Update app.py

app.py

@@ -114,7 +114,6 @@ def play_and_download_audio(file_path):
         st.markdown(get_download_link(file_path), unsafe_allow_html=True)
 #---------------------------
 
-
 def process_image(image_path, user_prompt):
     with open(image_path, "rb") as imgf:
         image_data = imgf.read()
@@ -188,11 +187,6 @@ def perform_ai_lookup(q):
     r2 = client.predict(q,"mistralai/Mixtral-8x7B-Instruct-v0.1",True,api_name="/ask_llm")
     result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"
 
-    #---------------------------------------------------------------
-    # Speak results
-    #speech_synthesis_html(r2)
-
-    # Instead of speech_synthesis_html, use EdgeTTS now:
     st.markdown(result)
 
     # Speak main result
@@ -200,7 +194,6 @@ def perform_ai_lookup(q):
     st.write("### Audio Output for Main Result")
     play_and_download_audio(audio_file_main)
 
-
     # Speak references summaries
     summaries_text = "Here are the summaries from the references: " + refs.replace('"','')
     audio_file_refs = speak_with_edge_tts(summaries_text, voice="en-US-AriaNeural", rate=0, pitch=0)
@@ -218,10 +211,7 @@ def perform_ai_lookup(q):
         audio_file_titles = speak_with_edge_tts(titles_text, voice="en-US-AriaNeural", rate=0, pitch=0)
         st.write("### Audio Output for Paper Titles")
         play_and_download_audio(audio_file_titles)
-    # --------------------------------------------
-
 
-    st.markdown(result)
     elapsed = time.time()-start
     st.write(f"Elapsed: {elapsed:.2f} s")
     fn = generate_filename(q,"md")
@@ -261,10 +251,15 @@ def process_with_claude(text):
         st.session_state.chat_history.append({"user":text,"claude":ans})
         return ans
 
-def create_zip_of_files(files):
+def create_zip_of_files():
+    # Include all .md and .mp3 files in the zip
+    md_files = glob.glob("*.md")
+    mp3_files = glob.glob("*.mp3")
+    all_files = md_files + mp3_files
     zip_name = "all_files.zip"
     with zipfile.ZipFile(zip_name,'w') as z:
-        for f in files: z.write(f)
+        for f in all_files:
+            z.write(f)
     return zip_name
 
 def get_media_html(p,typ="video",w="100%"):
@@ -274,63 +269,58 @@ def get_media_html(p,typ="video",w="100%"):
     else:
         return f'<audio controls style="width:{w};"><source src="data:audio/mpeg;base64,{d}" type="audio/mpeg"></audio>'
 
-def create_media_gallery():
-    st.header("🎬 Media Gallery")
-    tabs = st.tabs(["🖼️ Images", "🎵 Audio", "🎥 Video"])
-    with tabs[0]:
-        imgs = glob.glob("*.png")+glob.glob("*.jpg")
-        if imgs:
-            c = st.slider("Cols",1,5,3)
-            cols = st.columns(c)
-            for i,f in enumerate(imgs):
-                with cols[i%c]:
-                    st.image(Image.open(f),use_container_width=True)
-                    if st.button(f"👀 Analyze {os.path.basename(f)}"):
-                        a = process_image(f,"Describe this image.")
-                        st.markdown(a)
-    with tabs[1]:
-        auds = glob.glob("*.mp3")+glob.glob("*.wav")
-        for a in auds:
-            with st.expander(f"🎵 {os.path.basename(a)}"):
-                st.markdown(get_media_html(a,"audio"),unsafe_allow_html=True)
-                if st.button(f"Transcribe {os.path.basename(a)}"):
+def display_file_manager():
+    st.sidebar.title("🎵 Audio Files & Documents")
+    st.sidebar.markdown("Here you can find all recorded `.mp3` files and `.md` notes.")
+    
+    # Display .mp3 files in the sidebar
+    mp3_files = sorted(glob.glob("*.mp3"), reverse=True)
+    if mp3_files:
+        st.sidebar.subheader("MP3 Files:")
+        for a in mp3_files:
+            with st.sidebar.expander(f"{os.path.basename(a)}"):
+                # Show audio player
+                st.sidebar.markdown(get_media_html(a,"audio"),unsafe_allow_html=True)
+                # Download link for the MP3 file
+                st.sidebar.markdown(get_download_link(a), unsafe_allow_html=True)
+                # Button to transcribe this file
+                if st.sidebar.button(f"Transcribe {os.path.basename(a)}"):
                     t = process_audio(a)
-                    st.write(t)
-    with tabs[2]:
-        vids = glob.glob("*.mp4")
-        for v in vids:
-            with st.expander(f"🎥 {os.path.basename(v)}"):
-                st.markdown(get_media_html(v,"video"),unsafe_allow_html=True)
-                if st.button(f"Analyze {os.path.basename(v)}"):
-                    a = process_video_with_gpt(v,"Describe video.")
-                    st.markdown(a)
+                    st.sidebar.write("Transcription:")
+                    st.sidebar.write(t)
+    else:
+        st.sidebar.write("No MP3 files found.")
 
-def display_file_manager():
-    st.sidebar.title("📁 File Management")
-    files = sorted(glob.glob("*.md"),reverse=True)
-    if st.sidebar.button("🗑 Delete All"):
+    # Display .md files in the sidebar
+    st.sidebar.subheader("MD Files:")
+    files = sorted(glob.glob("*.md"), reverse=True)
+    if st.sidebar.button("🗑 Delete All MD"):
         for f in files: os.remove(f)
-        st.rerun()
-    if st.sidebar.button("⬇️ Download All"):
-        z= create_zip_of_files(files)
+        st.experimental_rerun()
+    # Download all as zip (including .mp3 and .md)
+    if st.sidebar.button("⬇️ Download All (.md and .mp3)"):
+        z = create_zip_of_files()
         st.sidebar.markdown(get_download_link(z),unsafe_allow_html=True)
+
     for f in files:
-        col1,col2,col3,col4 = st.sidebar.columns([1,3,1,1])
+        col1, col2, col3, col4 = st.sidebar.columns([1,3,1,1])
         with col1:
-            if st.button("🌐",key="v"+f):
-                st.session_state.current_file=f
-                c=open(f,'r',encoding='utf-8').read()
+            if st.sidebar.button("🌐", key="v"+f):
+                st.session_state.current_file = f
+                c = open(f,'r',encoding='utf-8').read()
+                st.write("**Viewing file content:**")
                 st.write(c)
         with col2:
-            st.markdown(get_download_link(f),unsafe_allow_html=True)
+            st.sidebar.markdown(get_download_link(f),unsafe_allow_html=True)
         with col3:
-            if st.button("📂",key="e"+f):
-                st.session_state.current_file=f
-                st.session_state.file_content=open(f,'r',encoding='utf-8').read()
+            if st.sidebar.button("📂", key="e"+f):
+                st.session_state.current_file = f
+                st.session_state.file_content = open(f,'r',encoding='utf-8').read()
         with col4:
-            if st.button("🗑",key="d"+f):
+            if st.sidebar.button("🗑", key="d"+f):
                 os.remove(f)
                 st.experimental_rerun()
+
 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)
@@ -341,7 +331,6 @@ def main():
     mycomponent = components.declare_component("mycomponent", path="mycomponent")
     val = mycomponent(my_input_value="Hello")
     if val:
-        # Strip whitespace and newlines from the end of the user input
         user_input = val.strip()
         if user_input:
             if model_choice == "GPT-4o":
@@ -372,7 +361,6 @@ def main():
     if tab_main == "🎤 Voice Input":
         st.subheader("🎤 Voice Recognition")
         user_text = st.text_area("Message:", height=100)
-        # Strip whitespace and newlines
         user_text = user_text.strip()
         if st.button("Send 📨"):
             if user_text:
@@ -407,12 +395,38 @@ def main():
                     st.markdown(m["content"])
 
     elif tab_main == "📸 Media Gallery":
-        create_media_gallery()
+        # Only show Images and Videos since Audio is now in sidebar
+        st.header("🎬 Media Gallery - Images and Videos")
+        tabs = st.tabs(["🖼️ Images", "🎥 Video"])
+        with tabs[0]:
+            imgs = glob.glob("*.png")+glob.glob("*.jpg")
+            if imgs:
+                c = st.slider("Cols",1,5,3)
+                cols = st.columns(c)
+                for i,f in enumerate(imgs):
+                    with cols[i%c]:
+                        st.image(Image.open(f),use_container_width=True)
+                        if st.button(f"👀 Analyze {os.path.basename(f)}"):
+                            a = process_image(f,"Describe this image.")
+                            st.markdown(a)
+            else:
+                st.write("No images found.")
+        with tabs[1]:
+            vids = glob.glob("*.mp4")
+            if vids:
+                for v in vids:
+                    with st.expander(f"🎥 {os.path.basename(v)}"):
+                        st.markdown(get_media_html(v,"video"),unsafe_allow_html=True)
+                        if st.button(f"Analyze {os.path.basename(v)}"):
+                            a = process_video_with_gpt(v,"Describe video.")
+                            st.markdown(a)
+            else:
+                st.write("No videos found.")
 
     elif tab_main == "🔍 Search ArXiv":
         q=st.text_input("Research query:")
         if q:
-            q = q.strip()  # Strip whitespace and newlines
+            q = q.strip()
             if q:
                 r=search_arxiv(q)
                 st.markdown(r)
@@ -421,14 +435,15 @@ def main():
         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)
-            # Here also you can strip if needed, but usually for file editing you might not want to.
             if st.button("Save"):
                 with open(st.session_state.current_file,'w',encoding='utf-8') as f:
                     f.write(new_text)
                 st.success("Updated!")
+        else:
+            st.write("Select a file from the sidebar to edit.")
 
     display_file_manager()
 
 
 if __name__=="__main__":
-    main()
+    main()