app.py

##### PREPARATIONS

# libraries
import datetime
import json
import os
import sys
import requests
import streamlit as st


MIN_TEXT_LEN = 300
MAX_TEXT_LEN = 32410
API_URL = "http://checkgpt.app:8880/predict"

# download with progress bar
mybar = None


def show_progress(block_num, block_size, total_size):
    global mybar
    if mybar is None:
        mybar = st.progress(0.0)
    downloaded = block_num * block_size / total_size
    if downloaded <= 1.0:
        mybar.progress(downloaded)
    else:
        mybar.progress(1.0)


##### CONFIG

# page config
st.set_page_config(page_title="CheckGPT - ChatGPT and other big LM detection engine",
                   page_icon=":books:",
                   layout="centered",
                   initial_sidebar_state="collapsed",
                   menu_items=None)

##### HEADER

# title
st.title('CheckGPT - AI-written text detect')


# description
st.write(
    'CheckGPT is a neural network to check if text is generated by '\
                           'big AI LMs (like ChatGPT, GPT3, GPT2, BLOOM, You.com AI and etc).')
st.write('Currently supported languages are: [\'en\'].')
st.write("Use our web app and RestAPI at https://checkgpt.app.\n")
st.write('Already telegram bot is available at: https://t.me/chatgpt_bot.')
st.write('To connect with authors please write to: https://t.me/uberwow | https://CheckGPT.app')


##### PARAMETERS

# title
st.header('Check for AI generated text?')


# input text
input_text = st.text_area('Which text would you like to check?', '')

##### MODELING

# compute readability
if st.button('Check'):

    # compute predictions
    with st.spinner('Computing prediction...'):

        # compute prediction
        if len(input_text) < MIN_TEXT_LEN:
            st.error(f'😐 Minimal text length: {MIN_TEXT_LEN} characters. Your text is {len(input_text)} characters.\n'
                     f'The longer the text, the higher the accuracy.\n')
        elif len(input_text) > MAX_TEXT_LEN:
            st.error('⚠ Seems we got too big input! Please try again with smaller text!')
        else:
            # make json-valid request
            formatted_req = {"text": input_text}
            jsoned_req = json.dumps(formatted_req)

            # try to send request to api
            try:
                r = requests.post(API_URL, data=jsoned_req, headers={'Content-Type': 'application/json'})
                answer = json.loads(r.text)
            except:
                st.error('Some backend RESTAPI error. Please try later!')
                print("Some error while sending POST request to RESTAPI. Please check your connection and try again!")

            # extract data from json anwser
            result = int(answer["result"])
            human_score = round(float(answer["human_score"]), 4)
            chatgpt_score = round(float(answer["ChatGPT_score"]), 4)
            req_id = answer["request_id"]
            execution_time = answer["execution_time"]

            # clear memory
            #gc.collect()

            # print output
            st.metric(label="Prediction", value=result)

            st.write(f"✅ Total score (AI signs):\n\n    Human-like score: {human_score}%\n    ChatGPT-like score: {chatgpt_score}%\n")
            st.write(f"⚙ Information:\n\n    Execution time: {execution_time} sec.\n    Request ID: {req_id}\n    Prediction: ", result)
            if result == 0:
                st.success(f"👨 Seems like text was written by the human ({human_score}%)!")

            if result == 1:
                st.success(f"🤖 Seems to be a ChatGPT generated text! ({chatgpt_score}%)")

            # save log
            with open('logs/' + 'text_' + str(
                    result) + '_' + '{:%Y-%m-%d_%H-%M-%S}'.format(
                    datetime.datetime.now()) + '.log', 'w', encoding="utf-8") as file:
                file.write(input_text)



##### DOCUMENTATION

# header
st.header('More information')

# models
with st.expander('Read about the models'):
    st.write(
        'For ChatGPT generated content detection, we are using statistical and heuristical methods, perplexity, '
        'entropy, '
        'coherence and consistency of the text and some our personal know-how ;).')

# metric

##### CONTACT

# header
st.header("Contact")

# website link

# copyright
st.text("All rights reserved © 2023 | https://t.me/uberwow | https://CheckGPT.app")