How to add streaming to my gradio chatbot when using Llama cpp pyhton with langchain

I am integrating Llama Cpp Python library to run huggingface LLMs on local, I am able to generate the output of text but i would like to add streaming to my chatbot so as soon as the generation is started gradio starts to get text.

Here is my code:

import os, torch, argparse
from threading import Thread
from typing import Optional

import gradio as gr
from llama_cpp import Llama
from src import quantize
from langchain import PromptTemplate, LLMChain
from langchain.llms.base import LLM
from langchain_community.llms import LlamaCpp
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain_core.prompts import PromptTemplate
from core import list_download_models, remove_dir, default_repo_id, read_config, update_config
from modelsui import create_models_ui
import sys

def snapshot_download_and_convert_to_gguf(repo_id):
gguf_model_path = quantize.quantize_model(repo_id)
return gguf_model_path

def init_llm_chain(model_path):
    llm = LlamaCpp(
        model_path=model_path,
        n_ctx=6000,
        n_batch=30,
        # temperature=0.9,
        # max_tokens=4095,
        n_parts=1,
        callback_manager=callback_manager, 
        verbose=True)

    template = """Question: {question}
        Answer: Let's work this out in a step by step way to be sure we have the right answer."""
    
    prompt = PromptTemplate.from_template(template)
    llm_chain = prompt | llm
    return llm_chain, llm

model_path = snapshot_download_and_convert_to_gguf(default_repo_id)
with gr.Blocks(css='style.css') as demo:
    with gr.Tab("Chat"):
        with gr.Row():
            with gr.Column(scale=1):
            with gr.Column(scale=4):
                with gr.Group():
                    chatbot = gr.Chatbot(elem_id="chatbot-container")
                    msg = gr.Textbox(label="Prompt")
                    stop = gr.Button("Stop")
    
    llm_chain, llm = init_llm_chain(model_path)
    
    def user(user_message, history):
        return "", history + [[user_message, None]]
    
    def bot(history):
        print("Question: ", history[-1][0])
        output = llm_chain.invoke({"question": history[-1][0]})
        print("stream:", output)
        history[-1][1] = ""
        for character in output:
            print(character)
            history[-1][1] += character
            yield history
    
    submit_event = msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(bot, chatbot, chatbot)

demo.queue()
demo.launch(server_name=args.host, server_port=args.port, share=args.share)

I have tried to create streaming chatbot but none of the methods works.