import gradio as gr
from huggingface_hub import InferenceClient
from datasets import load_dataset
from transformers import BartTokenizer, BartForSequenceClassification, Trainer, TrainingArguments

import pandas as pd
from datasets import load_dataset, DatasetDict

dataset = load_dataset("csv", data_files="FAQ_Appliance_Store_FR.csv")

split_dataset = dataset["train"].train_test_split(test_size=0.2)

dataset = DatasetDict({
    "train": split_dataset["train"],
    "test": split_dataset["test"]
})


# Load pretrained model and tokenizer
model = BartForSequenceClassification.from_pretrained("facebook/bart-large-mnli")
tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-mnli")

# Tokenize the dataset
def preprocess_function(examples):
    return tokenizer(examples['question'], examples['answer'], truncation=True, padding="max_length")

tokenized_datasets = dataset.map(preprocess_function, batched=True)

# Define training arguments
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    save_strategy="epoch",
    per_device_train_batch_size=8,
    num_train_epochs=3,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["test"],
)

trainer.train()
model.save_pretrained("./my_model")
tokenizer.save_pretrained("./my_model")


"""
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()