AMGPT: A large language model for contextual querying in additive manufacturing

Generalized large language models (LLMs) such as GPT-4 may not provide specific answers to queries formulated by materials science researchers. These models may produce a high-level outline but lack the capacity to return detailed instructions on manufacturing and material properties of novel alloys...

Full description

Saved in:
Bibliographic Details
Main Authors: Achuth Chandrasekhar, Jonathan Chan, Francis Ogoke, Olabode Ajenifujah, Amir Barati Farimani
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Additive Manufacturing Letters
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772369024000409
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846127126703505408
author Achuth Chandrasekhar
Jonathan Chan
Francis Ogoke
Olabode Ajenifujah
Amir Barati Farimani
author_facet Achuth Chandrasekhar
Jonathan Chan
Francis Ogoke
Olabode Ajenifujah
Amir Barati Farimani
author_sort Achuth Chandrasekhar
collection DOAJ
description Generalized large language models (LLMs) such as GPT-4 may not provide specific answers to queries formulated by materials science researchers. These models may produce a high-level outline but lack the capacity to return detailed instructions on manufacturing and material properties of novel alloys. We introduce “AMGPT”, a specialized LLM text generator designed for metal AM queries. The goal of AMGPT is to assist researchers and users in navigating a curated corpus of literature. Instead of training from scratch, we employ a pre-trained Llama2-7B model from Hugging Face in a Retrieval-Augmented Generation (RAG) setup, utilizing it to dynamically incorporate information from ∼50 AM papers and textbooks in PDF format. Mathpix is used to convert these PDF documents into TeX format, facilitating their integration into the RAG pipeline managed by LlamaIndex. A query retrieval function has also been added, enabling the system to fetch relevant literature from Elsevier journals based on the context of the query. Expert evaluations of this project highlight that specific embeddings from the RAG setup accelerate response times and maintain coherence in the generated text.
format Article
id doaj-art-e4fe90beec9e4d5c9efabedb9f46cd95
institution Kabale University
issn 2772-3690
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Additive Manufacturing Letters
spelling doaj-art-e4fe90beec9e4d5c9efabedb9f46cd952024-12-12T05:24:11ZengElsevierAdditive Manufacturing Letters2772-36902024-12-0111100232AMGPT: A large language model for contextual querying in additive manufacturingAchuth Chandrasekhar0Jonathan Chan1Francis Ogoke2Olabode Ajenifujah3Amir Barati Farimani4Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USAMechanical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USAMechanical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USAMechanical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USAMechanical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USA; Biomedical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USA; Chemical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USA; Machine Learning Department, Carnegie Mellon University, Pittsburgh, 15213, PA, USA; Correspondence to: 5000, Forbes Avenue, USA.Generalized large language models (LLMs) such as GPT-4 may not provide specific answers to queries formulated by materials science researchers. These models may produce a high-level outline but lack the capacity to return detailed instructions on manufacturing and material properties of novel alloys. We introduce “AMGPT”, a specialized LLM text generator designed for metal AM queries. The goal of AMGPT is to assist researchers and users in navigating a curated corpus of literature. Instead of training from scratch, we employ a pre-trained Llama2-7B model from Hugging Face in a Retrieval-Augmented Generation (RAG) setup, utilizing it to dynamically incorporate information from ∼50 AM papers and textbooks in PDF format. Mathpix is used to convert these PDF documents into TeX format, facilitating their integration into the RAG pipeline managed by LlamaIndex. A query retrieval function has also been added, enabling the system to fetch relevant literature from Elsevier journals based on the context of the query. Expert evaluations of this project highlight that specific embeddings from the RAG setup accelerate response times and maintain coherence in the generated text.http://www.sciencedirect.com/science/article/pii/S2772369024000409Large language modelsRetrieval-augmented generationMachine learningContextual queryingLaser powder bed fusion
spellingShingle Achuth Chandrasekhar
Jonathan Chan
Francis Ogoke
Olabode Ajenifujah
Amir Barati Farimani
AMGPT: A large language model for contextual querying in additive manufacturing
Additive Manufacturing Letters
Large language models
Retrieval-augmented generation
Machine learning
Contextual querying
Laser powder bed fusion
title AMGPT: A large language model for contextual querying in additive manufacturing
title_full AMGPT: A large language model for contextual querying in additive manufacturing
title_fullStr AMGPT: A large language model for contextual querying in additive manufacturing
title_full_unstemmed AMGPT: A large language model for contextual querying in additive manufacturing
title_short AMGPT: A large language model for contextual querying in additive manufacturing
title_sort amgpt a large language model for contextual querying in additive manufacturing
topic Large language models
Retrieval-augmented generation
Machine learning
Contextual querying
Laser powder bed fusion
url http://www.sciencedirect.com/science/article/pii/S2772369024000409
work_keys_str_mv AT achuthchandrasekhar amgptalargelanguagemodelforcontextualqueryinginadditivemanufacturing
AT jonathanchan amgptalargelanguagemodelforcontextualqueryinginadditivemanufacturing
AT francisogoke amgptalargelanguagemodelforcontextualqueryinginadditivemanufacturing
AT olabodeajenifujah amgptalargelanguagemodelforcontextualqueryinginadditivemanufacturing
AT amirbaratifarimani amgptalargelanguagemodelforcontextualqueryinginadditivemanufacturing