Skip to content

Latest commit

 

History

History
81 lines (70 loc) · 2.18 KB

File metadata and controls

81 lines (70 loc) · 2.18 KB

Vesper – AI-Powered Research & Writing Toolkit

Overview

Vesper is an AI-powered platform designed for researchers, students, and creators to refine, humanize, and interact with content and code. It supports tasks like PDF summarization, code debugging, text generation, and literature review — all via a clean, React-based interface backed by FastAPI.

Visit website

Key Features

  • Text Generation using Cohere and Google's Generative AI
  • PDF Summarization with section-wise analysis
  • Semantic Search powered by OpenAlex
  • Code Assistance for debugging, explaining, and completing code
  • Text Humanization for smoother and more natural phrasing
  • Automated Literature Reviews for academic research

Technologies

  • Backend: FastAPI, Cohere API, Google Generative AI, PyMuPDF
  • Frontend: React, Axios, CSS Modules

How to Run the Project

Run Locally

Backend

  1. Navigate to the backend directory:
    cd backend
  2. Create a virtual environment and activate it:
    python -m venv venv
    source venv/bin/activate  # On Windows: venv\Scripts\activate
  3. Install dependencies:
    pip install -r requirements.txt
  4. Start the backend server:
    uvicorn main:app --host 127.0.0.1 --port 8000

Frontend

  1. Navigate to the frontend directory:
    cd frontend
  2. Install dependencies:
    npm install
  3. Start the development server:
    npm start
  4. Access the website at:
    http://localhost:3000
    

Run with Docker

  1. Ensure Docker is installed and running.
  2. Navigate to the project directory:
    cd AI_agent
  3. Build and start the containers:
    docker-compose up -d --build
  4. Access the website:
    • Frontend: http://localhost:3000
    • Backend API Docs: http://localhost:8000/docs

Deployment

  • Frontend: Deploy on platforms like Vercel.
  • Backend: Deploy on platforms like Render.
  • Set REACT_APP_BACKEND_URL in the .env file to point to your backend URL.

Contributing

Feel free to contribute to this project by submitting issues or pull requests.