{"id":13699036,"url":"https://github.com/chiang-yuan/llamp","last_synced_at":"2025-04-07T07:17:41.452Z","repository":{"id":238899523,"uuid":"660920989","full_name":"chiang-yuan/llamp","owner":"chiang-yuan","description":"A web app and Python API for multi-modal RAG framework to ground LLMs on high-fidelity materials informatics. An agentic materials scientist powered by @materialsproject, @langchain-ai, and @openai","archived":false,"fork":false,"pushed_at":"2024-10-14T03:45:00.000Z","size":14351,"stargazers_count":75,"open_issues_count":7,"forks_count":13,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T06:06:01.475Z","etag":null,"topics":["ai4science","cheminformatics","language-model","materials-informatics","retrieval-augmented-generation"],"latest_commit_sha":null,"homepage":"http://ingress.llamp.development.svc.spin.nersc.org/about","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chiang-yuan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-07-01T08:15:34.000Z","updated_at":"2025-03-13T03:53:37.000Z","dependencies_parsed_at":"2024-06-10T05:34:29.473Z","dependency_job_id":"f7f7f30d-8181-4e8a-9a8b-0966b586401b","html_url":"https://github.com/chiang-yuan/llamp","commit_stats":null,"previous_names":["chiang-yuan/llamp"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiang-yuan%2Fllamp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiang-yuan%2Fllamp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiang-yuan%2Fllamp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiang-yuan%2Fllamp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chiang-yuan","download_url":"https://codeload.github.com/chiang-yuan/llamp/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247608160,"owners_count":20965953,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai4science","cheminformatics","language-model","materials-informatics","retrieval-augmented-generation"],"created_at":"2024-08-02T19:00:56.604Z","updated_at":"2025-04-07T07:17:41.428Z","avatar_url":"https://github.com/chiang-yuan.png","language":"Jupyter Notebook","funding_links":[],"categories":["Language Models"],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003e\n    \u003cb\u003eLLaMP 🦙🔮\u003c/b\u003e\n    \u003cbr\u003e\n    \u003ca href=\"https://arxiv.org/abs/2401.17244\"\u003e\n      \u003cimg src=\"https://img.shields.io/badge/cs.CL-2401.17244-b31b1b?logo=arxiv\u0026logoColor=white\" alt=\"arXiv\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"http://ingress.llamp.development.svc.spin.nersc.org/about\"\u003e\n      \u003cimg src=\"https://img.shields.io/badge/web-demo-magenta?style=flat\u0026link=http%3A%2F%2Fingress.llamp.development.svc.spin.nersc.org%2Fabout\" alt=\"Website\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://github.com/chiang-yuan/llamp/stargazers\"\u003e\n      \u003cimg src=\"https://img.shields.io/github/stars/chiang-yuan/llamp?style=social\" alt=\"Github Stars\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"http://colab.research.google.com/github/chiang-yuan/llamp/blob/main/experiments/00-notebook-chat.ipynb\"\u003e\n      \u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\"\u003e\n    \u003c/a\u003e\n\u003c/h1\u003e\n\u003ch4 align=\"center\"\u003eLarge Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation\u003c/h4\u003e\n\n\n\u003e [!TIP]\n\u003e TL;DR: LLaMP is a multimodal retrieval-augmented generation (RAG) framework of hierarchical ReAct agents that can dynamically and recursively interact with [Materials Project](https://materialsproject.org) to ground LLMs on high-fidelity materials informatics.\n\nThis repository accompanies our paper [**LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation**](https://arxiv.org/abs/2401.17244). Our codebase is built upon [LangChain](https://github.com/langchain-ai/langchain) and is designed to be modular and extensible, and can be used to reproduce the experiments in the paper, as well as to develop new experiments.\n\nLLaMP is also a homonym of **Large Language model [Materials Project](https://materialsproject.org)**. :wink: It empowers LLMs with large-scale computational materials database to reduce the likelihood of hallucination for materials informatics. \n\n\u003ch4 align=\"center\"\u003e\n  \u003cimg src=\"https://python.langchain.com/v0.1/img/brand/wordmark-dark.png\" height=\"30\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/sveltejs/branding/master/svelte-horizontal.svg\" height=\"30\"/\u003e\n  \u003ca href=\"https://elementari.janosh.dev/\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/janosh/elementari/main/static/favicon.svg\" height=\"30\"/\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.skeleton.dev/\"\u003e\u003cimg src=\"https://user-images.githubusercontent.com/1509726/199282306-7454adcb-b765-4618-8438-67655a7dee47.png\" height=\"30\"/\u003e\u003c/a\u003e\n\u003c/h4\u003e\n\n## 🔮 Quick Start\n\n#### Python API\n\n```shell\ngit clone https://github.com/chiang-yuan/llamp.git\ncd llamp/api\npip install -e .\n```\n\nAfter installation, check out [colab notebook chat](http://colab.research.google.com/github/chiang-yuan/llamp/blob/main/experiments/00-notebook-chat.ipynb) or the notebooks in `experiments` to start. \n\n#### (Optional) Atomistic Simulation\n\nYou may need to install additional packages to support atomistic simulations:\n\n```shell\npip install ase, atomate2, jobflow, mace-torch\n```\n\n#### (Optional) Docker Web Interface \n\n```shell\ndocker-compose up --build\n```\n\n## 👋 Contributing\n\nWe understand sometime it is difficult to navigate Materials Project database! We want everyone to be able to access materials informatics through conversational AI. We are looking for contributors to help us build a more powerful and user-friendly LLaMP to support more MP API endpoints or external datastore and agents.\n\nTo contirbute to LLaMP, please follow these steps:\n\n1. Fork the repository\n2. Set up environment variables\n    ```shell\n    cp .env.example .env.local\n    ```\n3. Deploy local development environment \n    ```shell\n    docker-compose up\n    ```\n4. Make changes and submit a pull request\n\n## 🌟 Authors and Citation\n\n\u003ca href=\"https://github.com/chiang-yuan\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/41962462?v=4\" title=\"chiang-yuan\" width=\"50\" height=\"50\"\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/knhn1004\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/49494541?v=4\" title=\"knhn1004\" width=\"50\" height=\"50\"\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/Ht2214\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/78026336?v=4\" title=\"Ht2214\" width=\"50\" height=\"50\"\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/janosh\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/30958850?v=4\" title=\"janosh\" width=\"50\" height=\"50\"\u003e\u003c/a\u003e\n\n![Alt](https://repobeats.axiom.co/api/embed/75e53e291a07ad8d4b60e5f800726debe01351fb.svg \"Repobeats analytics image\")\n\nIf you use LLaMP, our code and data in your research, please cite our paper:\n\n```bibtex\n@article{chiang2024llamp,\n  title={LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation},\n  author={Chiang, Yuan and Chou, Chia-Hong and Riebesell, Janosh},\n  journal={arXiv preprint arXiv:2401.17244},\n  year={2024}\n}\n```\n\n## 🤗 Acknowledgements\n\nWe thank Matthew McDermott (@mattmcdermott), Jordan Burns in Materials Science and Engineering at UC Berkeley for their valuable feedback and suggestions. We also thank the [Materials Project](https://materialsproject.org) team for their support and for providing the data used in this work. We also thank Dr. Karlo Berket (@kbuma) and Dr. Anubhav Jain (@computron) for their advice and guidance.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchiang-yuan%2Fllamp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchiang-yuan%2Fllamp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchiang-yuan%2Fllamp/lists"}