Update app.py

app.py

@@ -190,6 +190,7 @@ def StreamLLMChatResponse(prompt):
     try:
         endpoint_url = API_URL
         hf_token = API_KEY
+        st.write('Running client ' + endpoint_url)
         client = InferenceClient(endpoint_url, token=hf_token)
         gen_kwargs = dict(
             max_new_tokens=512,
@@ -252,6 +253,7 @@ def transcribe_audio(openai_key, file_path, model):
     }
     with open(file_path, 'rb') as f:
         data = {'file': f}
+        st.write('STT transcript ' + OPENAI_API_URL)
         response = requests.post(OPENAI_API_URL, headers=headers, files=data, data={'model': model})
     if response.status_code == 200:
         st.write(response.json())
@@ -378,6 +380,8 @@ 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):
         collected_chunks.append(chunk)  
         chunk_message = chunk['choices'][0]['delta']