In the world of online food delivery, user search queries are often vague, incomplete, or noisy — like "best pizza", "veg thali under 200", or "birynai" (yes, with a typo). This talk explores how Retrieval-Augmented Generation (RAG) can help rewrite such queries into more precise and intent-aware forms, improving both relevance and user experience. We’ll cover the core concepts behind RAG, how it combines external retrieval with generative language models, and how it compares to traditional query rewriting approaches. The session will wrap up with a hands-on demo showcasing a real-world use case in the online food delivery space, illustrating how RAG can be used to bridge the gap between user intent and search results.