RAG-FiT is a powerful tool aimed at enhancing large language models (LLMs) through Retrieval-Augmented Generation (RAG) techniques. It assists models in better utilizing external information by creating specialized RAG-enhanced datasets. This library supports the complete workflow from data preparation to model training, inference, and evaluation. Key advantages include modular design, customizable workflows, and support for various RAG configurations. RAG-FiT is open-source and suitable for rapid prototyping and experimentation by researchers and developers.