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

# Load model and tokenizer
model_name = "microsoft/DialoGPT-medium"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Store conversation history
chat_history_ids = None

def respond(message, history):
    global chat_history_ids

    # Encode user input
    new_input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')

    # Append to chat history
    if chat_history_ids is not None:
        bot_input_ids = torch.cat([chat_history_ids, new_input_ids], dim=-1)
    else:
        bot_input_ids = new_input_ids

    # Generate response
    chat_history_ids = model.generate(
        bot_input_ids,
        max_length=1000,
        pad_token_id=tokenizer.eos_token_id,
        do_sample=True,
        top_k=100,
        top_p=0.7,
        temperature=0.8
    )

    # Decode response
    response = tokenizer.decode(
        chat_history_ids[:, bot_input_ids.shape[-1]:][0],
        skip_special_tokens=True
    )

    return response

# Create Gradio interface
demo = gr.ChatInterface(
    fn=respond,
    title="Dialogue System using DialoGPT",
    description="A simple conversational AI built with HuggingFace Transformers and Gradio."
)

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