import gradio as gr
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


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


# import gradio as gr

# gr.load("models/meta-llama/Meta-Llama-3.1-70B-Instruct").launch()

# import streamlit as st
# from transformers import AutoTokenizer, AutoModelForCausalLM

# # Load model directly
# tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
# model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")

# # Initialize chat history
# if "chat_history" not in st.session_state:
#     st.session_state.chat_history = []

# # Display chat history
# for chat in st.session_state.chat_history:
#     st.write(f"User: {chat['user']}")
#     st.write(f"Response: {chat['response']}")

# # Get user input
# user_input = st.text_input("Enter your message:")

# # Generate response
# if st.button("Send"):
#     inputs = tokenizer(user_input, return_tensors="pt")
#     outputs = model.generate(**inputs)
#     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
#     st.session_state.chat_history.append({"user": user_input, "response": response})
#     st.write(f"Response: {response}")