Author: Ren Nakagawa
This is a repository for the final project of the PBL course at the University of Kobe. The project is about a railway knowledge system that utilizes AI technologies to support railway operations. The system is designed to help railway operators make decisions more efficiently and safely.
Image generated by DALL-E 3
The system is designed to help railway operators make decisions more efficiently and safely. The system uses AI technologies such as LLM, ReAct, and AutoGen to provide support for various tasks in railway operations. The system can help operators with tasks such as summarizing operation information, responding to inquiries, creating manuals, and analyzing operation data.
This image is a system image of the railway knowledge system usage.
This is the directory structure of the project:
pbl-railway-knowledge-system
├───assets: For README images
├───cache: For storing cached data
├───data: Input data for the system
├───docs: For prompt of the system
│ ├───evals: For evaluation
│ └───tools: For ReAct
├───interface: Example of UI
├───notebooks: The usage of the system
├───Presentation.pdf: Final presentation slides(Explain of this product)
├───requirements.txt: List of dependencies for python
└───README.md: This file
To use the system, you need to install the required dependencies. You can install the dependencies by running the following command:
pip install -r requirements.txtAfter installing the dependencies, you can run the system by running the following command:
python -m src.main # Run the systemmore usage is here
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.