app.py

import requests
import streamlit as st
from llama_cpp import Llama
import os

print(os.getcwd())
#===================Download Model==============================
url = "https://huggingface.co./ngxson/DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-abliterated-Q4_K_M.gguf?download=true"
file_name = "DeepSeek-R1-Distill-Qwen-7B-abliterated-Q4_K_M.gguf"

response = requests.get(url, stream=True)

if response.status_code == 200:
    with open(file_name, "wb") as file:
        for chunk in response.iter_content(chunk_size=8192):
            file.write(chunk)
    print("Download complete:", file_name)
else:
    print("Failed to download. Status code:", response.status_code)

#==================================Streamlit App====================================
# Set Streamlit page config
st.set_page_config(page_title="Llama Chatbot", page_icon="🤖")

# Model path (Ensure the model is in the correct directory)
MODEL_PATH = file_name

# Check if model exists, else download it
if not os.path.exists(MODEL_PATH):
    st.warning("Model not found! Please download it first.")
    st.stop()

# Load Llama model
st.session_state["llm"] = Llama(model_path=MODEL_PATH)

# Streamlit UI
st.title("🤖 Llama GGUF Chatbot")

if "messages" not in st.session_state:
    st.session_state["messages"] = []

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

# User input
user_input = st.chat_input("Type your message here...")

if user_input:
    # Display user message
    st.session_state["messages"].append({"role": "user", "content": user_input})
    with st.chat_message("user"):
        st.markdown(user_input)

    # Generate response
    with st.spinner("Thinking..."):
        response = st.session_state["llm"](user_input)["choices"][0]["text"]

    # Display bot response
    st.session_state["messages"].append({"role": "assistant", "content": response})
    with st.chat_message("assistant"):
        st.markdown(response)