streamlit_app_test.py

import streamlit as st
import replicate
import os
import logging
# App title
st.set_page_config(page_title="🦙💬 Llama 2 Chatbot")

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Create a Logger instance
logger = logging.getLogger(__name__)
# Replicate credentials

with st.sidebar:
    st.title("🦙💬 Llama 2 Chatbot")
    if 'REPLICATE_API_TOKEN' in st.secrets:
        st.success('API key already provided' ,icon='✅')
        replicate_api = st.secrets['REPLICATE_API_TOKEN']
    else:
        replicate_api = st.text_input('Enter Replicate API Token:', type='password')
        if not (replicate_api.startswith('r8_') and len(replicate_api) == 40):
            st.warning('Please enter your credentials!', icon='⚠️')
        else:
            st.success('Proceed to entering your prompt message!' ,  icon ='👉')

    temperature = st.sidebar.slider('temperature', min_value=0.01, max_value=5.0, value=0.1, step=0.01)
    top_p = st.sidebar.slider('top_p', min_value=0.01, max_value=1.0, value=0.9, step=0.01)
    max_length = st.sidebar.slider('max_length', min_value=64, max_value=4096, value=512, step=8)

    st.markdown('📖 If you enjoyed this show some love at my [Linkedin Profile](https://www.linkedin.com/in/wolfsbane9513/) ')
os.environ['REPLICATE_API_TOKEN'] = replicate_api

# Store the LLM Generated response

if "messages" not in st.session_state.keys():
    st.session_state.messages = [{"role":"assistant","content": "How may I assist you today?"}]

# Display or clear chat message

for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.write(message["content"])

def clear_chat_history():
    st.session_state.messages = [{"role":"assistant","content": "How may I assist you today?"}]
st.sidebar.button('Clear Chat History',on_click=clear_chat_history)


# Function for generating LLaMA2 response
# Refactored from <https://github.com/a16z-infra/llama2-chatbot>

def generate_llama2_response(prompt_input):
    #string_dialogue = "You are a helpful assistant.You do not respond as 'User' or pretend to  be a 'User'. You only respond once as 'Assistant'."
    string_dialogue = "You are a helpful assistant. You do not respond as 'User' or pretend to  be a 'User'. You only respond once as 'Assistant'."
    for dict_message in st.session_state.messages:
        if dict_message["role"] == "user":
            string_dialogue += "User" + dict_message["content"] + "\\n\\n"
        else:
            string_dialogue += "Assistant" + dict_message["content"] + "\\n\\n"
    logger.info(f"string dialogue{string_dialogue} - {prompt_input}")
    output = replicate.run('a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5',
                           input = {"prompt": f"{string_dialogue}{prompt_input} Assistant: ",
                                    "temperature":temperature, "top_p":top_p, "max_length":max_length, "repetition_penalty":1})
   
    return output

# User provided prompt
if prompt := st.chat_input(disabled= not replicate_api):
    st.session_state.messages.append({"role":"user","content":prompt})
    with st.chat_message("user"):
        st.write(prompt) 

# Generate a new response if last message is not from assistant

if st.session_state.messages[-1]["role"] != "assistant":
    with st.chat_message("assistant"):
        with st.spinner("Thinking..."):
            response = generate_llama2_response(prompt)
            placeholder = st.empty()
            full_response = ''
            for item in response:
                full_response += item
                placeholder.markdown(full_response)
            placeholder.markdown(full_response)
        logger.info(f"user prompt and api response {prompt},{full_response}")
        message = {"role":"assistant","content": full_response}
        st.session_state.messages.append(message)