Built with:
Edulytica is an open-source framework for evaluating text results of educational and scientific activities based on LLMs, which provides an integrated web application out of the box.
The goal is to provide experts with supporting materials in solving the tasks of reviewing final qualifying papers and articles by young scientists, as well as to reduce the time required for in-depth analysis of works.
- The extraction of goals and objectives from the text of the introduction of final qualifying papers has been implemented;
- As part of the work with scientific articles, the functionality of forming a primary review has been implemented;
- Algorithms for summarizing large texts and evaluating the achievement of stated goals and objectives;
- A web application for interacting with features and trained models through a user-friendly interface;
- Separate models have been trained to summarize and assess the achievability of goals and objectives;
- Datasets have been prepared for training models, separately for summarization, separately for goals and objectives.
Please help us improve this project, share your feedback with opening issue!
git clone https://github.com/aimclub/Edulytica.git
docker-compose up --build
source ~/PyProject/Edulytica/api_venv/bin/activate
pip install -r requirements.txt
python3 src/edulytica_api/app.py
celery -A src.edulytica_api.celery.tasks worker --loglevel=info -E -P gevent
npm start
celery -A src.edulytica_api.celery.tasks flower
First, you can familiarize yourself with the examples in JSON format of the system's responses to the test sample of works.
When you have managed to launch the service, you can send the documents yourself and get acquainted with the results of their verification!
Details of the documentation can be found at the links below:
- algorithms - part of the task of analyzing the text how much it is necessary to change the source text (which is written by AI) so that AI recognition systems do not recognize AI in this text;
- data_handling - an auxiliary module that stores parsers of data and documents for generating datasets;
- edulytica_api - this module stores the source code of the web service;
- extracting_rules - This module is devoted to an experiment with extracting design rules using LLM;
- rag - Package for an experiment with semantic search, kNN and the mBERT model are used.
Code documentation is available at the link.
For more information, see the file requiremets.txt.
Our contacts:
- Tereshchenko Vladislav, [email protected].
We also published several posts devoted to different aspects of the project:
In Russian:
- Edulytica: LLM-ассистент для проверки научных работ - Scientific Open Source Meetup №8, October 2024, 1:05:15 - 1:22:36;
- Как мы научили LLM-ассистента рецензировать научные работы студентов ИТМО: вновь о проекте Edulytica - Scientific Open Source Meetup №10, July 2025, 1:07:30 - 1:34:00.