We built a high-performance hybrid search using SingleStore in our gen AI eStore app, which loads the dashboard in under two seconds by executing five parallel queries that simultaneously read over 100 million rows. The app provides a text-to-SQL chat experience and performs a hybrid (vector + exact keyword match) search to find clothing products for users' needs. It also features conversational interface agentic widgets for purchasing and rating products, and maintains efficient performance while performing multiple function calls. We created a single database with a "products" table that uses vector columns and full-text keys for the hybrid search query, which accepts optional parameters like color, price, and size. The query performs a vector search over the product title and description vectors, as well as a full-text search over the description column, to find relevant products.