Development of local knowledge base application using retrieval augmented generation technology

Retrieval Augmented Generation (RAG) technology can enable large language models to access external knowledge bases by introducing external documents, thereby large language models can generate more authentic and reliable answers, and effectively solve the problems of outdated data and insufficient...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHU Junyi, ZHU Shangming
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2024-11-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024227/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841537100999032832
author ZHU Junyi
ZHU Shangming
author_facet ZHU Junyi
ZHU Shangming
author_sort ZHU Junyi
collection DOAJ
description Retrieval Augmented Generation (RAG) technology can enable large language models to access external knowledge bases by introducing external documents, thereby large language models can generate more authentic and reliable answers, and effectively solve the problems of outdated data and insufficient corpus. On the basis of introducing the basic architecture and fine-tuning techniques of large language models, the application framework of using retrieval enhanced generation technology to build a local knowledge base system was discussed. The application framework consisted of six parts: loading local documents, splitting documents, embedding splitting fragments, matching text based on questions, constructing prompts, and generating responses. Finally, based on the ERNIE-4.0 model and the AppBuilder development platform, an intelligent question answering system for campus information services was designed and developed, and a specific implementation was provided.
format Article
id doaj-art-9123383857df4e53baec03aa1ad19fa6
institution Kabale University
issn 1000-436X
language zho
publishDate 2024-11-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-9123383857df4e53baec03aa1ad19fa62025-01-14T08:46:45ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-11-014524224779661895Development of local knowledge base application using retrieval augmented generation technologyZHU JunyiZHU ShangmingRetrieval Augmented Generation (RAG) technology can enable large language models to access external knowledge bases by introducing external documents, thereby large language models can generate more authentic and reliable answers, and effectively solve the problems of outdated data and insufficient corpus. On the basis of introducing the basic architecture and fine-tuning techniques of large language models, the application framework of using retrieval enhanced generation technology to build a local knowledge base system was discussed. The application framework consisted of six parts: loading local documents, splitting documents, embedding splitting fragments, matching text based on questions, constructing prompts, and generating responses. Finally, based on the ERNIE-4.0 model and the AppBuilder development platform, an intelligent question answering system for campus information services was designed and developed, and a specific implementation was provided.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024227/large language modelretrieval augmented generationpromptlocal knowledge baseintelligent question answering system
spellingShingle ZHU Junyi
ZHU Shangming
Development of local knowledge base application using retrieval augmented generation technology
Tongxin xuebao
large language model
retrieval augmented generation
prompt
local knowledge base
intelligent question answering system
title Development of local knowledge base application using retrieval augmented generation technology
title_full Development of local knowledge base application using retrieval augmented generation technology
title_fullStr Development of local knowledge base application using retrieval augmented generation technology
title_full_unstemmed Development of local knowledge base application using retrieval augmented generation technology
title_short Development of local knowledge base application using retrieval augmented generation technology
title_sort development of local knowledge base application using retrieval augmented generation technology
topic large language model
retrieval augmented generation
prompt
local knowledge base
intelligent question answering system
url http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024227/
work_keys_str_mv AT zhujunyi developmentoflocalknowledgebaseapplicationusingretrievalaugmentedgenerationtechnology
AT zhushangming developmentoflocalknowledgebaseapplicationusingretrievalaugmentedgenerationtechnology