# from dotenv import load_dotenv
# from langchain import HuggingFaceHub, LLMChain
# from langchain import PromptTemplates
# import gradio

# load_dotenv()
# os.getenv('HF_API')

# hub_llm = HuggingFaceHub(repo_id='facebook/blenderbot-400M-distill')

# prompt = prompt_templates(
#     input_variable = ["question"],
#     template = "Answer is: {question}"
# )

# hub_chain = LLMChain(prompt=prompt, llm=hub_llm, verbose=True)





# Sample code for AI language model interaction
# from transformers import GPT2Tokenizer, GPT2LMHeadModel
# import gradio


# def simptok(data):
#     # Load pre-trained model and tokenizer (using the transformers library)
#     model_name = "gpt2"
#     tokenizer = GPT2Tokenizer.from_pretrained(model_name)
#     model = GPT2LMHeadModel.from_pretrained(model_name)
    
#     # User input
#     user_input = data
    
#     # Tokenize input
#     input_ids = tokenizer.encode(user_input, return_tensors="pt")
    
#     # Generate response
#     output = model.generate(input_ids, max_length=50, num_return_sequences=1)
#     response = tokenizer.decode(output[0], skip_special_tokens=True)
#     return response


# def responsenew(data):
#     return simptok(data)


from hugchat import hugchat
import gradio as gr
import time

# Create a chatbot connection
chatbot = hugchat.ChatBot(cookie_path="cookies.json")

# New a conversation (ignore error)
id = chatbot.new_conversation()
chatbot.change_conversation(id)


def get_answer(data):
    return chatbot.chat(data)

gradio_interface = gr.Interface(
  fn = get_answer,
  inputs = "text",
  outputs = "text"
)
gradio_interface.launch()

# gradio_interface = gradio.Interface(
#   fn = responsenew,
#   inputs = "text",
#   outputs = "text"
# )
# gradio_interface.launch()