Eunomia

AI Agent Chemist for Developing Materials Datasets

Iterative-Chain-of-Verification (CoV)

Eunomia employs a chain-of-verification process iteratively to minimize the likelihood of hallucination, as well as integrating chemistry-informed knowledge into decision-making and action-taking plannings of the LLM.

Live App

https://eunomia.streamlit.app/

Example 1: Molecular Targets and Peptide Sequences

VEGFR_affinity.mp4

Example 2: Water Stable Metal-organic Frameworks

Water_stability.mp4

Example 3: Thermal Conductivity of Metal-organic Frameworks

Thermal_conductivity.mp4

Installation

pip install materials-eunomia

or you can clone the source code and install in developer mode:

git clone https://github.com/AI4ChemS/Eunomia.git && cd Eunomia
pip install -e .

You need to have a valid OPENAI API key. If you are on a windows machine you can add OPENAI_API_KEY in your Environment Variables. For linux systems set the key by adding this line to ~/.bashrc:

export OPENAI_API_KEY=your_api_key_here

Confirm correct installation by running the unittests:

cd tests && python -m unittest discover

Applying Other LLMs

Eunomia uses openAI's gpt-4 by default but you can use other LLMs for driving the agent as well. Check out this notebook for examples.

Citation

For more details checkout paper and if you are using our methodology, please consider citing us using the citation below:

@article{ansari2024agent,
  title={Agent-based learning of materials datasets from scientific literature},
  author={Ansari, Mehrad Gholizadeh and Moosavi, Seyed Mohamad},
  journal={Digital Discovery},
  year={2024},
  publisher={Royal Society of Chemistry}
}