import gradio as gr
from transformers import pipeline
from datasets import Dataset, DatasetDict
import pandas as pd
import numpy as np
from transformers import RobertaTokenizerFast, RobertaForSequenceClassification,Trainer, TrainingArguments

model = RobertaForSequenceClassification.from_pretrained('Prakhar618/Gptdetect')
tokenizer = RobertaTokenizerFast.from_pretrained('Prakhar618/Gptdetect', max_length = 256)

def tokenize_function(examples):
    return tokenizer(examples['text'], padding=True, truncation=True,
        max_length=256)
    
def predict(text):
    # Convert test dataframe to Hugging Face dataset
    test_dataset = Dataset.from_pandas(pd.DataFrame(text,columns=['text']))

    # Apply the tokenization function to the train dataset
    train_dataset1 = test_dataset.map(tokenize_function, batched=True,)
    predictions, label_probs, _ = trainer.predict(train_dataset1)
    y_pred = np.argmax(predictions, axis=1)
    return y_pred
    
# Create Gradio interface
text_input = gr.Textbox(lines=7, label="Input Text", placeholder="Enter your text here...")
output_text = gr.Textbox(label="Predicted Sentiment")


test_args = TrainingArguments(
    do_train=False,
    do_predict=True,
    per_device_eval_batch_size = 2

)
trainer = Trainer(
    model=model,
    args=test_args,
)

iface = gr.Interface(fn=predict, inputs=text_input, outputs=output_text)
iface.launch(share=True)