Technological advances have facilitated content creation, dissemination, and global content distribution almost immediately. Advances in large language models (LLMs) facilitate the development of natural language processing (NLP) applications such as Q&A systems. This work aims at developing a Q&A system based on a Retrieval Augmented Generation (RAG) architecture for the domain of tourism in Ecuador. The system design includes items such as user, query, embeddings, retrieval model, generative model, and finally, the answer generated by the system. The retrieval component searches for relevant information in the knowledge base created for the project, providing context to the generative models Meta-Llama-3-8B-Instruct and Gemma-7b-it to produce reliable and accurate answers. The results indicated a reasonable performance in information retrieval and a superiority of the Meta-Llama-3-8B-Instruct model in text prediction. The interface, developed with Streamlit, offers a friendly experience for users, allowing effective consultations about tourism in Ecuador.