app.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import streamlit as st

torch.random.manual_seed(0)

model = AutoModelForCausalLM.from_pretrained(
     "microsoft/Phi-3-mini-4k-instruct",
    #"microsoft/Phi-3-mini-128k-instruct", 
    device_map="cpu", 
    torch_dtype="auto", 
    trust_remote_code=True, 
)
tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")    #("microsoft/Phi-3-mini-128k-instruct")

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)

generation_args = {
    "max_new_tokens": 500,
    "return_full_text": False,
    "temperature": 0.0,
    "do_sample": False,
}




st.title("💬 Chatbot")
st.caption("🚀 A streamlit chatbot powered by Microsoft Phi-3-mini")

# Initialize chat history
if 'messages' not in st.session_state:
    st.session_state['messages'] = [] #[{"role": "assistant", "content": "How can I help you?"}]

# Display chat messages from history on app rerun
for messasge in st.session_state.messages:
    st.chat_message(messasge["role"]).write(messasge["content"])

# React to user input
if prompt := st.chat_input():
    
     # Display user message in chat message container
    st.chat_message("user").write(prompt)
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})

    messages=st.session_state.messages

    ##Get response to the message using client
    output = pipe(messages, **generation_args)

    msg = output[0]['generated_text']
    
     # Display assistant response in chat message container
    st.chat_message("assistant").write(msg)

    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": msg})