Protótipo de Pesquisa Documental para a Polícia Militar do Paraná com Retrieval Augmented Generation e Gemini AI em Ambiente Dockerizado

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.