mih1ka/nlp-student-json

Student JSON Database with Agentic AI (Mini Project)

This project is a mini agentic AI system that manages a university student database stored in a JSON file.
It combines:

• A Flask MCP server to manage student records
• Ollama (LLaMA model) to convert natural language queries into structured actions
• A Python Tkinter GUI to display results

Features

• Add a new student (with ID, name, age, department, year, GPA, courses)a
• Update student details (e.g., change GPA or department)
• Delete a student by name
• Search students by:
  • Department
  • Year (e.g., FIRST, SECOND, FINAL)
  • GPA threshold (e.g., above 8.0)
  • Course name
• List all students in a GUI table
• Get details of a single student
• Query logs saved for debugging

Project Structure

student-json-project/ │── client.py # Natural language client (talks to LLaMA + Flask server) │── server.py # Flask MCP server handling students.json │── students.json # Dummy student data file │── requirements.txt # Python dependencies │── README.md # Project documentation │── query_log.txt # (Auto-generated) log of queries and AI responses

Setup & Run

1. Clone the Repository

git clone https://github.com/YOUR_USERNAME/student-json-project.git
cd student-json-project

2. Install Dependencies
pip install -r requirements.txt

3. Start the MCP Server
python server.py


By default, the server runs on http://localhost:5000.

4. Run the Client
python client.py