Update app.py

app.py

@@ -96,6 +96,7 @@ def add_witty_humor_buttons():
 
 
 # Function to Stream Inference Client for Inference Endpoint Responses
+@st.cache_resource
 def StreamLLMChatResponse(prompt):
 
     try:
@@ -174,8 +175,7 @@ def StreamLLMChatResponse(prompt):
     except:
         st.write('DromeLlama is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')
 
-
-
+@st.cache_resource
 def query(payload):
     response = requests.post(API_URL, headers=headers, json=payload)
     st.markdown(response.json())
@@ -191,6 +191,7 @@ def generate_filename(prompt, file_type):
     safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:90]
     return f"{safe_date_time}_{safe_prompt}.{file_type}"
 
+@st.cache_resource
 def transcribe_audio(openai_key, file_path, model):
     openai.api_key = openai_key
     OPENAI_API_URL = "https://api.openai.com/v1/audio/transcriptions"
@@ -224,6 +225,7 @@ def save_and_play_audio(audio_recorder):
         return filename
     return None
 
+@st.cache_resource
 def create_file(filename, prompt, response, should_save=True):
     if not should_save:
         return
@@ -248,6 +250,7 @@ def truncate_document(document, length):
 def divide_document(document, max_length):
     return [document[i:i+max_length] for i in range(0, len(document), max_length)]
 
+@st.cache_resource
 def get_table_download_link(file_path):
     with open(file_path, 'r') as file:
         try:
@@ -282,6 +285,7 @@ def CompressXML(xml_text):
             elem.parent.remove(elem)
     return ET.tostring(root, encoding='unicode', method="xml")
     
+@st.cache_resource
 def read_file_content(file,max_length):
     if file.type == "application/json":
         content = json.load(file)
@@ -303,6 +307,7 @@ def read_file_content(file,max_length):
     else:
         return ""
 
+@st.cache_resource
 def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
     model = model_choice
     conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
@@ -331,6 +336,7 @@ def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
     st.write(time.time() - start_time)
     return full_reply_content
 
+@st.cache_resource
 def chat_with_file_contents(prompt, file_content, model_choice='gpt-3.5-turbo'):
     conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
     conversation.append({'role': 'user', 'content': prompt})
@@ -362,6 +368,7 @@ def extract_file_extension(file):
     else:
         raise ValueError(f"Unable to extract file extension from {file_name}")
 
+@st.cache_resource
 def pdf2txt(docs):
     text = ""
     for file in docs:
@@ -383,10 +390,12 @@ def txt2chunks(text):
     text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len)
     return text_splitter.split_text(text)
 
+@st.cache_resource
 def vector_store(text_chunks):
     embeddings = OpenAIEmbeddings(openai_api_key=key)
     return FAISS.from_texts(texts=text_chunks, embedding=embeddings)
 
+@st.cache_resource
 def get_chain(vectorstore):
     llm = ChatOpenAI()
     memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
@@ -419,6 +428,7 @@ def divide_prompt(prompt, max_length):
     chunks.append(' '.join(current_chunk))
     return chunks
 
+@st.cache_resource
 def create_zip_of_files(files):
     zip_name = "all_files.zip"
     with zipfile.ZipFile(zip_name, 'w') as zipf:
@@ -426,6 +436,7 @@ def create_zip_of_files(files):
             zipf.write(file)
     return zip_name
 
+@st.cache_resource
 def get_zip_download_link(zip_file):
     with open(zip_file, 'rb') as f:
         data = f.read()
@@ -440,6 +451,7 @@ headers = {
 	"Content-Type": "audio/wav"
 }
 
+@st.cache_resource
 def query(filename):
     with open(filename, "rb") as f:
         data = f.read()
@@ -454,6 +466,7 @@ def generate_filename(prompt, file_type):
     return f"{safe_date_time}_{safe_prompt}.{file_type}"
 
 # 10. Audio recorder to Wav file:
+@st.cache_resource
 def save_and_play_audio(audio_recorder):
     audio_bytes = audio_recorder()
     if audio_bytes:
@@ -506,14 +519,7 @@ def main():
     openai.api_key = os.getenv('OPENAI_KEY')
     menu = ["txt", "htm", "xlsx", "csv", "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'))
-    
-    #filename = save_and_play_audio(audio_recorder)
-    #if filename is not None:
-    #    transcription = transcribe_audio(key, filename, "whisper-1")
-    #    st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
-    #    filename = None
-        
+    model_choice = st.sidebar.radio("Select Model:", ('gpt-3.5-turbo', 'gpt-3.5-turbo-0301'))        
     user_prompt = st.text_area("Enter prompts, instructions & questions:", '', height=100)
     collength, colupload = st.columns([2,3])  # adjust the ratio as needed
     with collength: