ai---research-assistant

https://github.com/mohamedal1362001/ai---research-assistant

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (13.9%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: mohamedal1362001
Language: Jupyter Notebook
Default Branch: main
Size: 8.45 MB

Statistics

Stars: 1
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created over 1 year ago · Last pushed over 1 year ago

Metadata Files

Readme Citation

# AI Research Assistant Tool ## Overview The AI Research Assistant Tool is a powerful system that automates the process of multi-document summarization, information extraction, and citation generation. It simplifies research workflows by extracting metadata like titles, authors, abstracts, and dates from academic PDFs and generating citations in APA, MLA, and Chicago formats.

Key Features

Multi-Document Summarization

Supports extractive and abstractive summarization using T5 models.
Processes multiple PDFs efficiently. -Information Extraction

Extracts key document metadata:

Title
Authors
Abstract
Date
Citation Generation

Automatically generates citations in:

APA Format
MLA Format
Chicago Format
Export citations in .docx or .bib formats.

PDF Processing

Handles PDFs and converts pages to images for model processing.

Technologies Used

Programming Language: Python
Frameworks & Libraries:
- PyTorch
- Transformers (HuggingFace)
- Detectron2
- Spacy
- Tesseract OCR
- PDF Processing: pdfplumber, pdf2image, Pillow
Models:
- T5: Summarization
- ResNet-X101: Information extraction # Installation Follow these steps to set up the project on your local machine: ## 1. Clone the Repository ``` git clone https://github.com/your-username/ai-research-assistant.git cd ai-research-assistant

```

2. Install Dependencies

Ensure Python 3.8+ is installed, then run: ``` pip install -r requirements.txt

```

3. Install Additional Tools

Install Tesseract OCR:
- Linux: ``` sudo apt install tesseract-ocr

```

Windows: Download Tesseract OCR. Install spacy model: ``` python -m spacy download encoreweb_trf

```

Usage

1. Summarization

To summarize PDFs and save the output: ``` python summarization.py --input --output

```

2. Information Extraction & Citation Generation

To extract metadata and generate citations: ``` python extractinfo.py --input <pathtopdffolder> --output

```

3. Export Citations

Export citations in .docx or .bib formats: ``` python exportcitations.py --format bib --output mycitation.bib python exportcitations.py --format docx --output citation.docx

```

Project File Structure

``` ai-research-assistant/ │ ├── models/ # Pre-trained models │ ├── X101/ # ResNet X101 config & model files │ └── T5/ # T5 summarization models │ ├── utils/ # Helper functions ├── data/ # Input/Output PDF files │ ├── extractinfo.py # Information extraction script ├── summarization.py # Summarization script ├── exportcitations.py # Export citations in multiple formats │ ├── requirements.txt # Python dependencies └── README.md # Project documentation

```

Limitations

Requires high computational resources for training models.
Limited to processing between 4-6 PDFs simultaneously due to server constraints.
PDF documents must be:
- Plain text or LaTeX format.
- Non-colored PDFs. # Future Improvements
Support for colored and complex PDFs.
Cloud-based processing to overcome hardware constraints.
Fine-tuning additional Transformer models for improved accuracy. # Contact For any queries or contributions, feel free to open an issue or contact the contributors. # Clone, Contribute, and Share! We welcome contributions to enhance the project. Fork the repository, create a feature branch, and submit a pull request.

Owner

Name: Mohamed Ali
Login: mohamedal1362001
Kind: user
Location: cairo

Repositories: 1
Profile: https://github.com/mohamedal1362001

Little things make big changes

Citation (citation.html)

<!DOCTYPE html>
<html>

<head>
  <link rel="stylesheet" type="text/css" href="static/citation.css">
  <link rel="stylesheet" type="text/css" href="static/styles.css">

  <meta charset="utf-8">
  <meta name="viewport" content="width=device-width , initial-scale=1 , shrink-to-fit=no">
  <title>PaperTown</title>
  <link rel="stylesheet" type="text/css"
    href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.11.2/css/all.min.css">
  <link rel="stylesheet" type="text/css"
    href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.11.2/css/fontawesome.min.css">
  <link rel="stylesheet" type="text/css"
    href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/4.4.1/css/bootstrap.css">
  <link href="https://fonts.googleapis.com/css?family=Poppins:400,500,700&display=swap" rel="stylesheet">
  <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@6.2.1/css/fontawesome.min.css"
    integrity="sha384-QYIZto+st3yW+o8+5OHfT6S482Zsvz2WfOzpFSXMF9zqeLcFV0/wlZpMtyFcZALm" crossorigin="anonymous">
  <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.3/css/all.min.css">
  <link rel="stylesheet" ,
    href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@6.2.1/css/fontawesome.min.css" ,
    integrity="sha384-QYIZto+st3yW+o8+5OHfT6S482Zsvz2WfOzpFSXMF9zqeLcFV0/wlZpMtyFcZALm" , crossorigin="anonymous">
  <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.4.0/css/font-awesome.min.css">

</head>

<body>
  <div class="nav">
    <a class="logo" href="#">
      <img class="image_logo" src="static/assets/icons/the_Papertown-removebg-preview.png">
    </a>
    <div class="navbar-toggler" type="button" id="bar">
      <span class="toggler-icon"></span>
      <span class="toggler-icon"></span>
      <span class="toggler-icon"></span>
    </div>
    <div class="menu-bar" id="navbar">
      <ul class="menu-items">
        <li><a href="{{ url_for('home') }}">Home</a></li>
        <li><a href="#">About us</a></li>
        {% if current_user.is_authenticated %}
        <li class="dropdown">
          <a href="#services">Service</a>
          <ul class="dropdown-menu">
            <li><a href="{{ url_for('summarization_page') }}">Summarization</a></li>
            <li><a href="{{ url_for('citation') }}">Citation</a></li>
          </ul>
        </li>
        <li><a href="{{ url_for('logout') }}">Logout</a></li>
        {% else %}
        <li><a href="{{ url_for('login') }}">Sign in</a></li>
        <li><a href="{{ url_for('register') }}">Sign up</a></li>
        {% endif %}
      </ul>
    </div>
    <div class="navbar-socail">
      <span>FOLLOW US</span>
      <ul>
        <li><a href="#"><svg class="insta" xmlns="http://www.w3.org/2000/svg" height="1em" viewBox="0 0 448 512">
              <!--! Font Awesome Free 6.4.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license (Commercial License) Copyright 2023 Fonticons, Inc. -->
              <style>
                svg {
                  fill: #6c6c6c
                }
              </style>
              <path
                d="M224,202.66A53.34,53.34,0,1,0,277.36,256,53.38,53.38,0,0,0,224,202.66Zm124.71-41a54,54,0,0,0-30.41-30.41c-21-8.29-71-6.43-94.3-6.43s-73.25-1.93-94.31,6.43a54,54,0,0,0-30.41,30.41c-8.28,21-6.43,71.05-6.43,94.33S91,329.26,99.32,350.33a54,54,0,0,0,30.41,30.41c21,8.29,71,6.43,94.31,6.43s73.24,1.93,94.3-6.43a54,54,0,0,0,30.41-30.41c8.35-21,6.43-71.05,6.43-94.33S357.1,182.74,348.75,161.67ZM224,338a82,82,0,1,1,82-82A81.9,81.9,0,0,1,224,338Zm85.38-148.3a19.14,19.14,0,1,1,19.13-19.14A19.1,19.1,0,0,1,309.42,189.74ZM400,32H48A48,48,0,0,0,0,80V432a48,48,0,0,0,48,48H400a48,48,0,0,0,48-48V80A48,48,0,0,0,400,32ZM382.88,322c-1.29,25.63-7.14,48.34-25.85,67s-41.4,24.63-67,25.85c-26.41,1.49-105.59,1.49-132,0-25.63-1.29-48.26-7.15-67-25.85s-24.63-41.42-25.85-67c-1.49-26.42-1.49-105.61,0-132,1.29-25.63,7.07-48.34,25.85-67s41.47-24.56,67-25.78c26.41-1.49,105.59-1.49,132,0,25.63,1.29,48.33,7.15,67,25.85s24.63,41.42,25.85,67.05C384.37,216.44,384.37,295.56,382.88,322Z" />
            </svg>
          </a>
        </li>
        <li><a href="#"><svg class="facebook" xmlns="http://www.w3.org/2000/svg" height="1em" viewBox="0 0 512 512">
              <!--! Font Awesome Free 6.4.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license (Commercial License) Copyright 2023 Fonticons, Inc. -->
              <path
                d="M504 256C504 119 393 8 256 8S8 119 8 256c0 123.78 90.69 226.38 209.25 245V327.69h-63V256h63v-54.64c0-62.15 37-96.48 93.67-96.48 27.14 0 55.52 4.84 55.52 4.84v61h-31.28c-30.8 0-40.41 19.12-40.41 38.73V256h68.78l-11 71.69h-57.78V501C413.31 482.38 504 379.78 504 256z" />
            </svg>
          </a>
        </li>
        <li><a href="#"><svg class="twitter" xmlns="http://www.w3.org/2000/svg" height="1em" viewBox="0 0 512 512">
              <!--! Font Awesome Free 6.4.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license (Commercial License) Copyright 2023 Fonticons, Inc. -->
              <path
                d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z" />
            </svg>
          </a>
        </li>
        <li><a href="#"><svg class="linked-in" xmlns="http://www.w3.org/2000/svg" height="1em" viewBox="0 0 448 512">
              <!--! Font Awesome Free 6.4.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license (Commercial License) Copyright 2023 Fonticons, Inc. -->
              <path
                d="M100.28 448H7.4V148.9h92.88zM53.79 108.1C24.09 108.1 0 83.5 0 53.8a53.79 53.79 0 0 1 107.58 0c0 29.7-24.1 54.3-53.79 54.3zM447.9 448h-92.68V302.4c0-34.7-.7-79.2-48.29-79.2-48.29 0-55.69 37.7-55.69 76.7V448h-92.78V148.9h89.08v40.8h1.3c12.4-23.5 42.69-48.3 87.88-48.3 94 0 111.28 61.9 111.28 142.3V448z" />
            </svg>
          </a>
        </li>



      </ul>
    </div>


  </div>
  <section class="section-services">
    <div class="cont">
      <div class="row justify-content-center text-center">
        <div class="col-md-10 col-lg-8">
          <div class="header-section">
            <h2 class="title" style="margin-top:15vh">Citation Generator</h2>
            <h6>Uplode Your PDF And Click on Generate After using your format of citation</h6>
          </div>
        </div>
      </div>
      <div class="my-box">
        <div class="col-md-6 col-lg-6 copy-area">
          <div class="type">
            <h5>scientific research</h3>
          </div>
          <!--
                        <textarea name=" " id=" " cols="30" rows="10" placeholder="text here"></textarea>
                    -->
          <div class="form-container">
            <form id="myForm" action="{{ url_for('predection') }}" method="POST">
              <label for="author">Author:</label>
              <input type="text" id="Author" name="Author" placeholder="eg: Author-1,Author-2,Author-3 or Author" >

              <label for="year">Year:</label>
              <input type="text" id="Date" name="Date" placeholder="eg: 14-6-2023 or Mon,14 june">

              <label for="title">Title:</label>
              <input type="text" id="Title" name="Title" placeholder="eg: Title for yor paper">

              <label for="publisher">Publisher:</label>
              <input type="text" id="Publisher" name="Publisher" placeholder="eg: puplisher institution ">
              <select name="citationStyleSelect" class="form-select" id="citationStyleSelect">
                <option selected disabled>Citation Style:</option>
                <option value="1">Citation Style: APA : American Psychological Association 7th</option>
                <option value="2">Citation Style: MLA : Modern Language Association 9th edition</option>
                <option value="3">Citation Style: Begell House - Chicago Manual of Style</option>
              </select>
              <input type="Submit" value="Generate" >
            </form>
            <div class="upload-genrate">
              <form method="POST" action="{{ url_for('upload') }}" enctype="multipart/form-data">
                <input type="file" name="file">
                <button type="submit">Upload</button>
                {% with messages = get_flashed_messages() %} {% if messages %}
                <ul class="flash-messages">
                  {% for message in messages %}
                  <li>{{ message }}</li>
                  {% endfor %}
                </ul>
                {% endif %} {% endwith %}
              </form>
            </div>
          </div>
        </div>
        <div class="col-md-6 col-lg-6 output">
          <div class="contaner">
            <div class="form-floating">


              <div class="block-citation-text">
                <h6>Main Citation:</h6>
                
                <div class="format-citation">
                  <form name='output_citation'method="POST">
                    <textarea class="citation-text"name='test' id='citationout'>{{ finalcitation }}</textarea>
                    <ul class="header-btn">
                      <li><a class="main-btn btn-one" onclick="triggerExample1()"><svg xmlns="http://www.w3.org/2000/svg"
                            height="1em" viewBox="0 0 512 512">
                            <!--! Font Awesome Free 6.4.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license (Commercial License) Copyright 2023 Fonticons, Inc. -->
                            <style>
                              svg {
                                fill: #a7aaaf
                              }
                            </style>
                            <path
                              d="M272 0H396.1c12.7 0 24.9 5.1 33.9 14.1l67.9 67.9c9 9 14.1 21.2 14.1 33.9V336c0 26.5-21.5 48-48 48H272c-26.5 0-48-21.5-48-48V48c0-26.5 21.5-48 48-48zM48 128H192v64H64V448H256V416h64v48c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V176c0-26.5 21.5-48 48-48z" />
                          </svg></a></li>
                      <li>
                        
                          <select class="border-radius: 10px;" name="citationFormatiesSelect" class="form-select-download" id="citationFormatiesSelect">
                            <option selected disabled>Download formates</option>
                            <option value="1">docx formate</option>
                            <option value="2">Bibtex formate</option>
                          </select>
                          
                      
                      </li>
                    </ul>
                    <button class="btn-download"type="submit">Download</button>
                  </form>
                </div>
              </div>
            </div>
          </div>
        </div>

      </div>
    </div>
  <footer>
    <footer class="footer">
      <div class="container">
        <div class="row">
          <div class="footer-col">
            <h4>company</h4>
            <ul>
              <li><a href="#">about us</a></li>
              <li><a href="#">our services</a></li>
              <li><a href="#">privacy policy</a></li>
              <li><a href="#">affiliate program</a></li>
            </ul>
          </div>
          <div class="footer-col">
            <h4>follow us</h4>
            <div class="social-links">
              <a href="#"><i class="fab fa-facebook-f"></i></a>
              <a href="#"><i class="fab fa-twitter"></i></a>
              <a href="#"><i class="fab fa-instagram"></i></a>
              <a href="#"><i class="fab fa-linkedin-in"></i></a>
            </div>
          </div>
        </div>
      </div>
    </footer>
  </footer>
  </section>

    <script>
      function triggerExample1() {
        // get the container
         var textarea = document.getElementById("citationout");
      textarea.select();
      navigator.clipboard.writeText(textarea.value)
        .then(function() {
          alert("Text copied to clipboard!");
        })
        .catch(function(error) {
          alert("Error copying text: " + error);
        });
    }
    </script>
    
    <script src="{{ url_for('static', filename='script.js') }}"></script>
    <script src="https://code.jquery.com/jquery-3.6.0.min.js"></script>
    <script src="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.3/js/all.min.js"></script>
    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.0.0-beta3/dist/js/bootstrap.bundle.min.js"
      integrity="sha384-JEW9xMcG8R+pH31jmWH6WWP0WintQrMb4s7ZOdauHnUtxwoG2vI5DkLtS3qm9Ekf" crossorigin="anonymous">
    </script>
</body>

</html>

GitHub Events

Total

Watch event: 1
Push event: 3

Last Year

Watch event: 1
Push event: 3

Dependencies

requirements.txt pypi

detectron2 v0.4
flask-ngrok *
flask_bcrypt *
flask_login *
flask_sqlalchemy *
flask_wtf *
layoutparser *
pdf2image *
pdfplumber *
pillow ==9.0.0
pybtex *
pyngrok *
pytesseract *
python-docx *
pytorch-pretrained-bert *
sentence-transformers *
spacy *
torch *
tqdm *
transformers *

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science