Publicação

Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal

Ver documento

Detalhes bibliográficos
Resumo:This thesis presents the development of the Malus Chatbot, a Retrieval-Augmented Generation conversational agent designed to support apple cultivation in Portugal. Apple growers and stakeholders frequently face challenges accessing timely and reliable information due to the fragmented and unstructured nature of agricultural knowledge sources. While advances in Large Language Models have enabled significant improvements in natural language understanding, most existing agricultural chatbots remain limited by static or rulebased approaches, resulting in outdated or generic responses. The Malus Chatbot addresses this gap by combining a curated, domain-specific knowledge base with advanced retrieval and generation techniques to provide contextually relevant, evidence-based answers. Uniquely, the system can extract and present visual information like the figures and tables from source documents and offers direct links to these sources alongside each answer, supporting transparency and user verification. The system employs state-of-the-art embeddings, a hybrid retrieval strategy, and the GPT-4.1-mini language model to generate accurate and informative responses. Evaluation of the chatbot was carried out using RAGAS metrics and an expert provided question-answer dataset. Results demonstrate that the RAG-based approach substantially enhances answer quality, reliability, and source traceability compared to traditional methods. This work highlights the potential of retrieval-augmented conversational AI for advancing specialized knowledge access in agriculture and lays the foundation for future research in domain-adapted chatbot systems.
Autores principais:Chen, Zenan
Assunto:Retrieval-Augmented Generation Chatbot Generative AI Large Language Models Natural Language Processing Agricultural Informatics Apple Cultivation SDG 8 - Decent work and economic growth SDG 9 - Industry, innovation and infrastructure SDG 12 - Responsible production and consumption SDG 15 - Life on land
Ano:2025
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
_version_ 1868020826514653184
author Chen, Zenan
author_facet Chen, Zenan
author_role author
contributor_name_str_mv Jardim, João Bruno Morais de Sousa
Neto, Miguel de Castro Simões Ferreira
RUN
country_str PT
creators_json_txt [{\"Person.name\":\"Chen, Zenan\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Jardim, João Bruno Morais de Sousa
Neto, Miguel de Castro Simões Ferreira
RUN
datacite.creators.creator.creatorName.fl_str_mv Chen, Zenan
datacite.date.Accepted.fl_str_mv 2025-11-04T00:00:00Z
datacite.date.available.fl_str_mv 2025-11-18T16:09:56Z
datacite.date.embargoed.fl_str_mv 2025-11-18T16:09:56Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Retrieval-Augmented Generation
Chatbot
Generative AI
Large Language Models
Natural Language Processing
Agricultural Informatics
Apple Cultivation
SDG 8 - Decent work and economic growth
SDG 9 - Industry, innovation and infrastructure
SDG 12 - Responsible production and consumption
SDG 15 - Life on land
datacite.titles.title.fl_str_mv Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
dc.contributor.none.fl_str_mv Jardim, João Bruno Morais de Sousa
Neto, Miguel de Castro Simões Ferreira
RUN
dc.creator.none.fl_str_mv Chen, Zenan
dc.date.Accepted.fl_str_mv 2025-11-04T00:00:00Z
dc.date.available.fl_str_mv 2025-11-18T16:09:56Z
dc.date.embargoed.fl_str_mv 2025-11-18T16:09:56Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10362/190967
dc.language.none.fl_str_mv eng
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Retrieval-Augmented Generation
Chatbot
Generative AI
Large Language Models
Natural Language Processing
Agricultural Informatics
Apple Cultivation
SDG 8 - Decent work and economic growth
SDG 9 - Industry, innovation and infrastructure
SDG 12 - Responsible production and consumption
SDG 15 - Life on land
dc.title.fl_str_mv Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_bdcc
description This thesis presents the development of the Malus Chatbot, a Retrieval-Augmented Generation conversational agent designed to support apple cultivation in Portugal. Apple growers and stakeholders frequently face challenges accessing timely and reliable information due to the fragmented and unstructured nature of agricultural knowledge sources. While advances in Large Language Models have enabled significant improvements in natural language understanding, most existing agricultural chatbots remain limited by static or rulebased approaches, resulting in outdated or generic responses. The Malus Chatbot addresses this gap by combining a curated, domain-specific knowledge base with advanced retrieval and generation techniques to provide contextually relevant, evidence-based answers. Uniquely, the system can extract and present visual information like the figures and tables from source documents and offers direct links to these sources alongside each answer, supporting transparency and user verification. The system employs state-of-the-art embeddings, a hybrid retrieval strategy, and the GPT-4.1-mini language model to generate accurate and informative responses. Evaluation of the chatbot was carried out using RAGAS metrics and an expert provided question-answer dataset. Results demonstrate that the RAG-based approach substantially enhances answer quality, reliability, and source traceability compared to traditional methods. This work highlights the potential of retrieval-augmented conversational AI for advancing specialized knowledge access in agriculture and lays the foundation for future research in domain-adapted chatbot systems.
dirty 0
eu_rights_str_mv openAccess
format masterThesis
fulltext.url.fl_str_mv https://run.unl.pt/bitstreams/344549b1-4edd-4b9d-9d6a-307c0a27fb7e/download
id run_fc7a8a4c3cb0e85fa910af8bfcdd0dde
identifier.url.fl_str_mv http://hdl.handle.net/10362/190967
instacron_str unl
institution Universidade Nova de Lisboa
instname_str Universidade Nova de Lisboa
language eng
network_acronym_str run
network_name_str Repositório Institucional da UNL
oai_identifier_str oai:run.unl.pt:10362/190967
organization_str_mv urn:organizationAcronym:unl
person_str_mv Chen, Zenan
publishDate 2025
reponame_str Repositório Institucional da UNL
repository_id_str urn:repositoryAcronym:run
service_str_mv urn:repositoryAcronym:run
spelling engpt_PTThis thesis presents the development of the Malus Chatbot, a Retrieval-Augmented Generation conversational agent designed to support apple cultivation in Portugal. Apple growers and stakeholders frequently face challenges accessing timely and reliable information due to the fragmented and unstructured nature of agricultural knowledge sources. While advances in Large Language Models have enabled significant improvements in natural language understanding, most existing agricultural chatbots remain limited by static or rulebased approaches, resulting in outdated or generic responses. The Malus Chatbot addresses this gap by combining a curated, domain-specific knowledge base with advanced retrieval and generation techniques to provide contextually relevant, evidence-based answers. Uniquely, the system can extract and present visual information like the figures and tables from source documents and offers direct links to these sources alongside each answer, supporting transparency and user verification. The system employs state-of-the-art embeddings, a hybrid retrieval strategy, and the GPT-4.1-mini language model to generate accurate and informative responses. Evaluation of the chatbot was carried out using RAGAS metrics and an expert provided question-answer dataset. Results demonstrate that the RAG-based approach substantially enhances answer quality, reliability, and source traceability compared to traditional methods. This work highlights the potential of retrieval-augmented conversational AI for advancing specialized knowledge access in agriculture and lays the foundation for future research in domain-adapted chatbot systems.application/pdfpt_PTMalus Chatbot: A Chatbot for Apple Tree Cultivation in PortugalChen, ZenanJardim, João Bruno Morais de SousaNeto, Miguel de Castro Simões FerreiraHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptURNurn:tid:2040720002025-11-18T16:09:56Z2025-11-042025-11-04T00:00:00ZHandlehttp://hdl.handle.net/10362/190967http://purl.org/coar/access_right/c_abf2open accessRetrieval-Augmented GenerationChatbotGenerative AILarge Language ModelsNatural Language ProcessingAgricultural InformaticsApple CultivationSDG 8 - Decent work and economic growthSDG 9 - Industry, innovation and infrastructureSDG 12 - Responsible production and consumptionSDG 15 - Life on land1449911 bytesliteraturehttp://purl.org/coar/resource_type/c_bdccmaster thesis2025-11-04http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/344549b1-4edd-4b9d-9d6a-307c0a27fb7e/download
spellingShingle Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
Chen, Zenan
Retrieval-Augmented Generation
Chatbot
Generative AI
Large Language Models
Natural Language Processing
Agricultural Informatics
Apple Cultivation
SDG 8 - Decent work and economic growth
SDG 9 - Industry, innovation and infrastructure
SDG 12 - Responsible production and consumption
SDG 15 - Life on land
status SINGLETON
subject.fl_str_mv Retrieval-Augmented Generation
Chatbot
Generative AI
Large Language Models
Natural Language Processing
Agricultural Informatics
Apple Cultivation
SDG 8 - Decent work and economic growth
SDG 9 - Industry, innovation and infrastructure
SDG 12 - Responsible production and consumption
SDG 15 - Life on land
title Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
title_full Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
title_fullStr Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
title_full_unstemmed Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
title_short Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
title_sort Malus Chatbot: A Chatbot for Apple Tree Cultivation in Portugal
topic Retrieval-Augmented Generation
Chatbot
Generative AI
Large Language Models
Natural Language Processing
Agricultural Informatics
Apple Cultivation
SDG 8 - Decent work and economic growth
SDG 9 - Industry, innovation and infrastructure
SDG 12 - Responsible production and consumption
SDG 15 - Life on land
topic_facet Retrieval-Augmented Generation
Chatbot
Generative AI
Large Language Models
Natural Language Processing
Agricultural Informatics
Apple Cultivation
SDG 8 - Decent work and economic growth
SDG 9 - Industry, innovation and infrastructure
SDG 12 - Responsible production and consumption
SDG 15 - Life on land
url http://hdl.handle.net/10362/190967
visible 1