Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. However, existing RAG research has focused on preventing unauthorized users from accessing sensitive data, while overlooking another important problem: external generators have access to the query and the retrieved documents, which may contain confidential information that could be misused or accessed for unintended purposes. This paper introduces the Sensitive Entity Alias Generator (SEAG), a privacy-preserving framework that empowers users to utilize powerful third-party generators without disclosing sensitive information. SEAG introduces a lightweight model that locates sensitive entities, generates corresponding aliases, and constructs an entity replacement table. The experimental results demonstrate the success of the SEAG framework. For the User metric, which measures the ability of the model to provide a correct response to the user while hiding sensitive information from the external generator, all SEAG models achieved over 80% accuracy. Blogger's Review: This paper proposes an effective privacy-preserving RAG framework that hides sensitive information to prevent external LLMs from misusing it. The experimental results demonstrate the success of the framework, providing a new approach to protecting user privacy.