{"id":{"repo_id":"helsinki","oai_identifier":"oai:helda.helsinki.fi:10138/598631"},"canonical_url":"https://search.dev.ndltd.org/etd/helsinki/oai:helda.helsinki.fi:10138/598631","repository":{"repo_id":"helsinki","name":"University of Helsinki","base_url":"https://helda.helsinki.fi/server/oai/request"},"display":{"title":"Integrating Open-Source Retrieval-Augmented Generation with Large Language Models for Business, Market and Responsibility Insights","abstract":"This thesis investigates the integration of open-source retrieval-augmented generation (RAG) with large language models (LLMs) on the Databricks platform. The aim is to provide advanced insights in the fields of business, market, and responsibility intelligence. The research explores combining RAG and LLMs to improve business intelligence by leveraging internal and external data sources. The integrated system uses unstructured data such as market reports and customer feedback to offer deeper insights into market trends, consumer behavior, and corporate responsibilities and aid in company employees everyday work. Methodologically, the thesis focuses on system architecture, data source selection, and technical implementation within the Databricks environment. Use-cases such as expert assistance, market analysis, and customer feedback answering, demonstrating the practical benefits of these models for business operations are outlined. The research discusses technical challenges, evaluation strategies, and ethical considerations. The results emphasize how this integration aim to enhance data analysis and decision-making and to improve the ability to generate insights. The system’s applications at Metsä Tissue highlight the strategic and operational advantages of implementing RAG with LLMs. The thesis provides a roadmap for using advanced AI techniques to improve business intelligence in various domains while considering ethical implications and future research pathways. In the development of this master’s thesis, the advanced capabilities of ChatGPT-4 and ChatGPT 4o have been utilized to assist in various stages of the writing process. These language models aided in planning the structure contents of the thesis, rephrasing text to enhance clarity and coherence, and checking the grammar to ensure the quality of academic writing.","abstract_html":"This thesis investigates the integration of open-source retrieval-augmented generation (RAG) with large language models (LLMs) on the Databricks platform. The aim is to provide advanced insights in the fields of business, market, and responsibility intelligence. The research explores combining RAG and LLMs to improve business intelligence by leveraging internal and external data sources. The integrated system uses unstructured data such as market reports and customer feedback to offer deeper insights into market trends, consumer behavior, and corporate responsibilities and aid in company employees everyday work. Methodologically, the thesis focuses on system architecture, data source selection, and technical implementation within the Databricks environment. Use-cases such as expert assistance, market analysis, and customer feedback answering, demonstrating the practical benefits of these models for business operations are outlined. The research discusses technical challenges, evaluation strategies, and ethical considerations. The results emphasize how this integration aim to enhance data analysis and decision-making and to improve the ability to generate insights. The system’s applications at Metsä Tissue highlight the strategic and operational advantages of implementing RAG with LLMs. The thesis provides a roadmap for using advanced AI techniques to improve business intelligence in various domains while considering ethical implications and future research pathways. In the development of this master’s thesis, the advanced capabilities of ChatGPT-4 and ChatGPT 4o have been utilized to assist in various stages of the writing process. These language models aided in planning the structure contents of the thesis, rephrasing text to enhance clarity and coherence, and checking the grammar to ensure the quality of academic writing.","abstract_has_math":false,"creators":["Roinisto, Henna"],"institution":"Helsingin yliopisto","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta","University of Helsinki, Faculty of Science","Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T19:56:09Z","subjects":["large language models","retrieval-augmented generation","Databricks","business intelligence"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["URN:NBN:fi:hulib-202507013357"],"render_values":[{"text":"URN:NBN:fi:hulib-202507013357","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10138/598631","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta","University of Helsinki, Faculty of Science","Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten"]},{"key":"dc:creator","label":"Author","values":["Roinisto, Henna"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["Helsingin yliopisto","University of Helsinki","Helsingfors universitet"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["large language models","retrieval-augmented generation","Databricks","business intelligence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["URN:NBN:fi:hulib-202507013357","http://hdl.handle.net/10138/598631"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis investigates the integration of open-source retrieval-augmented generation (RAG) with large language models (LLMs) on the Databricks platform. The aim is to provide advanced insights in the fields of business, market, and responsibility intelligence. The research explores combining RAG and LLMs to improve business intelligence by leveraging internal and external data sources. The integrated system uses unstructured data such as market reports and customer feedback to offer deeper insights into market trends, consumer behavior, and corporate responsibilities and aid in company employees everyday work. Methodologically, the thesis focuses on system architecture, data source selection, and technical implementation within the Databricks environment. Use-cases such as expert assistance, market analysis, and customer feedback answering, demonstrating the practical benefits of these models for business operations are outlined. The research discusses technical challenges, evaluation strategies, and ethical considerations. The results emphasize how this integration aim to enhance data analysis and decision-making and to improve the ability to generate insights. The system’s applications at Metsä Tissue highlight the strategic and operational advantages of implementing RAG with LLMs. The thesis provides a roadmap for using advanced AI techniques to improve business intelligence in various domains while considering ethical implications and future research pathways. In the development of this master’s thesis, the advanced capabilities of ChatGPT-4 and ChatGPT 4o have been utilized to assist in various stages of the writing process. These language models aided in planning the structure contents of the thesis, rephrasing text to enhance clarity and coherence, and checking the grammar to ensure the quality of academic writing."]},{"key":"dc:title","label":"Title","values":["Integrating Open-Source Retrieval-Augmented Generation with Large Language Models for Business, Market and Responsibility Insights"]}]}],"canonical_facts":{"dc:contributor":["Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta","University of Helsinki, Faculty of Science","Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten"],"dc:creator":["Roinisto, Henna"],"dc:date.issued":["2024"],"dc:description.abstract":["This thesis investigates the integration of open-source retrieval-augmented generation (RAG) with large language models (LLMs) on the Databricks platform. The aim is to provide advanced insights in the fields of business, market, and responsibility intelligence. The research explores combining RAG and LLMs to improve business intelligence by leveraging internal and external data sources. The integrated system uses unstructured data such as market reports and customer feedback to offer deeper insights into market trends, consumer behavior, and corporate responsibilities and aid in company employees everyday work. Methodologically, the thesis focuses on system architecture, data source selection, and technical implementation within the Databricks environment. Use-cases such as expert assistance, market analysis, and customer feedback answering, demonstrating the practical benefits of these models for business operations are outlined. The research discusses technical challenges, evaluation strategies, and ethical considerations. The results emphasize how this integration aim to enhance data analysis and decision-making and to improve the ability to generate insights. The system’s applications at Metsä Tissue highlight the strategic and operational advantages of implementing RAG with LLMs. The thesis provides a roadmap for using advanced AI techniques to improve business intelligence in various domains while considering ethical implications and future research pathways. In the development of this master’s thesis, the advanced capabilities of ChatGPT-4 and ChatGPT 4o have been utilized to assist in various stages of the writing process. These language models aided in planning the structure contents of the thesis, rephrasing text to enhance clarity and coherence, and checking the grammar to ensure the quality of academic writing."],"dc:identifier.uri":["URN:NBN:fi:hulib-202507013357","http://hdl.handle.net/10138/598631"],"dc:language.iso":["eng"],"dc:publisher":["Helsingin yliopisto","University of Helsinki","Helsingfors universitet"],"dc:subject":["large language models","retrieval-augmented generation","Databricks","business intelligence"],"dc:title":["Integrating Open-Source Retrieval-Augmented Generation with Large Language Models for Business, Market and Responsibility Insights"]},"updated_at":"2026-07-27T19:56:09Z"}