app.py

from flask import Flask, request
from transformers import RobertaForSequenceClassification, RobertaTokenizer, RobertaConfig
import torch
import gradio as gr
import os
import re
app = Flask(__name__)

ACCESS_TOKEN = os.environ["ACCESS_TOKEN"]
config = RobertaConfig.from_pretrained("PirateXX/ChatGPT-Text-Detector", use_auth_token= ACCESS_TOKEN)
model = RobertaForSequenceClassification.from_pretrained("PirateXX/ChatGPT-Text-Detector", use_auth_token= ACCESS_TOKEN, config = config)

model_name = "roberta-base"
tokenizer = RobertaTokenizer.from_pretrained(model_name, map_location=torch.device('cpu'))

# function to break text into an array of sentences
def text_to_sentences(text):
    return re.split(r'[.!?]', text)

# function to concatenate sentences into chunks of size 600 or less
def chunks_of_600(text, chunk_size=600):
    sentences = text_to_sentences(text)
    chunks = []
    current_chunk = ""
    for sentence in sentences:
        if len(current_chunk + sentence) <= chunk_size:
            current_chunk += sentence
        else:
            chunks.append(current_chunk)
            current_chunk = sentence
    chunks.append(current_chunk)
    return chunks
    
def predict(query, device="cpu"):
    tokens = tokenizer.encode(query)
    all_tokens = len(tokens)
    tokens = tokens[:tokenizer.model_max_length - 2]
    used_tokens = len(tokens)
    tokens = torch.tensor([tokenizer.bos_token_id] + tokens + [tokenizer.eos_token_id]).unsqueeze(0)
    mask = torch.ones_like(tokens)

    with torch.no_grad():
        logits = model(tokens.to(device), attention_mask=mask.to(device))[0]
        probs = logits.softmax(dim=-1)

    fake, real = probs.detach().cpu().flatten().numpy().tolist()
    return real

def findRealProb(text):
    chunksOfText = (chunks_of_600(text))
    results = []
    for chunk in chunksOfText:
        output = predict(chunk)
        results.append([output, len(chunk)])
    
    ans = 0
    for prob, length in results:
        ans = ans + prob*length
    realProb = ans/len(text)
    print(results)
    return {"Real": realProb, "Fake": 1-realProb}

demo = gr.Interface(
        fn=findRealProb, 
        inputs=gr.Textbox(placeholder="Copy and paste here..."), 
        outputs="label",
        interpretation="default",
        examples=["Cristiano Ronaldo is a Portuguese professional soccer player who currently plays as a forward for Manchester United and the Portugal national team. He is widely considered one of the greatest soccer players of all time, having won numerous awards and accolades throughout his career. Ronaldo began his professional career with Sporting CP in Portugal before moving to Manchester United in 2003. He spent six seasons with the club, winning three Premier League titles and one UEFA Champions League title. In 2009, he transferred to Real Madrid for a then-world record transfer fee of $131 million. He spent nine seasons with the club, winning four UEFA Champions League titles, two La Liga titles, and two Copa del Rey titles. In 2018, he transferred to Juventus, where he spent three seasons before returning to Manchester United in 2021. He has also had a successful international career with the Portugal national team, having won the UEFA European Championship in 2016 and the UEFA Nations League in 2019.", "One rule of thumb which applies to everything that we do - professionally and personally : Know what the customer want and deliver. In this case, it is important to know what the organisation what from employee. Connect the same to the KRA. Are you part of a delivery which directly ties to the larger organisational objective. If yes, then the next question is success rate of one’s delivery. If the KRAs are achieved or exceeded, then the employee is entitled for a decent hike."])

demo.launch(show_api=False)