Skip to main content

chatmof

Project description

PypI Figshare DOI Lincense

ChatMOF: an artificial intelligence system for predicting and generating metal-organic frameworks using large language models

ChatMOF is an artificial intelligence (AI) system that is built to predict and generate metal-organic frameworks (MOFs). By leveraging a large-scale language model (GPT-4, GPT-3.5-turbo, and GPT-3.5-turbo-16k), ChatMOF extracts key details from textual inputs and delivers appropriate responses, thus eliminating the necessity for rigid and formal structured queries. The system is comprised of three core components (i.e., an agent, a toolkit, and an evaluator) and it forms a robust pipeline that manages a variety of tasks, including data retrieval, property prediction, and structure generations. ChatMOF shows high accuracy rates of 96.9% for searching, 95.7% for predicting, and 87.5% for generating tasks with GPT-4. Additionally, it successfully creates materials with user-desired properties from natural language.

NOTE: ChatMOF has been updated to 0.2.0 and includes a new tool unit converter.

Online Demo

You can test ChatMOF in Online-Demo site. It requires an OpenAI key (For more information, visit the OpenAI site). In online demo, only the Search task is available. For prediction tasks and generation tasks that require machine learning do not work properly, except for the provided examples.

OnlineDemo

Install

Dependencies

NOTE: This package is primarily tested on Linux. We strongly recommend using Linux for the installation.

python>=3.9

Installation

$ pip install chatmof

If you have a dependency issues between torch and moftransformer, uninstall torch and pytorch-lightning, install torch <2.0.0, and reinstall.

For prediction and generation task, you have to setup modules.

$ chatmof setup

Add the following line to .bashrc for the openai api key.

# openai api key
export OPENAI_API_KEY="enter_your_api_key"

If you want to search the internet, you'll need to enter the GOOGLE_API_KEY and GOOGLE_CSE_ID into .bashrc.

# google api and cse_id
export GOOGLE_API_KEY="enter_your_api_key"
export GOOGLE_CSE_ID="enter_your_id"

For MOF generation, you need to install GRIDAY.

$ chatmof install-griday

How to use ChatMOF

You can use it by running chatmof's run function.

$ chatmof run

example

You can adjust argument of Chatmof such as model and temperature.

$ chatmof run --model-name gpt-3.5-turbo --temperature 0.5

You can use help to see more options.

$ chatmof run --help

Example of ChatMOF

1) Search task

2) prediction task

3) generation task

Architecture

ChatMOF comprises three core components: an agent, toolkits, and an evaluator. Upon receiving a query from human, the agent formulates a plan and selects a suitable toolkit. Subsequently, the toolkit generates outputs following the proposed plan, and the evaluator makes these results into a final response. More details for ChatMOF structure are described at structure.md.

Citation

if you want to cite ChatMOF, please refer to the following paper:

ChatMOF: an artificial intelligence system for predicting and generating metal-organic frameworks using large language models, Nature Communications 15, 4705 (2024) [link]

Contributing 🙌

Contributions are welcome! If you have any suggestions or find any issues, please open an issue or a pull request.

License 📄

This project is licensed under the MIT License. See the LICENSE file for more information.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

chatmof-0.2.2.tar.gz (1.4 MB view hashes)

Uploaded Source

Built Distribution

chatmof-0.2.2-py3-none-any.whl (1.4 MB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page