🤖 Towards Agentic Schema Refinement

Constructing a semantic layer using Multi-agent LLM pipelines.

Updates

If you find our data or the paper helpful, please cite the paper

@article{rissaki2024towards,
  title={Towards Agentic Schema Refinement},
  author={Rissaki, Agapi and Fountalis, Ilias and Vasiloglou, Nikolaos and Gatterbauer, Wolfgang},
  journal={arXiv preprint arXiv:2412.07786},
  year={2024}
}

Conda Environment

This project requires Python3.11+.

The environment.yml file can be used to create a conda environment with all necessary dependencies.

conda env create -f environment.yml

Setup

• We use OpenAI for our LLM agents. You will need to configure the OpenAI credentials. Copy OAI_CONFIG_LIST_sample, name to OAI_CONFIG_LIST, and set the correct configuration.

Contact

Your support in improving this work is greatly appreciated! If you have any questions or feedback, please send an email to [email protected].