subash-lamichhane / pdfassistant

---

PDFAssistant : Streamline Your PDF Workflow

Welcome to PDFAssistant, a powerful web application designed to make working with PDF documents easier and more efficient. PDFAssistant allows you to extract keywords, generate summaries by page, and ask questions related to the content of your PDFs with the help of llmware models. Whether you're a student, researcher, or professional, PDFAssistant is here to help you quickly navigate and understand your documents.

Introduction

PDFAssistant is a web application that provides a suite of tools for analyzing PDF documents. It simplifies the process of extracting essential information from PDFs, enabling users to focus on the content that matters most. With PDFAssistant, you can obtain key insights from your documents without the hassle of manually sifting through pages.

Features

• Keyword Extraction: PDFAssistant identifies and extracts the most relevant keywords from your PDF documents. This feature helps you quickly grasp the main topics and themes within the document.
• Page-specific Summaries: Generate concise summaries for each page of your PDF. This feature allows you to understand the content of each page at a glance, saving you time and effort.
• Question and Answer: Ask questions related to the content of your PDF, and PDFAssistant will provide accurate and relevant answers. This feature is particularly useful for research and study purposes, as it helps you find specific information without extensive reading.

Demo

PDF_assistant.mp4

Dependencies

• React
• Tailwind
• FastAPI
• Uvicogitrn
• LLMWare models

Getting Started

Installation

Clone the repository:

git clone https://github.com/Subash-Lamichhane/PDFAssistant.git

Go to the repository:

cd PDFAssistant

Setup Frontend

Navigate to the frontend directory:

cd frontend

Install dependencies:

yarn install

Start the development server:

yarn run dev

Setup Backend

Navigate to the backend directory:

cd ../backend

Set up a virtual environment :

python -m venv env

source env/bin/activate 

# For Windows use:
env\Scripts\activate # to activate

Install dependencies:

pip install -r requirements.txt

Start the API server:

uvicorn server:app --reload

Usage

Visit the frontend application:

Open your browser and navigate to http://localhost:5173.

Note: If your frontend isn't running at http://localhost:5173 you must change allow_origins in backend\server.py

Make sure the backend is running at:

http://localhost:8000.

Screenshots

Contributing

We welcome contributions from the community! If you'd like to contribute to PDFAssistant, please follow these steps:

1. Fork the Repository: Click the "Fork" button on GitHub to create your copy.

2. Clone Your Fork:

   git clone https://github.com/Subash-Lamichhane/PDFAssistant.git

3. Create a Branch:

   git checkout -b your-branch-name

4. Make Changes: Implement your changes.

5. Commit Your Changes:

   git commit -m "Description of your changes"

6. Push Your Changes:

   git push -u origin your-branch-name

7. Create a Pull Request: Submit your changes for review.

License

This project is licensed under the MIT License.

Acknowledgments

• LLMWare for AI models
• React library for web and native user interfaces
• Tailwind for the styling
• FastAPI for the fast and efficient web framework
• Uvicorn to serve Python web applications that adhere to the ASGI specification

---