import gradio as gr
from transformers import GPT2LMHeadModel, GPT2Tokenizer
import torch

# Load model and tokenizer
model = GPT2LMHeadModel.from_pretrained("burman-ai/gpt2-chatbot")
tokenizer = GPT2Tokenizer.from_pretrained("burman-ai/gpt2-chatbot")
tokenizer.pad_token = tokenizer.eos_token

# Chat history list
chat_history = []

# Generate response
def chatbot(user_input):
    global chat_history
    chat_history.append(f"User: {user_input}")
    prompt = "\n".join(chat_history) + "\nBot:"
    
    inputs = tokenizer.encode(prompt, return_tensors="pt", truncation=True, max_length=512)
    outputs = model.generate(inputs, max_length=512, pad_token_id=tokenizer.eos_token_id, do_sample=True, top_k=50, top_p=0.95)
    
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    response = response.split("Bot:")[-1].strip().split("\n")[0]
    
    chat_history.append(f"Bot: {response}")
    return response

def clear_chat():
    global chat_history
    chat_history = []
    return "Chat cleared."

# UI
demo = gr.Interface(
    fn=chatbot,
    inputs=gr.Textbox(lines=2, placeholder="Type your message here..."),
    outputs="text",
    title="GPT-2 Chatbot",
    description="Chat with a fine-tuned GPT-2 model.",
    live=True
).queue()

demo.launch()