app.py

from openai import OpenAI
import streamlit as st
import os
from datetime import datetime

# Load API key securely
API_KEY = os.getenv("NV_API_KEY", "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")
if not API_KEY:
    st.error("API key is missing! Please set NV_API_KEY as an environment variable.")
    st.stop()

client = OpenAI(
    base_url="https://integrate.api.nvidia.com/v1",
    api_key=API_KEY
)

st.title("Nemotron 4 340B")

# Sidebar content
with st.sidebar:
    st.markdown("This is a basic chatbot. Ask anything. The app is supported by Nazmul Hasan Nihal.")
    if st.button("Clear Session"):
        st.session_state.clear()
    st.write(f"Copyright 2023-{datetime.now().year} Present Nazmul Hasan Nihal")

# Initialize session state
if "openai_model" not in st.session_state:
    st.session_state['openai_model'] = "invidia/nemotron_4"

if "messages" not in st.session_state:
    st.session_state.messages = [{"role": "system", "content": "You are a helpful assistant."}]

# Display previous messages
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# Handle user input
if prompt := st.chat_input("What is up"):
    st.session_state.messages.append({"role": "user", "content": prompt})
    with st.chat_message("user"):
        st.markdown(prompt)

    # Assistant response
    with st.chat_message("assistant"):
        with st.spinner("The assistant is thinking... Please wait."):
            try:
                # Generate response
                stream = client.chat.completions.create(
                    model=st.session_state["openai_model"],
                    messages=st.session_state.messages,
                    temperature=0.5,
                    top_p=0.7,
                    max_tokens=1024,
                    stream=True,
                )
                response_chunks = []
                for chunk in stream:
                    if chunk.choices[0].delta.content:
                        response_chunks.append(chunk.choices[0].delta.content)
                response = "".join(response_chunks)
                st.markdown(response)

                # Save assistant message
                st.session_state.messages.append({"role": "assistant", "content": response})

            except Exception as e:
                st.error(f"An error occurred: {e}")