This project seeks to assess the capabilities of Large Language Models (LLMs) in the task of Entity Resolution. The primary goal of the experiment is to verify whether the LLM can discern if an execution trace in XES format of a business process matches another one.
To install the required Python packages for this project, you can use pip along with the requirements.txt file.
First, you need to clone the repository:
git clone https://github.com/AngeloC99/Trace_similarity_LLM
cd Trace_similarity_LLM
Run the following command to install the necessary dependencies using pip:
pip install -r requirements.txt
This command will read the requirements.txt file and install all the specified packages along with their dependencies.
Please note that this software leverages open-source LLMs such as Mistral and DeciLM, which have specific requirements in terms of GPU availability. It is recommended to have access to a GPU-enabled environment to run the software effectively.
Before running the project, it is necessary to replace in the main.py file the predefined string in the hf_token with your personal HuggingFace token. Then, you can proceed by going in the project directory and executing the following command:
python3 main.py