Update app.py

app.py

@@ -142,9 +142,57 @@ def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0):
 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>'
+        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
+
 def process_image(image_path, user_prompt):
     with open(image_path, "rb") as imgf:
         image_data = imgf.read()
@@ -197,47 +245,6 @@ def process_video_with_gpt(video_path, prompt):
     )
     return resp.choices[0].message.content
 
-def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True):
-    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)
-
-    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):
     if not text: return
     st.session_state.messages.append({"role":"user","content":text})
@@ -385,9 +392,6 @@ 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)
 
-    # Removed the old model_choice radio
-    # Instead, we rely on the dropdown in the Process Input section.
-
     mycomponent = components.declare_component("mycomponent", path="mycomponent")
     val = mycomponent(my_input_value="Hello")
 
@@ -396,39 +400,51 @@ def main():
         val_stripped = val.replace('\n', ' ')
         edited_input = st.text_area("Edit your detected input:", value=val_stripped, height=100)
         run_option = st.selectbox("Select AI Model:", ["Arxiv", "GPT-4o", "Claude-3.5"])
-        autorun = st.checkbox("AutoRun on input change", value=False)
+        col1, col2 = st.columns(2)
+        with col1:
+            autorun = st.checkbox("AutoRun on input change", value=False)
+        with col2:
+            full_audio = st.checkbox("Generate Complete Audio", value=False, 
+                                   help="Generate audio for the complete response including all papers and summaries")
 
         input_changed = (val != st.session_state.old_val)
 
         if autorun and input_changed:
-            # Automatically run the selected model if input changed
             st.session_state.old_val = val
-            run_selected_model(run_option, edited_input)
+            if run_option == "Arxiv":
+                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)
         else:
-            # If not autorun, show a button to run manually
             if st.button("Process Input"):
                 st.session_state.old_val = val
-                run_selected_model(run_option, edited_input)
-
+                if run_option == "Arxiv":
+                    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 tab_main == "🔍 Search ArXiv":
         st.subheader("🔍 Search ArXiv")
-        q=st.text_input("Research query:")
+        q = st.text_input("Research query:")
 
         st.markdown("### 🎛️ Audio Generation Options")
         vocal_summary = st.checkbox("🎙️ Vocal Summary (Short Answer)", value=True)
         extended_refs = st.checkbox("📜 Extended References & Summaries (Long)", value=False)
         titles_summary = st.checkbox("🔖 Paper Titles Only", value=True)
+        full_audio = st.checkbox("📚 Generate Complete Audio Response", value=False,
+                               help="Generate audio for the complete response including all papers and summaries")
 
         if q and st.button("Run ArXiv Query"):
-            perform_ai_lookup(q, vocal_summary=vocal_summary, extended_refs=extended_refs, titles_summary=titles_summary)
+            perform_ai_lookup(q, vocal_summary=vocal_summary, extended_refs=extended_refs, 
+                            titles_summary=titles_summary, full_audio=full_audio)
 
     elif tab_main == "🎤 Voice Input":
         st.subheader("🎤 Voice Recognition")
         user_text = st.text_area("Message:", height=100)
         user_text = user_text.strip().replace('\n', ' ')
         if st.button("Send 📨"):
-            # Default to GPT-4o here, or you could similarly provide options.
             process_with_gpt(user_text)
         st.subheader("📜 Chat History")
         t1,t2=st.tabs(["Claude History","GPT-4o History"])
@@ -506,4 +522,4 @@ def main():
         st.rerun()
 
 if __name__=="__main__":
-    main()
+    main()