import gradio as gr
from huggingface_hub import InferenceClient
import pandas as pd
import torch

"""
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]],
    max_tokens = 2048,
    temperature = 0.7,
    top_p = 0.95,
):
    messages = [{"role": "system", "content": "You are a moslem bot that always give answer based on quran and hadith!"}]
    df = pd.read_csv("moslem-bot-reference.csv")

    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": "I want you to answer strictly based on quran and hadith"})
    messages.append({"role": "assistant", "content": "I'd be happy to help! Please go ahead and provide the sentence you'd like me to analyze. Please specify whether you're referencing a particular verse or hadith (Prophetic tradition) from the Quran or Hadith, or if you're asking me to analyze a general statement."})

    for index, row in df.iterrows():
        messages.append({"role": "user", "content": row['user']})
        messages.append({"role": "assistant", "content": row['assistant']})

    selected_dfs = torch.load('selected_dfs.sav', map_location=torch.device('cpu'))
    for df in selected_dfs:
        df = df.dropna()
        df = df.sample(df.shape[0].div(10))
        for index, row in df.iterrows():
            messages.append({"role": "user", "content": row['Column1.question']})
            messages.append({"role": "assistant", "content": row['Column1.answer']})
    
    messages.append({"role": "user", "content": message})
    print(messages)

    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.Slider(minimum=1, maximum=2048, value=2048, 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)",
        ),
    ],
    examples=[
                ["Why is men created?"],
                ["How is life after death?"],
                ["Please tell me about superstition!"],
                ["How moses defeat pharaoh?"],
                ["Please tell me about inheritance law in Islam!"],
                ["A woman not wear hijab"],
                ["Worshipping God beside Allah"],
                ["Blindly obey a person"],
                ["Make profit from lending money to a friend"],
            ],
)


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