT-4o":
+                        process_with_gpt(edited_input)
+                    elif run_option == "Claude-3.5":
+                        process_with_claude(edited_input)
 
     if tab_main == "🔍 Search ArXiv":
         st.subheader("🔍 Search ArXiv")