Update app.py

app.py

@@ -191,6 +191,7 @@ def StreamLLMChatResponse(prompt):
         endpoint_url = API_URL
         hf_token = API_KEY
         client = InferenceClient(endpoint_url, token=hf_token)
+        st.write('Opened HF hub Inference Client for endpoint URL: ' + endpoint_url)
         gen_kwargs = dict(
             max_new_tokens=512,
             top_k=30,
@@ -251,7 +252,8 @@ def transcribe_audio(openai_key, file_path, model):
         "Authorization": f"Bearer {openai_key}",
     }
     with open(file_path, 'rb') as f:
-        data = {'file': f}
+        data = {'file': f
+        st.write('Transcribe Audio is Posting request to ' + 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())
@@ -377,7 +379,8 @@ def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
     report = []
     res_box = st.empty()
     collected_chunks = []
-    collected_messages = []
+    collected_messages = 
+    st.write('Running prompt with ' + model)
     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']  
@@ -451,6 +454,7 @@ def txt2chunks(text):
 # Vector Store using FAISS
 @st.cache_resource
 def vector_store(text_chunks):
+    st.write('Retrieving OpenAI embeddings')
     embeddings = OpenAIEmbeddings(openai_api_key=key)
     return FAISS.from_texts(texts=text_chunks, embedding=embeddings)
 
@@ -528,7 +532,8 @@ headers = {
 #@st.cache_resource
 def query(filename):
     with open(filename, "rb") as f:
-        data = f.read()
+        data = f.read
+    st.write('Posting request to model ' + API_URL_IE)
     response = requests.post(API_URL_IE, headers=headers, data=data)
     return response.json()