With the development of digital learning environments, the internet has become the primary source for learners to access educational materials. However, the vast and ever-growing amount of information online leads to serious information overload. Although traditional search engines can filter out some irrelevant content, they still rely on string matching and fail to provide accurate content difficulty matching based on learners’ needs. The extracted search results only contain partial content with keywords, making it difficult to quickly understand key points. As a result, learners have to spend a lot of time reading and filtering, leading to low retrieval efficiency. Against this backdrop, this study integrates generative AI with Retrieval-Augmented Generation technology to provide a more precise and efficient retrieval method. Users can filter based on semantic conditions and quickly focus on content that meets their needs. This not only solves the information overload problem but also offers more personalized and relevant search results. Additionally, the system can automatically generate summaries based on user needs, condensing large amounts of material into clear and structured presentations, helping learners quickly understand key points. The generated summaries, evaluated by experts, received positive feedback, and users also gave positive reviews of the system's usability. Combining generative AI with Retrieval-Augmented Generation technology helps learners filter out the most suitable content and effectively addresses information overload, enhancing the presentation of material summaries for a more efficient and personalized learning experience.