app.py

import gradio as gr
from main import main
import json
import subprocess

def installChrome(): 
    subprocess.run(['apt-get', 'update'])
    subprocess.run(['apt-get', 'install', '-y', 'wget', 'unzip'])
    subprocess.run(['wget', 'https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb'])
    subprocess.run(['apt-get', 'install', '-y', './google-chrome-stable_current_amd64.deb'])
    subprocess.run(['rm', 'google-chrome-stable_current_amd64.deb'])
    subprocess.run(['apt-get', 'clean'])


def rexplore_summarizer(url, title, id, citation, access_key):
    response = json.loads(main(url, title, id, citation, access_key))
    data = json.dumps(response, ensure_ascii=False, indent=4)
    if response["mindmap_status"] != "success":
        mindmap = "error"
    else:
        mindmap = response["mindmap"]
    if response["summary_status"] != "success":
        summary = "error"
    else:
        summary = response["summary"]
    return data, summary, mindmap

def clear_everything(url, title, id, citation, access_key, raw_data, summary, mindmap):
    return None, None, None, None, None, None

theme = gr.themes.Soft(
    primary_hue="purple",
    secondary_hue="cyan",
    neutral_hue="slate",
    font=[
        gr.themes.GoogleFont("Syne"), 
        gr.themes.GoogleFont("Poppins"), 
        gr.themes.GoogleFont("Poppins"), 
        gr.themes.GoogleFont("Poppins")
    ],
)

with gr.Blocks(theme=theme, title="ReXplore Summarizer", fill_height=True) as app:
    gr.HTML(
        value ="""
        <h1 style="text-align: center;">ReXplore Summarizer <p style="text-align: center;">Designed and Developed by <a href="https://raannakasturi.eu.org" target="_blank" rel="nofollow noreferrer external">Nayan Kasturi</a></p> </h1>
        <p style="text-align: center;">This app uses a hybrid approach to summarize PDF documents based on CPU as well as GPU.</p>
        <p style="text-align: center;">The app uses traditional methodologies such as TextRank, LSA, Luhn algorithms as well as large language model (LLM) to generate summaries as well as mindmaps.</p>
        <p style="text-align: center;">The summarization process can take some time depending on the size of the text corpus and the complexity of the content.</p>
        """)
    with gr.Row():
        with gr.Column():
            url = gr.Textbox(label="PDF URL", placeholder="Paste the PDF URL here")
            title = gr.Textbox(label="Title", placeholder="Enter the title Research Paper")
            id = gr.Textbox(label="DOI/arXiv ID", placeholder="Enter the DOI or arXiv ID of the Research Paper")
            citation = gr.Textbox(label="Citation", placeholder="Enter the citation of the Research Paper")
            access_key = gr.Textbox(label="Access Key", placeholder="Enter the Access Key", type="password")
            with gr.Row():
                clear_btn = gr.Button(value="Clear", variant="stop")
                summarize_btn = gr.Button(value="Summarize", variant="primary")
        raw_data = gr.TextArea(label="Raw Data", placeholder="The generated raw data will be displayed here", lines=7, interactive=False, show_copy_button=True)
    with gr.Row():
        summary = gr.TextArea(label="Summary", placeholder="The generated summary will be displayed here", lines=7, interactive=False, show_copy_button=True)
        mindmap = gr.TextArea(label="Mindmap", placeholder="The generated mindmap will be displayed here", lines=7, interactive=False, show_copy_button=True)
    summarize_btn.click(
        rexplore_summarizer,
        inputs=[url, title, id, citation, access_key],
        outputs=[raw_data, summary, mindmap],
        concurrency_limit=25,
        scroll_to_output=True,
        show_api=True,
        api_name="rexplore_summarizer",
        show_progress="full",
    )
    clear_btn.click(clear_everything, inputs=[url, title, id, citation, raw_data, summary, mindmap, access_key], outputs=[url, id, raw_data, summary, mindmap, access_key], show_api=False)

installChrome()
app.queue(default_concurrency_limit=25).launch(show_api=True, ssr_mode=False)