Prototype for Document Retrieval for the Military Police of Paraná with Retrieval Augmented Generation and Gemini AI in a Dockerized Environment
Prototype for Document Retrieval for the Military Police of Paraná with Retrieval Augmented Generation and Gemini AI in a Dockerized Environment
DOI:
https://doi.org/10.51473/rcmos.v1i2.2024.736Abstract
This paper presents the development of a prototype for document retrieval for the Military Police of Paraná (PMPR) using the Retrieval Augmented Generation (RAG) strategy and the Gemini AI Flash 1.5 language model. The prototype was implemented in a containerized environment with Docker, aiming to ensure portability and reproducibility. The RAG strategy combines traditional search with advanced language models to generate more accurate and complete answers to user queries. The prototype was tested with real questions and preliminary results demonstrate the system's ability to understand the questions and provide relevant answers, based on the information contained in the PMPR documents. The paper discusses the potential of the prototype to assist military police officers in accessing relevant information, overcoming the limitations of the current form of document retrieval in the institution.
Downloads
References
BAUMANN, P. et al. Large Language Models for Retrieval Augmented Generation: A Comprehensive Survey. arXiv preprint arXiv:2308.01186, 2023.
BOETTIGER, C. An introduction to Docker for reproducible research. ACM SIGOPS Operating Systems Review, v. 49, n. 1, p. 71-79, 2015.
BRASIL. Ministério da Justiça e Segurança Pública. Portaria nº 332, de 27 de abril de 2023. Dispõe sobre o Manual de Uso da Força Policial. Diário Oficial da União, Brasília, DF, 28 abr. 2023. Seção 1, p. 47.
LEWIS, P. et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, v. 33, p. 9459-9474, 2020.
N8N. n8n - Workflow Automation. Disponível em: https://n8n.io/. Acesso em: 06 nov. 2024.
QDRANT. Qdrant - Vector Database. Disponível em: https://qdrant.tech/. Acesso em: 06 nov. 2024.
Downloads
Additional Files
Published
Issue
Section
Categories
License
Copyright (c) 2024 Cleiton Giacomelli da Silva (Autor/in)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This means you are free to:
- Share — copy and redistribute the material in any medium or format.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
The use of this material is conditioned upon proper attribution to the original author(s), providing a link to the license, and indicating if changes were made. The license does not require permission from the author or the publisher as long as these conditions are met.
The Creative Commons license logo is displayed permanently in the footer of the journal.
The copyright of the manuscript can be retained by the authors without restrictions and can be requested at any time, even after publication in the journal.
How to Cite
