This assistant is designed to function as an educational support tool, aimed at assisting institutions in analyzing student data and identifying patterns of dropout risk based on the information provided by the institution's database.
- Data Analysis: Processes and analyzes student data to detect trends and insights.
- Dropout Risk Prediction: Identifies patterns associated with dropout risks using the provided institutional data.
- Customizable Integration: Works with different database formats for seamless integration with institutional systems.
- Database Access: The tool requires access to the institution's database for data processing.
- Environment:
- Programming Language: Python
- Libraries:
- Flask==2.3.0
- Flask-SQLAlchemy==2.5.1
- Flask-Cors==3.0.10
- Werkzeug==2.3.0
- mysql-connector-python==9.1.0
- sentence-transformers==3.3.1
- qdrant-client==1.12.1
- openai==1.55.3
-
Clone the repository:
git clone https://github.com/Johnymonteiiro/ai_school_assistent
-
Navigate to the project directory:
cd ai_school_assistent
-
Install the required dependencies:
pip install -r requirements.txt
Ensure your
requirements.txt
includes the following:Flask==2.3.0 Flask-SQLAlchemy==2.5.1 Flask-Cors==3.0.10 Werkzeug==2.3.0 mysql-connector-python==9.1.0 sentence-transformers==3.3.1 qdrant-client==1.12.1 openai==1.55.3
-
Configure the database connection in the
.env
file:DATABASE_URL=your-database-url
-
Start the assistant:
python app.py
-
Provide the necessary database access credentials.
-
Use the interface to upload or select data for analysis.
-
View the generated reports and dropout risk patterns in the output section.
We welcome contributions to enhance the functionality of this tool. To contribute:
-
Fork the repository.
-
Create a new branch for your feature or bugfix:
git checkout -b feature-name
-
Commit your changes:
git commit -m "Add feature-name"
-
Push your changes and open a pull request:
git push origin feature-name
This project is licensed under the MIT License. See the LICENSE
file for more details.
For questions or support, please contact [johnymonteiiro@gmail.com].