Update app.py

app.py

@@ -190,7 +190,7 @@ def generate_filename(prompt, response, file_type="md"):
     return filename
 
 def create_file(prompt, response, file_type="md"):
-    """Create file with intelligent naming"""
+    """Create file with an intelligent naming scheme."""
     filename = generate_filename(prompt.strip(), response.strip(), file_type)
     with open(filename, 'w', encoding='utf-8') as f:
         f.write(prompt + "\n\n" + response)
@@ -226,7 +226,7 @@ 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"""
+    """Generate audio using Edge TTS (async)"""
     text = clean_for_speech(text)
     if not text.strip():
         return None
@@ -238,17 +238,16 @@ async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=
     return out_fn
 
 def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0):
-    """Wrapper for edge TTS generation"""
+    """Wrapper for edge TTS generation (sync)"""
     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"""
+    """Play and provide a 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)
 
-# NEW: Helper to embed auto-play audio
 def auto_play_audio(file_path):
     """
     Reads MP3 file as base64, displays an <audio> tag with autoplay + controls + download link.
@@ -270,17 +269,19 @@ def auto_play_audio(file_path):
     </a>
     """, unsafe_allow_html=True)
 
-# NEW: Generate specialized MP3 filename using query + paper metadata
 def generate_audio_filename(query, title, summary):
+    """
+    Example specialized MP3 filename: prefix + query + short snippet of title/summary
+    """
     combined = (query + " " + title + " " + summary).strip().lower()
     combined = re.sub(r'[^\w\s-]', '', combined)  # remove special chars
-    combined = "_".join(combined.split())[:80]    # max ~80 chars to keep it short
+    combined = "_".join(combined.split())[:80]    # limit length
     prefix = datetime.now().strftime("%y%m_%H%M")
     return f"{prefix}_{combined}.mp3"
 
 # 🎬 8. Media Processing
 def process_image(image_path, user_prompt):
-    """Process image with GPT-4V"""
+    """Process image with GPT-4V (placeholder logic)"""
     with open(image_path, "rb") as imgf:
         image_data = imgf.read()
     b64img = base64.b64encode(image_data).decode("utf-8")
@@ -301,14 +302,14 @@ def process_image(image_path, user_prompt):
     return resp.choices[0].message.content
 
 def process_audio(audio_path):
-    """Process audio with Whisper"""
+    """Process audio with Whisper (placeholder logic)"""
     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"""
+    """Extract frames from video (placeholder logic)"""
     vid = cv2.VideoCapture(video_path)
     total = int(vid.get(cv2.CAP_PROP_FRAME_COUNT))
     fps = vid.get(cv2.CAP_PROP_FPS)
@@ -325,7 +326,7 @@ 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"""
+    """Analyze video frames with GPT-4V (placeholder logic)"""
     frames = process_video(video_path)
     resp = openai_client.chat.completions.create(
         model=st.session_state["openai_model"],
@@ -334,7 +335,7 @@ def process_video_with_gpt(video_path, prompt):
             {
                 "role": "user",
                 "content": [
-                    {"type": "text","text": prompt},
+                    {"type":"text","text":prompt},
                     *[{"type":"image_url","image_url":{"url":f"data:image/jpeg;base64,{fr}"}} for fr in frames]
                 ]
             }
@@ -348,108 +349,104 @@ def save_full_transcript(query, text):
     """Save full transcript of Arxiv results as a file."""
     create_file(query, text, "md")
 
-# NEW: parse references with bracketed titles, up to 20
+# ---------------------------------------------------
+# NEW: Extremely simple "parse_arxiv_refs" logic
+# that reads each non-empty line, up to 20 lines.
+# Extract bracketed title if present, year if present.
+# The entire line is the "summary" for display + TTS.
+# ---------------------------------------------------
 def parse_arxiv_refs(ref_text: str):
     lines = ref_text.split('\n')
-    results = []
-    for line in lines:
-        line = line.strip()
-        if not line:
-            continue
-        # bracketed title
-        title_match = re.search(r"\[([^\]]+)\]", line)
-        if title_match:
-            raw_title = title_match.group(1).strip()
-        else:
-            raw_title = "No Title"
-        remainder = line.replace(title_match.group(0), "").strip() if title_match else line
-        summary = remainder
-
-        # guess year from either title or summary
-        year_match = re.search(r'(20\d{2})', raw_title)
-        if not year_match:
-            year_match = re.search(r'(20\d{2})', summary)
+    # remove empty lines
+    lines = [ln.strip() for ln in lines if ln.strip()]
+    # limit to 20
+    lines = lines[:20]
+
+    refs = []
+    for ln in lines:
+        # bracketed title if found
+        bracket_match = re.search(r"\[([^\]]+)\]", ln)
+        title = bracket_match.group(1) if bracket_match else "No Title"
+        # find a year 20xx if present
+        year_match = re.search(r"(20\d{2})", ln)
         year = int(year_match.group(1)) if year_match else None
-
-        results.append({
-            'title': raw_title,
-            'summary': summary,
-            'year': year
+        
+        refs.append({
+            "line": ln,      # the entire raw line for display
+            "title": title,  # bracketed content or "No Title"
+            "year": year     # e.g. 2023, 2024, or None
         })
-    return results
-
+    return refs
 
 def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, 
                       titles_summary=True, full_audio=False):
-    """Perform Arxiv search and generate audio summaries."""
+    """
+    1) Query the RAG pipeline
+    2) Display results
+    3) Also parse references into lines, up to 20
+    4) Show each reference with full content
+    5) If year in [2023, 2024], auto-generate TTS
+    """
     start = time.time()
 
-    # 1) Query the HF RAG pipeline
+    # 1) Query 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]
+    # 20 references
+    refs = client.predict(q, 20, "Semantic Search", "mistralai/Mixtral-8x7B-Instruct-v0.1",
+                          api_name="/update_with_rag_md")[0]
+    # Main summary
     r2 = client.predict(q, "mistralai/Mixtral-8x7B-Instruct-v0.1", True, api_name="/ask_llm")
 
-    # 2) Combine for final text output
+    # 2) Combine for final text
     result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"
     st.markdown(result)
 
-    # Existing logic for "all-at-once" audio
+    # Optionally produce "all at once" TTS
     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)  # or auto_play_audio(audio_file_full)
+        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)  # or auto_play_audio(audio_file_main)
+        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)  # or auto_play_audio(audio_file_refs)
-
-    # --------------------------------------
-    # Parse references, limit to 20, generate TTS if year==2023 or 2024
-    # --------------------------------------
-    parsed_refs = parse_arxiv_refs(refs)[:20]
-    # Sort by year descending (None -> 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']}")
+        play_and_download_audio(audio_file_refs)
+
+    # 3) Parse references
+    parsed = parse_arxiv_refs(refs)
+
+    # 4) Show references
+    st.write("## Individual Paper Lines (Up to 20)")
+    for i, ref in enumerate(parsed):
+        st.markdown(f"**Ref #{i+1}**:  {ref['line']}")
+        if ref['year'] in [2023, 2024]:
+            # TTS content: "Title + entire line"
+            tts_text = f"Title: {ref['title']}. Full content: {ref['line']}"
+            out_fn = generate_audio_filename(q, ref['title'], ref['line'])
+            tmp_mp3 = speak_with_edge_tts(tts_text)
+            if tmp_mp3 and os.path.exists(tmp_mp3):
+                # rename to out_fn
+                os.rename(tmp_mp3, out_fn)
+                # auto-play
+                auto_play_audio(out_fn)
         st.write("---")
 
-        # Only auto-generate TTS if year is 2023 or 2024
-        if paper["year"] in [2023, 2024]:
-            # Combine Title, Year, Summary in one text
-            tts_text = (
-                f"Title: {paper['title']}. "
-                f"Year: {paper['year']}. "
-                f"Summary: {paper['summary']}"
-            )
-            # Generate specialized MP3 filename
-            mp3_filename = generate_audio_filename(q, paper['title'], paper['summary'])
-
-            # Create TTS as usual
-            temp_mp3 = speak_with_edge_tts(tts_text)
-            if temp_mp3 and os.path.exists(temp_mp3):
-                # rename to a meaningful name
-                os.rename(temp_mp3, mp3_filename)
-                # Now embed the auto-play audio
-                auto_play_audio(mp3_filename)
-
-    # Titles Only (all-in-one)
+    # Titles only block
     if titles_summary:
+        # This was your older code - parse bracketed titles from each line
+        # to produce an all-in-one TTS if desired
+        lines = refs.split('\n')
         titles = []
-        for line in refs.split('\n'):
+        for line in lines:
             m = re.search(r"\[([^\]]+)\]", line)
             if m:
                 titles.append(m.group(1))
@@ -459,17 +456,15 @@ def perform_ai_lookup(q, vocal_summary=True, extended_refs=False,
             audio_file_titles = speak_with_edge_tts(titles_text)
             st.write("### 🔖 Titles (All-In-One)")
             play_and_download_audio(audio_file_titles)
-            # or auto_play_audio(audio_file_titles)
 
     elapsed = time.time() - start
     st.write(f"**Total Elapsed:** {elapsed:.2f} s")
 
-    # Save entire text to file as usual
+    # 5) Save entire text as MD file
     create_file(q, result, "md")
 
     return result
 
-
 def process_with_gpt(text):
     """Process text with GPT-4"""
     if not text:
@@ -509,7 +504,7 @@ def process_with_claude(text):
 
 # 📂 10. File Management
 def create_zip_of_files(md_files, mp3_files):
-    """Create zip with intelligent naming"""
+    """Create zip with a short naming approach"""
     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:
@@ -541,22 +536,21 @@ 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
 
+    all_files = md_files + mp3_files
     groups = defaultdict(list)
     for f in all_files:
         fname = os.path.basename(f)
-        prefix = fname[:10]
+        prefix = fname[:10]  # e.g. "2310_1205_"
         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):
@@ -596,14 +590,14 @@ 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]
         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)
+            c1,c2 = st.columns(2)
             with c1:
                 if st.button("👀ViewGrp", key="view_group_"+prefix):
                     st.session_state.viewing_prefix = prefix
@@ -624,7 +618,7 @@ def main():
     st.sidebar.markdown("### 🚲BikeAI🏆 Multi-Agent Research")
     tab_main = st.radio("Action:", ["🎤 Voice","📸 Media","🔍 ArXiv","📝 Editor"], horizontal=True)
 
-    # This is your custom React component reference, if used.
+    # If you have a custom React component
     mycomponent = components.declare_component("mycomponent", path="mycomponent")
     val = mycomponent(my_input_value="Hello")
 
@@ -650,11 +644,10 @@ def main():
                                   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)
+            elif 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
@@ -664,11 +657,10 @@ def main():
                                       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)
+                elif 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")
@@ -726,7 +718,7 @@ def main():
         with tabs[0]:
             imgs = glob.glob("*.png")+glob.glob("*.jpg")
             if imgs:
-                c = st.slider("Cols",1,5,3)
+                c = st.slider("Cols", 1, 5, 3)
                 cols = st.columns(c)
                 for i, f in enumerate(imgs):
                     with cols[i % c]:
@@ -749,7 +741,7 @@ def main():
                 st.write("No videos found.")
 
     elif tab_main == "📝 Editor":
-        if getattr(st.session_state,'current_file', None):
+        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"):
@@ -760,9 +752,11 @@ def main():
         else:
             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}")
@@ -784,6 +778,5 @@ def main():
         st.session_state.should_rerun = False
         st.rerun()
 
-
 if __name__ == "__main__":
     main()