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
Example 2: Water Stable Metal-organic Frameworks
Example 3: Thermal Conductivity of Metal-organic Frameworks
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 preprint and if you are using our methodology, please consider citing us using the citation below:
@misc{ansari2023agentbased,
title={Agent-based Learning of Materials Datasets from Scientific Literature},
author={Mehrad Ansari and Seyed Mohamad Moosavi},
year={2023},
eprint={2312.11690},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
Metadata
Release files for materials-eunomia 1.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| materials_eunomia-1.1.0.tar.gz | 1.8 MB | Without provenance | Details for materials_eunomia-1.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| materials_eunomia-1.1.0-py2.py3-none-any.whl | Python 3, Python 2 | none | any | Details for materials_eunomia-1.1.0-py2.py3-none-any.whl |
Total release size: 1.8 MB
Release files / materials_eunomia-1.1.0.tar.gz
| Download URL | materials_eunomia-1.1.0.tar.gz |
|---|---|
| Size | 1.8 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
550e0fc5c98e01808fcf94858dc09d37b283dc3f23ebbd0e987fbdda7d51d373
|
|
BLAKE2b-256 checksum How to use checksums |
768b7d102fa58df13925ee1aa847be7e5a1a591017cf11a6b250d192081c4cf0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.9.18
|
Release files / materials_eunomia-1.1.0-py2.py3-none-any.whl
| Download URL | materials_eunomia-1.1.0-py2.py3-none-any.whl |
|---|---|
| Size | 15.5 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
c93f719b6e27a49cbeabdab5764d008da082a342bfd23c34bb2873d71c217c72
|
|
BLAKE2b-256 checksum How to use checksums |
bfd15f48bf868c58c70b824a2ec110791739747e5d58a1a5033cb4e9bc4c3662
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.9.18
|
Security for materials-eunomia 1.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.