Arquitectura RAG para el Contexto en PLN Generación y Acceso Inteligente de Datos

Gonzalez Torres, Daniel Leonardo; Santa Quintero, Ricardo Andres

Arquitectura RAG para el Contexto en PLN Generación y Acceso Inteligente de Datos

dc.contributor.advisor	Gonzalez Torres, Daniel Leonardo
dc.contributor.advisor	Santa Quintero, Ricardo Andres
dc.contributor.author	Gonzalez Torres, Daniel Leonardo
dc.contributor.author	Santa Quintero, Ricardo Andres
dc.coverage.spatial	Bogotá	spa
dc.creator.email	daniell-gonzalezt@unilibre.edu.co	spa
dc.creator.email	ricardoa.santaq@unilibre.edu.co	spa
dc.date.accessioned	2025-06-04T15:32:03Z
dc.date.available	2025-06-04T15:32:03Z
dc.date.created	2025-03-06
dc.description.abstract	Este artículo explora en profundidad la integración de técnicas avanzadas de machine learning mediante la metodología Retrieval Augmented Generation (RAG). Se analiza la arquitectura dual que combina procesos de recuperación y generación de información, resaltando su impacto en el entrenamiento de modelos de lenguaje natural. Asimismo, se presentan variantes especializadas como el Corrective RAG y el Advanced RAG, que incorporan mecanismos de retroalimentación y optimización en tiempo real. Se incluye, además, una mención del producto JurislibreIA, desarrollado por el semillero Sensorama, ejemplificando aplicaciones prácticas en dominios complejos como el legal. El estudio se fundamenta en ejemplos de implementación en Python, diagramas explicativos y una revisión crítica de las fuentes relevantes, ofreciendo una guía completa para investigadores y desarrolladores interesados en impulsar soluciones innovadoras basadas en RAG.	spa
dc.description.abstractenglish	This article explores in depth the integration of advanced machine learning techniques using the Retrieval Augmented Generation (RAG) methodology. The dual architecture that combines information retrieval and generation processes is analyzed, highlighting its impact on the training of natural language models. Likewise, specialized variants such as Corrective RAG and Advanced RAG are presented, which incorporate real-time feedback and optimization mechanisms. Also included a mention of the JurislibreIA product, developed by the Sensorama research group, exemplifying practical applications in complex domains such as the legal one. The study is based on implementation examples in Python, explanatory diagrams and a critical review of relevant sources, offering a complete guide for researchers and developers interested in promoting innovative solutions based on RAG.	spa
dc.description.sponsorship	Universidad Libre -- Ingenieria -- Ingenieria de sistemas	spa
dc.format	PDF	spa
dc.identifier.uri	https://hdl.handle.net/10901/31241
dc.relation.references	P. Lewis, et al., "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks," Advances in Neural Information Processing Systems (NeurIPS), 2020.	spa
dc.relation.references	J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," Proc. of NAACL, 2018.	spa
dc.relation.references	T. Mikolov, et al., "Distributed Representations of Words and Phrases and their Compositionality," Advances in Neural Information Processing Systems (NeurIPS), 2013.	spa
dc.relation.references	A. Vaswani, et al., "Attention is All You Need," Advances in Neural Information Processing Systems (NeurIPS), 2017.	spa
dc.relation.references	I. Sutskever, O. Vinyals, and Q. V. Le, "Sequence to Sequence Learning with Neural Networks," Advances in Neural Information Processing Systems (NeurIPS), 2014.	spa
dc.relation.references	S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.	spa
dc.relation.references	Y. Kim, "Convolutional Neural Networks for Sentence Classification," Proc. of EMNLP, 2014.	spa
dc.relation.references	R. Johnson, et al., "Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation," arXiv:1609.08144, 2016.	spa
dc.relation.references	Z. Yang, et al., "XLNet: Generalized Autoregressive Pretraining for Language Understanding," Advances in Neural Information Processing Systems (NeurIPS), 2019.	spa
dc.relation.references	K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Proc. of CVPR, 2016.	spa
dc.relation.references	M. Abadi, et al., "TensorFlow: A System for Large-Scale Machine Learning," Proc. of OSDI, 2016.	spa
dc.relation.references	F. Chollet, "Keras," GitHub repository, 2015. [Online]. Available: https://github.com/keras-team/keras.	spa
dc.relation.references	P. Russell and S. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed. Prentice Hall, 2010.	spa
dc.relation.references	S. Bengio and Y. LeCun, "Scaling Learning Algorithms towards AI," in Large-Scale Kernel Machines, 2007.	spa
dc.relation.references	Hugging Face, "Retrieval-Augmented Generation (RAG)," [Online]. Available: https://huggingface.co/docs/transformers/model_doc/rag Accessed: Feb. 18, 2025.	spa
dc.rights.accessrights	info:eu-repo/semantics/openAccess	spa
dc.rights.coar	http://purl.org/coar/access_right/c_abf2	spa
dc.rights.license	Atribución-NoComercial-SinDerivadas 2.5 Colombia	spa
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/2.5/co/	spa
dc.subject	Retrieval Augmented Generation (RAG)	spa
dc.subject	Machine Learning	spa
dc.subject	Natural Language Processing (NLP)	spa
dc.subject	Corrective RAG	spa
dc.subject	Advanced RAG	spa
dc.subject	JurislibreIA	spa
dc.subject	Sensorama	spa
dc.subject	Bases de Datos Vectoriales	spa
dc.subject	Grafos	spa
dc.subject	Modelos de Lenguaje (LLM)	spa
dc.subject.lemb	Gestión de datos	spa
dc.subject.subjectenglish	Retrieval Augmented Generation (RAG)	spa
dc.subject.subjectenglish	Machine Learning	spa
dc.subject.subjectenglish	Natural Language Processing (NLP)	spa
dc.subject.subjectenglish	Corrective RAG	spa
dc.subject.subjectenglish	Advanced RAG	spa
dc.subject.subjectenglish	JurislibreIA	spa
dc.subject.subjectenglish	Sensorama	spa
dc.subject.subjectenglish	Vector database	spa
dc.subject.subjectenglish	Graph	spa
dc.subject.subjectenglish	Language Models (LLM)	spa
dc.title	Arquitectura RAG para el Contexto en PLN Generación y Acceso Inteligente de Datos	spa
dc.title.alternative	Written Work: RAG Architecture for Context in NLP: Intelligent Data Generation and Access	spa
dc.type.coar	http://purl.org/coar/resource_type/c_7a1f	spa
dc.type.driver	info:eu-repo/semantics/bachelorThesis	spa
dc.type.hasversion	info:eu-repo/semantics/acceptedVersion	spa
dc.type.local	Tesis de Pregrado	spa

Archivos

Bloque original

Mostrando 1 - 2 de 2

Nombre:: Trabajo Escrito Arquitectura RAG para el Contexto en PLN Generación y Acceso Inteligente de Datos.pdf
Tamaño:: 694.8 KB
Formato:: Adobe Portable Document Format
Descripción:

Descargar

Nombre:: Formato autorización PUBLICACIÓN DE OBRAS - Trabajo Escrito Arquitectura RAG para el Contexto en PLN Generación y Acceso Inteligente de Datos.pdf
Tamaño:: 182.79 KB
Formato:: Adobe Portable Document Format
Descripción:

Descargar

Bloque de licencias

Mostrando 1 - 1 de 1

Nombre:: license.txt
Tamaño:: 1.71 KB
Formato:: Item-specific license agreed upon to submission
Descripción:

Descargar

Colecciones

Sensorama