Update app.py

app.py

@@ -922,7 +922,7 @@ def read_file_content(file,max_length):
 
 # 11. Chat with GPT - Caution on quota - now favoring fastest AI pipeline STT Whisper->LLM Llama->TTS
 @st.cache_resource
-def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):
+def chat_with_model(prompt, document_section='', model_choice='gpt-4-0125-preview'):    # gpt-4-0125-preview	gpt-3.5-turbo
     model = model_choice
     conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
     conversation.append({'role': 'user', 'content': prompt})
@@ -933,9 +933,7 @@ def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):
     res_box = st.empty()
     collected_chunks = []
     collected_messages = []
-
-    st.write('LLM stream ' + 'gpt-3.5-turbo')
-    for chunk in openai.ChatCompletion.create(model='gpt-3.5-turbo', messages=conversation, temperature=0.5, stream=True):
+    for chunk in openai.ChatCompletion.create(model='gpt-4-0125-preview', messages=conversation, temperature=0.5, stream=True):   # gpt-4-0125-preview	gpt-3.5-turbo
         collected_chunks.append(chunk)  
         chunk_message = chunk['choices'][0]['delta']  
         collected_messages.append(chunk_message) 
@@ -953,7 +951,7 @@ def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):
     return full_reply_content
 
 @st.cache_resource
-def chat_with_file_contents(prompt, file_content, model_choice='gpt-3.5-turbo'):
+def chat_with_file_contents(prompt, file_content, model_choice='gpt-4-0125-preview'):  # gpt-4-0125-preview	gpt-3.5-turbo
     conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
     conversation.append({'role': 'user', 'content': prompt})
     if len(file_content)>0: