Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2025
License: CC BY NC ND
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

Técnicas de lenguaje natural aplicadas a consultas documentales

Authors: León Martín, Javier;

Técnicas de lenguaje natural aplicadas a consultas documentales

Abstract

La inteligencia artificial generativa, y en particular los modelos de lenguaje de gran tamaño (LLMs), han transformado radicalmente la manera en que los seres humanos interactúan con la información. Este Trabajo Fin de Grado presenta el desarrollo de una aplicación web que permite a los usuarios subir documentos en formato PDF y realizar consultas en lenguaje natural sobre su contenido. La aplicación implementa la técnica de Retrieval-Augmented Generation (RAG), que combina recuperación semántica mediante embeddings vectoriales con generación de respuestas contextualizadas por parte de un modelo de lenguaje. Todo el proceso se ejecuta en entornos locales mediante la herramienta Ollama, lo que garantiza la privacidad de los datos y la independencia de servicios en la nube. Los resultados obtenidos muestran que el sistema es funcional, extensible y aplicable en entornos académicos y profesionales, aunque presenta limitaciones de rendimiento en equipos sin GPU dedicada NVIDIA.

Generative artificial intelligence, and in particular Large Language Models (LLMs), have radically transformed the way humans interact with information. This Final Degree Project presents the development of a web application that allows users to upload PDF documents and perform natural language queries about their content. The application implements the technique of Retrieval-Augmented Generation (RAG), which combines semantic retrieval through vector embeddings with the generation of contextualized responses by a language model. The entire process is executed locally using the Ollama tool, ensuring data privacy and independence from cloud services. The results obtained show that the system is functional, extensible, and applicable in academic and professional environments, although it presents performance limitations on systems without a dedicated NVIDIA GPU.

Grado en Ingeniería Telemática

Country
Spain
Related Organizations
Keywords

LLM, Informática, pgvector, Ollama, Procesamiento de lenguaje natural, Natural language processing, RAG, Computer science, Chatbot, Embeddings

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green
Related to Research communities