Update app.py

app.py

@@ -23,29 +23,6 @@ menu = ["txt", "htm", "md", "py"]
 choice = st.sidebar.selectbox("Output File Type:", menu)
 model_choice = st.sidebar.radio("Select Model:", ('gpt-3.5-turbo', 'gpt-3.5-turbo-0301'))
 
-audio_enabled = st.sidebar.checkbox("Audio", value=False)
-
-if audio_enabled:
-    def save_and_play_audio(audio_recorder):
-        audio_bytes = audio_recorder()
-        if audio_bytes:
-            filename = generate_filename("Recording", "wav")
-            with open(filename, 'wb') as f:
-                f.write(audio_bytes)
-            st.sidebar.audio(audio_bytes, format="audio/wav")
-            return filename
-        return None
-
-    # Updated to call direct from transcription to chat inference.
-    filename = save_and_play_audio(audio_recorder)
-    if filename is not None:
-        transcription = transcribe_audio(openai.api_key, filename, "whisper-1")
-        st.sidebar.markdown('### Transcription:')
-        st.sidebar.write(transcription)
-        
-    # max_length moved to the sidebar
-    max_length = st.sidebar.slider("File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
-
 def generate_filename(prompt, file_type):
     central = pytz.timezone('US/Central')
     safe_date_time = datetime.now(central).strftime("%m%d_%I%M")  
@@ -53,6 +30,20 @@ def generate_filename(prompt, file_type):
     return f"{safe_date_time}_{safe_prompt}.{file_type}"
 
 TEMPERATURE = st.sidebar.slider("Adjust Creativity:", min_value=0.1, max_value=1.0, value=0.5, step=0.1)
+
+audio_checkbox = st.sidebar.checkbox("Audio", value=False)
+
+if audio_checkbox:
+    record_audio = st.sidebar.button("Record Audio")
+    if record_audio:
+        filename = save_and_play_audio(audio_recorder)
+        if filename is not None:
+            transcription = transcribe_audio(openai.api_key, filename, "whisper-1")
+            st.markdown('### Transcription:')
+            st.write(transcription)
+else:
+    record_audio = False
+
 def chat_with_model(prompt, document_section):
     model = model_choice
     conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
@@ -60,7 +51,7 @@ def chat_with_model(prompt, document_section):
     conversation.append({'role': 'assistant', 'content': document_section})
     response = openai.ChatCompletion.create(model=model, messages=conversation, temperature=TEMPERATURE)
     return response['choices'][0]['message']['content']
-    
+
 def create_file(filename, prompt, response):
     if filename.endswith(".txt"):
         with open(filename, 'w') as file:
@@ -71,7 +62,7 @@ def create_file(filename, prompt, response):
     elif filename.endswith(".md"):
         with open(filename, 'w') as file:
             file.write(f"# Prompt:\n{prompt}\n# Response:\n{response}")
-    
+
 # Updated to auto process transcript to chatgpt in AI pipeline from Whisper to ChatGPT
 def transcribe_audio(openai_key, file_path, model):
     OPENAI_API_URL = "https://api.openai.com/v1/audio/transcriptions"
@@ -93,7 +84,7 @@ def transcribe_audio(openai_key, file_path, model):
         st.write(response.json())
         st.error("Error in API call.")
         return None
-        
+
 def save_and_play_audio(audio_recorder):
     audio_bytes = audio_recorder()
     if audio_bytes:
@@ -105,7 +96,7 @@ def save_and_play_audio(audio_recorder):
     return None
 
 # Updated to call direct from transcription to chat inference.
-filename = save_and_play_audio(audio_recorder)
+filename = save_and_play_audio(audio_recorder) if record_audio else None
 if filename is not None:
     #if st.button("Transcribe"):
     transcription = transcribe_audio(openai.api_key, filename, "whisper-1")
@@ -143,7 +134,7 @@ def CompressXML(xml_text):
         if isinstance(elem.tag, str) and 'Comment' in elem.tag:
             elem.parent.remove(elem)
     return ET.tostring(root, encoding='unicode', method="xml")
-    
+
 def read_file_content(file,max_length):
     if file.type == "application/json":
         content = json.load(file)
@@ -174,7 +165,7 @@ def main():
         max_length = st.slider("File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
     with colupload:
         uploaded_file = st.file_uploader("Add a file for context:", type=["xml", "json", "html", "htm", "md", "txt"])
-    
+
     document_sections = deque()
     document_responses = {}
 
@@ -183,12 +174,12 @@ def main():
         document_sections.extend(divide_document(file_content, max_length))
 
     if len(document_sections) > 0:
-        
+
         if st.button("👁️ View Upload"):
             st.markdown("**Sections of the uploaded file:**")
             for i, section in enumerate(list(document_sections)):
                 st.markdown(f"**Section {i+1}**\n{section}")
-        
+
         st.markdown("**Chat with the model:**")
         for i, section in enumerate(list(document_sections)):
             if i in document_responses: