app.py

import gradio as gr
import os

os.system('pip install transformers torch')

from transformers import GPT2LMHeadModel, GPT2Tokenizer

# Load the pre-trained model and tokenizer
model_name = "microsoft/DialoGPT-small"
model = GPT2LMHeadModel.from_pretrained(model_name)
tokenizer = GPT2Tokenizer.from_pretrained(model_name)

# Initial system prompt and chat history
system_prompt = "You are a helpful assistant."
chat_history = system_prompt

def generate_response(prompt, max_length=50, temperature=0.8):
    global chat_history
    input_text = chat_history + " User: " + prompt
    input_ids = tokenizer.encode(input_text, return_tensors="pt")
    output_ids = model.generate(input_ids, max_length=max_length, temperature=temperature, num_return_sequences=1)
    response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
    
    # Update chat history
    chat_history += f" User: {prompt} Assistant: {response}"
    
    return response

iface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(),
    outputs="text",
)

iface.launch()