app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")

def predict(input, history=[]):
    # tokenize the new input sentence
    new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')

    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)

    # generate a response 
    history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()

    # convert the tokens to text, and then split the responses into lines
    response = tokenizer.decode(history[0]).split("<|endoftext|>")
    response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list
    return response, history

demo = gr.Blocks()

with demo:
    gr.Markdown("Start typing below and then click **Run** to see the output.")
    with gr.Row():
        inp = gr.Textbox(["text", "state"])
        out = gr.Textbox(["text", "state"])
    btn = gr.Button("Run")
    btn.click(fn=predict, inputs=inp, outputs=out)

demo.launch()