Retrieval-Augmented Generation (RAG) systems have emerged as powerful tools for leveraging enterprise data to generate contextually relevant and accurate responses. However, building RAG systems with enterprise data poses several challenges that must be addressed to ensure their effectiveness and reliability. To begin with, data from enterprise data sources like document hubs, ticketing systems, intranet and internal data sources need to be pulled together. Structured and unstructured data need to be integrated into indexes. High quality retrieval is challenging, as one has to deal with enterprise vocabulary and user expectations. In this session, we will discuss these unique enterprise challenges for RAG and solutions to overcome them. We will share results from our real world experience on improving RAG for enterprises. Enterprise data scientists and AI managers will be able to learn a few best practices and leverage them in their organization.