Skip to content

NilanchalaPanda/campusPro

Repository files navigation

AI Chatbot for College Assistance 🔗

Welcome to the AI Chatbot for College Assistance project! This AI chatbot is designed to assist students with their college-related queries via a user-friendly interface. Utilizing Next.js for the frontend, WhisperAI for voice queries, Command R+ LLM for real-time data scraping, and Twilio for WhatsApp integration, this solution significantly enhances the user experience and reduces the workload on college administrators.

image

The User Flow of the CampusPro

image

Technologies Used

  • Next.js: Framework for building server-rendered React applications.
  • WhisperAI: Used for processing voice queries.
  • Command R+ LLM: Enables real-time data scraping for up-to-date information.
  • Twilio: Integrates WhatsApp for direct communication.
  • Docker: Containerization of ML models for easy deployment.
  • Recommendation System: Offers personalized college recommendations based on user preferences.

Features

  • Voice Query Support:

    • Users can ask questions using their voice, making interactions more intuitive and accessible, especially for those on the go.
  • Real-Time Data Scraping:

    • The chatbot can pull information from various online sources in real time, ensuring users receive the latest updates on college admissions, courses, deadlines, and events.
  • WhatsApp Integration:

    • By leveraging Twilio, users can interact with the chatbot directly through WhatsApp, making it convenient to get assistance without needing a dedicated app.
  • Personalized College Recommendations:

    • Based on user inputs and preferences, the recommendation system suggests colleges tailored to the individual's interests, helping them make informed decisions.
  • User-Friendly Interface:

    • Built with Next.js, the chatbot provides a smooth and responsive user experience, making it easy for users to navigate and find the information they need.
  • Scalable and Dockerized Deployment:

    • The entire application, including the ML models, is containerized using Docker, allowing for easy scaling and deployment in different environments.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published