How to implement chatbot streaming with a function

Beginners
1

HI everyone.

I am trying to build a basicchatbot with streaming.
from the documentation we have the following code.

import gradio as gr
import random
import time

with gr.Blocks() as demo:
    chatbot = gr.Chatbot()
    msg = gr.Textbox()
    clear = gr.Button("Clear")

    def respond(message, chat_history):
        bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
        chat_history.append((message, bot_message))
        time.sleep(2)
        return "", chat_history

    msg.submit(respond, [msg, chatbot], [msg, chatbot])
    clear.click(lambda: None, None, chatbot, queue=False)

if __name__ == "__main__":
    demo.launch()```

and I wrote this function

import os
os.environ["OPENAI_API_KEY"] = '  dsdsds'

from pathlib import Path
from llama_index import LLMPredictor, GPTVectorStoreIndex, PromptHelper, ServiceContext
from llama_index import StorageContext, load_index_from_storage
from langchain.chat_models import ChatOpenAI
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler


llm_predictor = LLMPredictor(
    llm=ChatOpenAI(
        streaming=True,
        callbacks=[StreamingStdOutCallbackHandler()],
        temperature=0.7,
        model_name="gpt-3.5-turbo",
        max_tokens=1000
    )
)


max_input_size = 4096
max_chunk_overlap = 0.2
chunk_size_limit = 60
num_outputs = 1000
prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)

service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor)
storage_context = StorageContext.from_defaults(persist_dir="./storage")

index = load_index_from_storage(storage_context, service_context=service_context)

question = 'how many times has my son watched the curious george movie?'
query_engine = index.as_query_engine()
response = query_engine.query(question)
#print(response)

How can I combine them together to make a chatbot with Streaming?

I tried the following code


import os
os.environ["OPENAI_API_KEY"] = 'dsdsdsddsdsd'

from pathlib import Path
from llama_index import LLMPredictor, GPTVectorStoreIndex, PromptHelper, ServiceContext
from llama_index import StorageContext, load_index_from_storage
from langchain.chat_models import ChatOpenAI
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
import gradio as gr
import random
import time

llm_predictor = LLMPredictor(
    llm=ChatOpenAI(
        streaming=True,
        callbacks=[StreamingStdOutCallbackHandler()],
        temperature=0.7,
        model_name="gpt-3.5-turbo",
        max_tokens=2000
    ))
    

max_input_size = 4096
max_chunk_overlap = 0.2
chunk_size_limit = 600
num_outputs = 2000
prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor)
storage_context = StorageContext.from_defaults(persist_dir="./storage")
index = load_index_from_storage(storage_context, service_context=service_context)
query_engine = index.as_query_engine()

with gr.Blocks() as demo:
    chatbot = gr.Chatbot()
    msg = gr.Textbox()
    clear = gr.Button("Clear")

    def user(user_message, history):
        return gr.update(value="", interactive=False), history + [[user_message, None]]

    def bot(history):
        bot_message = query_engine.query(history[len(history)-1][0])
        history[-1][1] = ""
        for character in bot_message:
            history[-1][1] += character
            time.sleep(0.05)
            yield history

    response = msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
        bot, chatbot, chatbot
    )
    response.then(lambda: gr.update(interactive=True), None, [msg], queue=False)
    clear.click(lambda: None, None, chatbot, queue=False)

demo.queue()
demo.launch()

but it says
TypeError: ‘Response’ object is not iterable

Any kind or hint is greatly appreciated