PathFinder

PathFinder is an AI-driven platform designed to provide personalized career guidance to students in educational institutions. Leveraging machine learning algorithms,PathFinder analyzes a wide range of student data to offer tailored recommendations for courses, topics, and career fields based on individual preferences, academic performance, and ongoing trends.

Key Features

• Data Collection: Gathers comprehensive student data including academic records, preferences, interests, goals, and feedback.
• Machine Learning Models: Employs algorithms to analyze data and uncover patterns for academic and career insights.
• Personalized Recommendations: Provides tailored guidance on courses, topics of focus, and potential career fields.
• Interactive Interface: Offers a user-friendly interface for seamless interaction.
• Continuous Improvement: Incorporates feedback to enhance recommendation accuracy over time.

Tech Stack

• Backend: Flask, Python , Streamlit, FastAPI,etc
• Machine Learning Library: Pytorch..
• LLM's: llama3(8b),llava
• Web Framework: Flask , HTML5, CSS3, JS, Bootstrap
• Database Management System: MySQL (not implemented yet)

Getting Started

Prerequisites

Ensure you have the following installed:

• Python 3.11.x
• pip (Python package installer)
• MySQL (optional)

Installation

1. Clone the repository:

   git clone https://github.com/HackStyx/PathFinder.git
   cd PathFinder

2. Install the required packages:

   pip install -r requirements.txt

3. Set up the LLM locally:

   • Install the ollama locally with all the required applications.
   • Start the ollama with 'llama3' profile.(tutorial)

4. Run the application:

   python app.py (for connecting the auth page to form)
   python LLM_Main.py (for connecting the Local LLM to Program via API)
   index.html

Usage

• Access the platform at http://localhost:5000.
• Sign up and provide your academic and personal information.
• Get personalized course and career recommendations.

Folder Structure

PathFinder/
├── README.md
├── LLM_Main.md
├── requirements.txt
├── index.html
├── dashboard.html
├── results.html
├── dashb.html
├── assets/..
├──Login/
│   ├── index.html
│   ├── signup.html
│   ├── others/..
└── question_final/
    └── data/submissions.csv
	└── app.py
	└──format_data.py
	└── llm_responses.txt

Note

->If something is not working or getting connection error try changing the host address and relative path of the resources.

->If you are getting slow output that's totally hardware dependent. (you can use cuda cores for better performance)

Screenshots

Contributing

We welcome contributions from the our community! If you'd like to contribute to the project, please follow our contributing guidelines.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

If you have any questions, suggestions, or want to contribute to this project, please feel free to reach :

• Prince