Update app.py

app.py

@@ -19,7 +19,6 @@ import extra_streamlit_components as stx
 from streamlit.runtime.scriptrunner import get_script_run_ctx
 import asyncio
 import edge_tts
-import moviepy.editor as mp  # 🆕 Import moviepy for MP4 generation
 
 # 🎯 1. Core Configuration & Setup
 st.set_page_config(
@@ -48,7 +47,7 @@ EDGE_TTS_VOICES = [
     "en-CA-LiamNeural"
 ]
 
-# Add this to your session state initialization section:
+# Initialize session state variables
 if 'tts_voice' not in st.session_state:
     st.session_state['tts_voice'] = EDGE_TTS_VOICES[0]  # Default voice
 if 'audio_format' not in st.session_state:
@@ -109,7 +108,7 @@ st.markdown("""
 FILE_EMOJIS = {
     "md": "📝",
     "mp3": "🎵",
-    "mp4": "🎬"  # 🆕 Add emoji for MP4
+    "wav": "🔊"  # 🆕 Add emoji for WAV
 }
 
 # 🧠 5. High-Information Content Extraction
@@ -202,8 +201,8 @@ def get_download_link(file, 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 == "mp4":
-        return f'<a href="data:video/mp4;base64,{b64}" download="{os.path.basename(file)}">🎬 Download {os.path.basename(file)}</a>'  # 🆕 MP4 download link
+    elif file_type == "wav":
+        return f'<a href="data:audio/wav;base64,{b64}" download="{os.path.basename(file)}">🔊 Download {os.path.basename(file)}</a>'  # 🆕 WAV download link
     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:
@@ -240,43 +239,21 @@ async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=
     rate_str = f"{rate:+d}%"
     pitch_str = f"{pitch:+d}Hz"
     communicate = edge_tts.Communicate(text, voice, rate=rate_str, pitch=pitch_str)
-    if file_format == "mp3":
-        out_fn = generate_filename(text, text, "mp3")
-        await communicate.save(out_fn)
-        return out_fn
-    elif file_format == "mp4":
-        # Generate MP3 first
-        mp3_filename = generate_filename(text, text, "mp3")
-        await communicate.save(mp3_filename)
-        
-        # Create MP4 by combining MP3 with a placeholder image
-        placeholder_image = "placeholder.jpg"  # 🆕 Ensure this image exists in your directory
-        if not os.path.exists(placeholder_image):
-            st.error(f"Placeholder image '{placeholder_image}' not found. Please add it to the directory.")
-            return mp3_filename  # Return MP3 if image not found
-        
-        video_filename = os.path.splitext(mp3_filename)[0] + ".mp4"
-        try:
-            audio_clip = mp.AudioFileClip(mp3_filename)
-            image_clip = mp.ImageClip(placeholder_image).set_duration(audio_clip.duration)
-            video_clip = image_clip.set_audio(audio_clip)
-            video_clip.write_videofile(video_filename, codec="libx264", audio_codec="aac", verbose=False, logger=None)
-            return video_filename
-        except Exception as e:
-            st.warning(f"Error generating MP4 for {mp3_filename}: {str(e)}")
-            return mp3_filename  # Return MP3 if MP4 generation fails
+    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"):
     """Wrapper for edge TTS generation"""
     return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch, file_format))
 
 def play_and_download_audio(file_path, file_type="mp3"):
-    """Play and provide download link for audio/video"""
+    """Play and provide download link for audio"""
     if file_path and os.path.exists(file_path):
-        if file_type in ["mp3", "wav"]:
+        if file_type == "mp3":
+            st.audio(file_path)
+        elif file_type == "wav":
             st.audio(file_path)
-        elif file_type == "mp4":
-            st.video(file_path)  # 🆕 Use st.video for MP4 files
         dl_link = get_download_link(file_path, file_type=file_type)
         st.markdown(dl_link, unsafe_allow_html=True)
 
@@ -299,7 +276,7 @@ def process_image(image_path, user_prompt):
     )
     return resp.choices[0].message.content
 
-def process_audio(audio_path):
+def process_audio_file(audio_path):
     """Process audio with Whisper"""
     with open(audio_path, "rb") as f:
         transcription = openai_client.audio.transcriptions.create(model="whisper-1", file=f)
@@ -422,7 +399,7 @@ def create_paper_audio_files(papers, input_question):
             full_file = speak_with_edge_tts(full_text, voice=st.session_state['tts_voice'], file_format=file_format)
             paper['full_audio'] = full_file
 
-            # Display the audio/video immediately after generation
+            # Display the audio immediately after generation
             st.write(f"### {FILE_EMOJIS.get(file_format, '')} {os.path.basename(full_file)}")
             play_and_download_audio(full_file, file_type=file_format)
             
@@ -432,18 +409,18 @@ def create_paper_audio_files(papers, input_question):
             st.warning(f"Error generating audio for paper {paper['title']}: {str(e)}")
             paper['full_audio'] = None
 
-    # After all individual audios, create a combined summary audio/video
+    # After all individual audios, create a combined summary audio
     if combined_titles:
         combined_text = f"Here are the titles of the papers related to your query: {'; '.join(combined_titles)}. Your original question was: {input_question}"
         file_format = st.session_state['audio_format']
         combined_file = speak_with_edge_tts(combined_text, voice=st.session_state['tts_voice'], file_format=file_format)
-        st.write(f"### {FILE_EMOJIS.get(file_format, '')} Combined Summary {'Video' if file_format=='mp4' else 'Audio'}")
+        st.write(f"### {FILE_EMOJIS.get(file_format, '')} Combined Summary Audio")
         play_and_download_audio(combined_file, file_type=file_format)
         papers.append({'title': 'Combined Summary', 'full_audio': combined_file})
 
 def display_papers(papers):
     """
-    Display papers with their audio/video controls using URLs as unique keys.
+    Display papers with their audio controls using URLs as unique keys.
     """
     st.write("## Research Papers")
     
@@ -453,18 +430,18 @@ def display_papers(papers):
             st.markdown(f"*{paper['authors']}*")
             st.markdown(paper['summary'])
             
-            # Single audio/video control for full content
+            # Single audio control for full content
             if paper.get('full_audio'):
-                st.write("📚 Paper Audio/Video")
-                file_ext = os.path.splitext(paper['full_audio'])[1].lower()
-                if file_ext == ".mp3":
+                st.write("📚 Paper Audio")
+                file_ext = os.path.splitext(paper['full_audio'])[1].lower().strip('.')
+                if file_ext == "mp3":
+                    st.audio(paper['full_audio'])
+                elif file_ext == "wav":
                     st.audio(paper['full_audio'])
-                elif file_ext == ".mp4":
-                    st.video(paper['full_audio'])
 
 def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, 
                      titles_summary=True, full_audio=False):
-    """Perform Arxiv search with audio/video generation per paper."""
+    """Perform Arxiv search with audio generation per paper."""
     start = time.time()
 
     # Query the HF RAG pipeline
@@ -532,11 +509,11 @@ def process_with_claude(text):
     return ans
 
 # 📂 10. File Management
-def create_zip_of_files(md_files, mp3_files, mp4_files, input_question):
+def create_zip_of_files(md_files, mp3_files, wav_files, input_question):
     """Create zip with intelligent naming based on top 10 common words."""
     # Exclude 'readme.md'
     md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
-    all_files = md_files + mp3_files + mp4_files
+    all_files = md_files + mp3_files + wav_files
     if not all_files:
         return None
 
@@ -546,12 +523,7 @@ def create_zip_of_files(md_files, mp3_files, mp4_files, input_question):
         if f.endswith('.md'):
             with open(f, 'r', encoding='utf-8') as file:
                 all_content.append(file.read())
-        elif f.endswith('.mp3'):
-            # Replace underscores with spaces and extract basename without extension
-            basename = os.path.splitext(os.path.basename(f))[0]
-            words = basename.replace('_', ' ')
-            all_content.append(words)
-        elif f.endswith('.mp4'):
+        elif f.endswith('.mp3') or f.endswith('.wav'):
             # Replace underscores with spaces and extract basename without extension
             basename = os.path.splitext(os.path.basename(f))[0]
             words = basename.replace('_', ' ')
@@ -577,10 +549,10 @@ def load_files_for_sidebar():
     """Load and group files for sidebar display"""
     md_files = glob.glob("*.md")
     mp3_files = glob.glob("*.mp3")
-    mp4_files = glob.glob("*.mp4")  # 🆕 Load MP4 files
+    wav_files = glob.glob("*.wav")  # 🆕 Load WAV files
 
     md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
-    all_files = md_files + mp3_files + mp4_files
+    all_files = md_files + mp3_files + wav_files
 
     groups = defaultdict(list)
     for f in all_files:
@@ -610,17 +582,17 @@ def display_file_manager_sidebar(groups_sorted):
 
     all_md = []
     all_mp3 = []
-    all_mp4 = []  # 🆕 List to hold MP4 files
+    all_wav = []  # 🆕 List to hold WAV files
     for group_name, files in groups_sorted:
         for f in files:
             if f.endswith(".md"):
                 all_md.append(f)
             elif f.endswith(".mp3"):
                 all_mp3.append(f)
-            elif f.endswith(".mp4"):
-                all_mp4.append(f)  # 🆕 Append MP4 files
+            elif f.endswith(".wav"):
+                all_wav.append(f)  # 🆕 Append WAV files
 
-    top_bar = st.sidebar.columns(4)  # 🆕 Adjusted columns to accommodate MP4
+    top_bar = st.sidebar.columns(4)  # 🆕 Adjusted columns to accommodate WAV
     with top_bar[0]:
         if st.button("🗑 DelAllMD"):
             for f in all_md:
@@ -632,13 +604,13 @@ def display_file_manager_sidebar(groups_sorted):
                 os.remove(f)
             st.session_state.should_rerun = True
     with top_bar[2]:
-        if st.button("🗑 DelAllMP4"):
-            for f in all_mp4:
+        if st.button("🗑 DelAllWAV"):
+            for f in all_wav:
                 os.remove(f)
             st.session_state.should_rerun = True
     with top_bar[3]:
         if st.button("⬇️ ZipAll"):
-            zip_name = create_zip_of_files(all_md, all_mp3, all_mp4, input_question=st.session_state.get('last_query', ''))
+            zip_name = create_zip_of_files(all_md, all_mp3, all_wav, input_question=st.session_state.get('last_query', ''))
             if zip_name:
                 st.sidebar.markdown(get_download_link(zip_name, file_type="zip"), unsafe_allow_html=True)
 
@@ -677,7 +649,7 @@ def main():
     st.sidebar.markdown("### 🔊 Audio Format")
     selected_format = st.sidebar.radio(
         "Choose Audio Format:",
-        options=["MP3", "MP4"],
+        options=["MP3", "WAV"],
         index=0  # Default to MP3
     )
     
@@ -838,8 +810,8 @@ def main():
                         st.markdown(content)
                     elif ext == "mp3":
                         st.audio(f)
-                    elif ext == "mp4":
-                        st.video(f)  # 🆕 Handle MP4 files
+                    elif ext == "wav":
+                        st.audio(f)  # 🆕 Handle WAV files
                     else:
                         st.markdown(get_download_link(f), unsafe_allow_html=True)
                 break