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

# Initialize the model and tokenizer
model_name = "microsoft/DialoGPT-medium"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

chat_history_ids = None

def chat(message, history):
    global chat_history_ids
    
    message = str(message)
    history = str(history)

    # Encode the new user input, add the eos_token, and return a tensor in PyTorch
    new_user_input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')

    # Append the new user input tokens to the chat history
    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if chat_history_ids is not None else new_user_input_ids

    # Generate a response while limiting the total chat history to 1000 tokens
    chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)

    # Decode and return the bot's response
    response = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    return response
    

# Create and launch the Gradio interface
iface = gr.ChatInterface(
    fn=chat,
    title="UrFriendly Chatbot",
    theme="soft",
    description="Chat with me!",
    examples=[
        "Howdy!",
        "Tell me a joke.", 
        "Explain quantum computing in simple terms.", 
        "How are you?", 
        "What is an exponent in mathematics?",
        "Does money buy happiness?"
    ]
)

iface.launch()