In today's data-driven world, efficient data gathering and preparation are crucial for any application. Retrieval-Augmented Generation (RAG) relies heavily on well-structured and optimized data to function effectively. To prepare data for RAG, we need to collect information systematically using tools like Scrapy, extract relevant text content from HTML and PDF files, chunk the extracted text into manageable units, and embed these chunks in a high-dimensional vector space using the BAAI model BGE-M3. By following this process, we can ensure that our data is organized, optimized, and ready for use in RAG applications. This journey highlights the importance of efficient data gathering and processing techniques to unlock the full potential of RAG systems.